稀疏编码SIFT特征在植物图像分类中的应用(IJIGSP-V9-N10-6)
I.J. Image, Graphics and Signal Processing, 2017, 10, 50-59
Published Online October 2017 in MECS (https://www.wendangku.net/doc/351031913.html,/)
DOI: 10.5815/ijigsp.2017.10.06
Application of Sparse Coded SIFT Features for Classification of Plant Images
Suchit Purohit
Department of Computer Science Gujarat University Ahmedabad, India
Email: Suchit.s.purohit@https://www.wendangku.net/doc/351031913.html,
Savita R. Gandhi
Department of Computer Science Gujarat University Ahmedabad, India
Email: drsavitagandhi@https://www.wendangku.net/doc/351031913.html,
Received: 26 May 2017; Accepted: 15 June 2017; Published: 08 October 2017 Abstract—Automated system for plant species
recognition is need of today since manual taxonomy is cumbersome, tedious, time consuming, expensive and suffers from perceptual biasness as well as taxonomic impediment. Availability of digitized databases with high resolution plant images annotated with metadata like date and time, lat long information has increased the interest in development of automated systems for plant taxonomy. Most of the approaches work only on a particular organ of the plant like leaf, bark or flowers and utilize only contextual information stored in the image which is time dependent whereas other metadata associated should also be considered. Motivated from the need of automation of plant species recognition and availability of digital databases of plants, we propose an image based identification of species of plant when the image may belong to different plant parts such as leaf, stem or flower, fruit , scanned leaf, branch and the entire plant. Besides using image content, our system also uses metadata associated with images like latitude, longitude and date of capturing to ease the identification process and obtain more accurate results. For a given image of plant and associated metadata, the system recognizes the species of the given plant image and produces an output that contains the Family, Genus, and Species name. Different methods for recognition of the species are used according to the part of the plant to which the image belongs to. For flower category, fusion of shape, color and texture features are used. For other categories like stem, fruit, leaf and leafscan, sparsely coded SIFT features pooled with Spatial pyramid matching approach is used. The proposed framework is implemented and tested on ImageClef data with 50 different classes of species. Maximum accuracy of 98% is attained in leaf scan sub-category whereas minimum accuracy is achieved in fruit sub-category which is 67.3 %.
Index Terms—SIFT; Sparse Coding; Plant Species; Content based retrievel; Spatial Pyramid matching, HSV color space, Texture fetaures extraction
I.I NTRODUCTION
Plant Taxonomy is a science to separate plants into similar groups based on the characteristics like color of the flower, shape of the flower, leaf shape and form, fruits, bark of the stem etc. Plant recognition when done manually by specialized taxonomists, suffers from perceptual biasness, cost of hiring of experts and shortage of experts (‘‘taxonomic impediment’’) [1]. The process of manual taxonomy becomes time consuming and tedious when more and more images are added to the database. Automation of the recognition process can improve the time, efficiency, accuracy and cost associated with the recognition process. This has given rise to the demand of automatic tools for plant species recognition and classification. Major support system for the automation is availability of digitized databases with high resolution plant images annotated with species names and metadata like date and time, lat long information aided by high resolution cameras available on handheld devices. Royal Botanic Gardens, Kew provides a digital catalogue of over 200,000 high-resolution images, with more being added continuously as part of an ongoing digitization project. Motivated from availability of pictures of plants in digital format and need of automation, we propose an automatic plant classification system using techniques from image processing, computer vision and machine learning fields. The current approaches for plant species identification utilize either only leaf form and shape [2]-[12 or combination of leaf and bark [13] or color, shape and texture of the flowers [14]-[19] to identify the species of the plant. This paper presents a system that identifies the species of the plant based on the information provided by different parts of the plants like leaf, flower, fruit and bark of the stem. The major contributions to this paper are:
1.An automatic plant species recognition framework
which considers different organs of the plant
like leaf, flower, fruit, and bark to identify the
species while including seasonal and topographic
parameters in classification. The uniqueness of
the framework is that for different parts of the
plants different techniques are used. The system
along with the test image identifies the part of the
plant through meta data provided with the image
and then dynamically selects the technique
according to the part of the plant. The appropriate
technique according to the particular organ of the
plant has been decided after careful and rigorous
testing.
2.Existing leaf detection approaches utilize global
features of leaf like diameter, length, width, area,
perimeter, aspect ratio, eccentricity etc. which
require domain knowledge. In contrast our
proposed approach based on sparsely coded SIFT
features automatically generates features and
classify the images without knowledge of domain
that too with an exceptional accuracy of 98%.
3.Sparsely coded SIFT representation approach
makes the classification robust in cluttered
environment like flower amongst leaves, images
with objects of different orientation like horizontal
and vertical stem images, images corrupted with
noise.
II.R ELATED W ORK
Most of the work done on plant species recognition works on leaf images of plant. A number of project-systems namely Leafsnap in America [2], CLOVER [4] in Asia, Pl@ntNet[5], ReVes[6] and ENVIROFI [7] in Europe are based on leaf identification to recognize the species. These approaches utilize global features of leaves like color ,texture (entropy, energy, contrast) , shape (eccentricity, circularity , aspect ratio, rectangularity) and applied them to different classification approaches to identify the species. The problem with these approaches is that leaves of many plants like decidous trees are not available throughout the year. Moreover the leaves may be too young or may be too distorted or less informative as large banana leaves, needles in pine trees etc. To refine the leaf approach, Zuolin ZHAO proposed the method for recognizing plants by combining leaf and bark features together. The characteristic parameters of leaves and bark were extracted based on background segmentation and filtering method, and plants were recognized using SVM [13]. Zisserman proposed flower classification approach based on combined vocabulary of shape, texture color features. The system was tested on 103 classes [14]-[15]. Wenjing Qi, et al. suggested the idea of flower classification based on local and spatial cues with help of SIFT feature descriptors [16]. Yong Pei and Weiqun Cao provided the application of neural network for performing digital image processing for understanding the regional features based on shape of a flower [17]. Salahuddin et al. proposed an efficient segmentation method which combines color clustering and domain knowledge for extracting flower regions from flower images [18]. D S Guru et al. developed an algorithmic model for automatic flowers classification using KNN as the classifier [19]. But flowers have limitation that it is difficult to analyze shapes and structures of flowers since they have complex 3D structures. Naiara, Javier presented an automatic system for the identification of plants based on the content of images and metadata associated to them. The classification has been defined as a classification plus fusion solution [20].The authors of [21] have combined different views of plant organs (such as flowers, bark, leaves) using a late fusion process for efficient plant classification process.
III.D ATA S ET
In this study, ImageCLEF 2015 [40] data is used which focuses on 1000 herb, tree and fern species centered on France and neighbouring countries. Seven types of image content are considered: scan and scan-like pictures(free from background) of leaf, and 6 kinds of images of different organs of the plant taken from different views like Flower, fruit, stem and bark, branch, leaf and entire view. The data set is built through a crowd sourcing initiative conducted by T e l a Botanica and covers 1000 species [22]. The dataset contains 1,13,204 images provided for training. Each image is associated with an xml file containing contextual meta data described as below:
“ObservationId: Plant observation ID from which several pictures can be associated.
o FileName: Name of the image file with which it is associated.
o Content: Branch, Entire, Flower, Fruit, Leaf, LeafScan, Stem.
o ClassId: Class number ID that must be used as ground-truth. It is a numerical taxonomical number
used by Tela Botanica.
o Species: Species names (containing 3 parts: the Genus name, the Species name, and the author who
discovered or revised the name of the species).
o Genus: Name of the Genus, one level above the Speciesin the taxonomical hierarchy used by Tela
Botanica.
o Family: Name of the Family, two levels above the Speciesin the taxonomical hierarchy used by Tela
Botanica.
o Date: (if available) Date when the plant was observed.
o Vote: (round up) Average of the user ratings on image quality.
o Locality: (if available) Locality name, most of the time a town.
o Latitude & Longitude: (if available) GPS coordinates of the observation or the towns” [40].
Fig. 1 shows a sample picture of plant. The xml file of the same is as follows:
Fig.1. Sample Image
Due to unavailability of hardware resources, we have used 10 classes for classification purpose with five organs of plant in each class. Since supervised learning has been employed in our proposed framework, more and more images are required for training to achieve better results. So we have chosen top 10 species with maximum number of images provided in training. We have taken 75 images per species for flower, leaf and leafscan category whereas 50 images per class are taken for fruit and stem category. 25 images per class have been used for testing.
IV.M ETHODOLOGY
The species recognition process is implemented as a classic Image Classification problem. Image classification algorithms classify the objects based on their visual/semantic content described by features. The features can be global like colour, shape, texture and describe the image as a whole whereas local features describes local patches. Initial researches in Image classification were based on pixel based global features like colour, texture, shape, histogram etc. The global features are found to be affected significantly by various illumination effects, viewing angles, noise and other distortions and it is found that classifiers based on global features lack in accuracy. Hence recent researches are focusing on classification based on local features for quantification of visual information present in the image [24].We have used both global and local features subjective to the category of the plant image belongs to . The choice of features had been inferred through extensive testing of both the approaches for different categories. It was concluded that sparsely coded SIFT features approach gives best accuracy for leaf and leaf scan like images, images of stem/bark and fruits categories whereas colour and texture are additional discriminative features required for flowers. The framework is described in Fig. 2. The next two sub-sections explain both the approaches in detail.
Fig.2.Framework of recognition system
A.Sparse coded SIFT feature representation
A good local feature should be easy to extract, distinctive, repetitive, invariant and robust to noise occlusion and clutter. A survey o n local features has proved the superiority of a local feature detector and descriptor founded by David Lowe popularly known as known as SIFT or Scale Invariant Feature Transform. SIFT was founded in 1999 and summarized in 2004. “Sc ale Invariant Feature Transform is a method for extracting distinctive features from images which are invariant to image scale and rotation and provide robust matching in the presence of some affine transformations, change in viewpoint, addition of noise and change in illumination”[23]. SIFT descriptor calculates value of 4X4 grid around feature points from eight directions, which is 128-bit feature vector and many features are detected from each image (Fig 3(b)). It is evident from the picture that the SIFT algorithm rejects keypoints from the low contrast areas like background which is helpful when the object of interest is present in the cluttered environment. Due to rotational invariance, SIFT also reduces the ambiguity in case of stem images which
can be vertical or horizontal.
(a)
(b)
Fig.3. (a) Original Image. (b) SIFT features extracted from the image
while leaving the background environment
The classifiers expect the image to be described as a single vector, hence the SIFT vectors need to be quantized. One of the popular approaches is Bag-of-visual words in which the features are quantized using flat k-means or hierarchical k-means and then computes the histogram for semantic classification [27] .The discriminatory power of Bag-of- words suffers due to quantization errors and loss of spatial order of descriptors. An extension of Bag-of-features model was proposed in [28] called Spatial pyramid matching. It segments image into 2lX2l segments in different scale l=0,1, 2 and computes BoF histograms in each segment, and finally concatenates them to form a vector representation of the image. This algorithm is widely used in many computer vision applications, but problem of one or more vocabularies still exists, hence we have used Sparse coding to compress and quantize SIFT vectors.
Sparse coding is a representation of data as a linear combination of atoms (patterns) learned from the data itself. Such a collection of atoms (code words) is called dictionary or codebooks [29]. For an input X,
D = {d1, d2, d3… dp } (1)
Dictionary D is set of normalized basis column vectors of size p such that there exists a vector α known as sparse coefficient vector α such that
X=Dα (2)
Where α should be as sparse as possible, i.e. most of the entries in α should be zero.
Sparse representation is more compact and high level representation of the image. As compared with vector quantization, sparse coding has a low reconstruction error, more separable in high dimensional spaces making them suitable for classification purposes. It can be seen in Fig. 4 that SIFT features before sparse coding occupied memory of 20GB whereas the memory reduced to 1 GB after sparse coding. The last years have witnessed an increase in computer vision algorithms that
utilize sparse coding survey of which is presented in [29]. Success of sparse coding depends on selection of dictionary. One approach to choose Dictionary D is to choose from known transform (steerable wavelet, coverlet, contourlet, bandlets) These off-the-shelf dictionaries fails for specific images like face, digits, etc. [39] therefore current researches are focusing on learning the dictionary from a set of given input sample. The approach is known as Dictionary learning. Given a set of SIFT features , K random features are selected to train the dictionary using following optimization.
()
2
2,min k y Y a y Da a λ?∈-+Ω (3)
A lot of research has been noticed in recent years in development of dictionary learning algorithms some of which are K-SVD of Aharon [38], Olshausen and field [18], SPAMS of Mairal [33] and others [34], [35], [36], [39]. Yang in 2011 proposed Fisher Discriminative Dictionary learning which instead of learning a common dictionary to all classes, learns a structured dictionary D as [D1, D2, D3… DC] where c is the number of classes hence increasing the discriminative power. The performance was reported to be highest using this learning method in terms of high recognition rate and low error rate. We have used Mairal ’s online dictionary which is available in SPAMS a Sparse modeling software containing an optimization toolbox for various sparse estimation problems. Once the dictionary is learnt from eq. (1), it is applied to code all SIFT vectors in all images and sparse representation is generated via following optimization.
()
22111min ,2k k k k D a y Da a k λ=??
-+Ω????
∑ (4)
Therefore, for every SIFT vector, a sparse vector is learnt which are pooled using Spatial Pyramid matching before feeding to the classifier.
The sparse vectors obtained from eq 2 are max-pooled according to technique described in 28.Hence a spatial pyramid representation of the image which has 1024X21 dimensions uniform throughout all the images suitable to be fed into the classifier. The flow chart of the process is shown in Fig 6.
Fig.4. Memory occupied by SIFT features has reduced by 20 times
after applying sparse coding.
Fig.5. Framework for identification of species using leaf, bark, fruit
images
B. Fusion of shape,color and texture features
As already mentioned, the most distinguishing characteristics of a flower image are the shape, color and texture. Using only one of these features do not provide accurate results since there can be more than specieshaving same colour, shape and texture. So we have used combination of all three features to represent flower images. To compact the features, we have used Bag-of-features approach to create visual vocabularies which are combined and fed into classifier as shown in Fig. 6.
Fig.6. Identification of species using flower image
The steps are summarized as:
?Segmentation is done to extract the flower image from the background(Fig 9)
?Color features are extracted from HSV (Hue, Saturation and Value) color model since it is less
sensitive to illumination variations. Color visual
words are created by clustering the HSV value of
each pixel.
?Shape features are extracted by SIFT representation and then clustered using bag-of-
words approach. SIFT feature representation
makes the approach robust against noise and
occlusion as well reduces effects of rotation and
scaling variances (Fig 3(b)).
?To find textures on the petals of the flowers, texture features are extracted by convolving the
images with rotational invariant filters from an
MR8 (Maximum Response) filter bank (Fig 8).
?All the vocabularies are combined into single vocabulary and fed to SVM classifier.
Fig.7. Textures extracted from flower image
Fig.8. Flower image before and after segmentation
V.E XPERIMENTS FOR P ARAMETER S ETTING
To implement the above techniques, experiments have been conducted for making the following decisions: Choice of classifier (SVM/knn)
?Fixing upon particular size of image to maintain uniformity since all the images are with different
sizes
?Experiments to decide upon number of sample features to train the dictionary for sparse coding
?Number of iterations in sparse coding
?Choice of approach to be followed for each category
The results and analysis of these experiments are as follows:
A. Experiments for choice of classifier
Table 1. Performance comparison of SVM and knn
From table 1, we can observe that on increasing the number of training images the accuracy increases using both of the classifier SVM and KNN. After the number of images for training reached to 250 per class the accuracy of SVM classifier reached to 100%. Another observation derived was that though SVM gives higher accuracy than that of knn but it ALSO takes more time than knn.
Table 2. Performance comparison of SVM and knn
From above table 2 , we conclude that that the accuracy for both SVM and knn reduces as number of classes increase but it is yet relatively more while using SVM. Looking at the accuracy efficiency of SVM from above observations, we set SVM as choice of classifier. B. Experiment for size of image
Table 3. Effect of image size on accuracy
From the above table we observed that decreasing size of image does not reduce the accuracy. Infact on reducing the size from 400 to 300, accuracy is showing increase. Time taken for smaller size image is less because for smaller images less features are extracted resulting in less processing time during testing and training. Smaller size of image, less the number features extracted, reducing memory requirements.
C. Experiments for number of random samples for
training the dictionary
Table 4. Number of random samples Vs accuracy The dictionary learning takes random number of samples from the large dataset of the features extracted. From the above table and the graph we can observe that keeping the random number of samples higher does not increase the accuracy. The results of the experiment are fluctuating yet a stable increase in performance is observed around 1.75 to 2 %. So, we decided to keep the number of random samples as less as 2% of the total number of features extracted from the Images.
D. Experiments on number of iterations in dictionary
learning
Table 5. Number of Iterations Vs accuracy
This experiment is for the number of iterations while learning dictionary. Dictionary is updated in each iteration of dictionary learning. The more the number of iteration, the more time it takes for dictionary learning. So, to maintain tradeoff between accuracy and time, we set number of iterations to 10.
E.Experiments to decide on choice of approach
The above table shows the experimental results that compares the different approaches for classification, i.e. Color, Shape, Texture Based classification or Pixel based classification or sparsely coded SIFT based classification on each sub-category. We have tested different approaches on 10 classes of species with five sub-categories.
1)Flower: We observed that for flower sub-
category, the species recognition accuracy was
only 33.62% when we used intensity values as
features i.e. the pixel based approach. When using
sparse coded SIFT features pooled by SPM, the
accuracy achieved was 69.54 whereas
classification using combined vocabulary of color,
shape and texture features gave maximum accuracy
of 73.18.
2)Fruit: It was observed that intensity based approach
gave very poor accuracy of 18.9% which further
increased to 57% when combined vocabulary
was used but maximum accuracy achieved was
only 67.3% with Sparse coded SIFT feature
representation.
3)Leaf: This category consists of leaf images on the
plants with a cluttered background. With pixel
representation, the accuracy is 22.9 which
improved to 45% with color, shape and feature
based approach but again the maximum accuracy
attained is 69.17 with SIFT and Sparse coding.
4)Leaf Scan: This type of category contains images
of leaves totally free from background. Either they
are scanned images or leaf of the plant is
photographed. The accuracy for pixel based is
72.77 which jumps to 82.67 on application of
combined vocabulary of shape, color and texture
features but on using Sparse coded SIFT features
approach, excellent accuracy of 98% was obtained.
5)Stem: Stem is the part of the plant which is
characterized by different textures therefore a texture
feature based approach should ideally be suitable for
identification of plant species on the basis of stem
image. But to our surprise, the SIFT based approach
also outperforms here with a superior accuracy of
76.57% as compared to accuracy of 58.76%
while using combined vocabulary and a very poor
performance of 20.75% while using intensity
representation.
VI.R ESULTS
The framework for automatic plant species recognition is implemented in MATLAB in the form of an interactive software named Plantector snapshots shown in figure 11 and 12. The software accepts a plant image and its corresponding metada xml file. The software returns the family, genus and species as output. The software is tested on 10 classes of plant species under five categories namely flower, fruit, leaf, leafscan and stem. Each class of species has images from these five categories which have been used for training. To train the algorithm, 75 images per class has been taken from flower, leaf and leafscan whereas 50 images for fruit and stem classes. In total 3250 images have been available for testing. 25 images from each class have been taken for testing. So in all 250 images have been used for testing. We have implemented three approaches namely Color, shape and texture based approach,SIFT based approach and pixel based approach. From the observations summarized in Table 1 we concluded that when a flower image of the plant is provided for species recognition, the combined vocabulary approach outperforms the other two approaches whereas for all the other sub- categories namely stem, fruit, leaf and leafscan, Sparsely coded SIFT features pooled with SPM approach gives best accuracy.
Therefore to dynamically choose the approach, our Plant species recognition system first identifies the sub-category by reading the xml file provided with the test image and then chooses the approach dynamically. We also concluded that maximum accuracy is achieved in the sub-category leaf-scan which is 98% then in the stem sub-category which is 76.57, next in order is flower sub-category with 73.18 % accuracy and the two sub-categories with lowest accuracies are leaf and fruit with 69.17% and 67.33 % respectively. The results can be directly analysed from the graph shown in Fig. 9
Fig.9. Accuracy comparison of various approaches
Figure 9&10 show the snap shots of the software for Automatic Plant Species Identification. We have named it as Plantector. The software accepts plant image as input. The sub-category is identified via xml file provided with the image. According to the sub-category identified, the system chooses the approach and returns the species of the plant identified by the system. The average response time of the software is between 1 to 2 seconds. If the meta data file is not provided, the system manually accepts the sub-category from the user. After evaluating the class of the species, an xml file is automatically created with the image and its subcategory and its evaluated species. The image
with this metadata is automatically stored. Thus the system also contributes in dynamic generation of database. Table 6. Performance comparison of different classification approaches
VII.C ONCLUSION
An automatic plant speciesrecognition application has been presented. Currently the application has been tested on 10 classes of speciesunder five organs due to hardware constraint. Motivated from success rate for 10 classes, best being 98% accuracy for leafscan images our future work will be to test on all 1000 classes. The future work aims at testing on more number of classes. We also aim to deploy the software as an Android mobile application which captures image of plant from the plant and performs recognition task through the application.
R EFERENCES
[1]James S. Cope, David P. A. Corney, Jonathan Y. Clark,
Paolo Remagnino, and Paul Wilkin. Plant speciesidentification using digital morphometrics: A review. Expert Syst. Appl., 39(8):7562{7573, 2012. [2]Kumar, N., Belhumeur, P.N., Biswas, A., Jacobs, D.W.,
Kress, W.J., Lopez, I.C., Soares, J.V.B.: Leafsnap: A computer vision system for automatic plant speciesidentification. European Conference on Computer Vision. pp. 502{516 (2012)
[3]Backes, A.R., Casanova, D., Bruno, O.M. Plant leaf
identification based on volumetric fractal dimension.
International Journal of Pattern Recognition and Artificial Intelligence 23(6), 1145{1160 (2009)
[4]Y. Nam, E. Hwang, and D. Kim. Clover: A mobile
content-based leaf image retrieval system. In Digital Libraries: Implementing Strategies and Sharing Experiences, Lecture Notes in Computer Science, pages139{148. 2005.
[5] D. Barthelemy. The pl@ntnet project: A computational
plant identification and collaborative information system. Technical report, XIII World Forestry Congress,2009.
[6]G. Cerutti, V. Antoine, L. Tougne, J. Mille, L. Valet, D.
Coquin, and A.Vacavant.Reves participation -tree speciesclassification using random forests and botanical features. In Conference and Labs of the Evaluation Forum, 2012.
[7]Envirofi. http://www.envirofi.eu/.
[8]J.-X. Du, X.-F. Wang and G.-J. Zhang, “Leaf shape based
plant species recognition,”Applied Mathematics and Computation, vol. 185, 2007.
[9] A. H. Kulkarni, H. M. Rai, K. A. Jahagirdar and P. S.
Upparamani, (2013). A Leaf Recognition Technique for Plant Classification Using RBPNN and Zernike Moments, International Journal of Advanced Research in Computer and Communication Engineering, Vol. 2, Issue 1, pp. 984-988.
[10]Krishna Singh, Indra Gupta, Sangeeta Gupta, SVM-
BDT PNN and Fourier Moment Technique for classification of Leaf, Internatio Guru, D. S., Y. H.
Sharath, and S. Manjunath. Texture features and KNN in classification of flower images.IJCA, Special Issue on RTIPPR (1) (2010): 21-29, 2010.nal Journal of Signal Processing, Image Processing and Pattern Recognition Vol. 3, No. 4, December, 2010.
[11]Gopal, S. P. Reddyn and V. Gayatri, (2012).
Classification of Selected Medicinal Plants Leaf Using Image Processing, IEEE International Conference on Machine Vision and Image Processing(MVIP), Taipei, pp. 5-8.
[12]O. Mzoughi, I. Yahiaoui, N. Boujemaa, and E. Zagrouba.
Advanced tree speciesidentification using multiple leaf parts image queries. In IEEE International Conference on Image Processing (ICIP), 2013.
[13]Zuolin ZHAO, Gang YANG, Xinyuan HUANG. Plant
Recognition Based on Leaf and Bark Images, School of Information Science and Technology, Beijing Forestry University, Beijing 100024, China.
[14]Nilsback and Andrew Zisserman. A Visual Vocabulary
for Flower https://www.wendangku.net/doc/351031913.html,puter Vision and Pattern Recognition, IEEE Computer Society Conference on.
Vol.2, 2006.
[15]Nilsback, M.E., Zisserman, A. Automated flower
classification over a large num-ber of classes. Indian Conference on Computer Vision, Graphics and Image Processing. pp. 722{729 (2008)
[16]Qi, Wenjing, Xue Liu, and Jing Zhao. Flower
classification based on local and spatial visual cues.
Computer Science and Automation Engineering (CSAE), Vol. 3,2012.
[17]Pei, Yong, and Weiqun Cao. A method for regional
feature extraction of flower images.Intelligent Control and Information Processing (ICICIP), IEEE, 2010.
[18]Siraj, Fadzilah, Muhammad Ashraq Salahuddin, and
Shahrul Azmi Mohd Yusof.Digital Image Classification for Malaysian Blooming Flower. Computational Intelligence, Modelling and Simulation (CIMSiM), IEEE, 2010.
[19]Guru, D. S., Y. H. Sharath, and S. Manjunath. Texture
features and KNN in classification of flower images.IJCA, Special Issue on RTIPPR (1) (2010): 21-29, 2010.
[20]Naiara Aginako, Javier Lozano, Marco Quartulli, Basilio
Sierra, Igor G.Olaizola.Identification of plant species on large botanical image datasets, Artificial Intelligence Department,University of the Basque Country,and Paseo Mikeletegi,57, 20009 Donostia-San Sebastián, 2014. [21]H. Goeau, P. Bonnet, J. Barbe, V. Bakic, A. Joly, J.-F.
Molino, D.Barthelemy, and N.Boujemaa. Multi-organ plant identification. In Proceedings of the 1st ACM International Workshop on Multimedia Analysis for Ecological Data, MAED '12,2012.
[22]https://www.wendangku.net/doc/351031913.html,
[23]Lowe, David G. "Distinctive image features from scale-
invariant keypoints." International journal of computer vision (Springer Netherlands) 60, no. 2 (November 2004): 91-110.
[24]Lisin, Dimitri A, Marwan A Mattar, Matthew B Blaschko,
Erik G
[25]Learned-Miller, and Mark C Benfield. "Combining local
and global image features for object class recognition."
Computer Vision and Pattern Recognition-Workshops.
IEEE, 2005. 47-47.
[26]K, Mikolajczyk, and Schmid C. "A performance
evaluation of local descriptors." IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE) 27, no.
10 (October 2005 ): 1615 - 1630.
[27]Lindeberg, T. Journal of Applied Statistics, 21(2):224-270.
[28]J, Sivic, and Zisserman A. "Video Google: a text retrieval
approach to object matching in videos." Ninth IEEE
International Conference on Computer Vision, 2003.
Proceedings. Nice, France : IEEE, 2003. 1470 -1477. [29]Lazebnik, Svetlana, Cordelia Schmid, and Jean Ponce.
"Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories." IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE, 2006. 2169-2178.
[30]J Wright, Y Ma, J Mairal, G Sapiro, TS Huang, S Yan -
Sparse representation for computer vision and pattern recognition,Proceedings of the IEEE, 2010.
[31] B. Olshausen, D. Field(2004). Current Opinion in
Neurobiology Current Opinion in Neurobiology 2004, 14(4):481–487
[32]Yang J-C, Yu K, Gong Y-H, et al.J OURNAL OF
MULTIMEDIA, VOL. 9, NO. 1, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1794-1801, 2009.
[33]Mairal, F. Bach, J. Ponce, G. Sapiro, and A. Zisserman.
Supervised dictionary learning. In NIPS, 2009.
[34]Ramirez, P. Sprechmann, a nd G. Sapiro. Classification
and clustering via dictionary learning with structured incoherence and shared features. In CVPR, 2010.
[35]J.C. Yang, K. Yu, and T. Huang. Supervised Translation-
Invariant Sparse coding. In CVPR, 2010.
[36]M. Yang, L. Zhang, J. Yang and D. Zhang. Metaface
learning for sparse representation based face recognition.
In ICIP, 2010.
[37]J. Mairal, F. Bach, J. Ponce, G. Sapiro, and A.
Zissserman Learning discriminative dictionaries for local image analysis. In CVPR, 2008.
[38] F. Rodriguez and G.Sapiro. Sparse representation for
image classification: Learning discriminative and reconstructive non- parametric dictionaries . IMA Preprint 2213, 2007.
[39]Pham and S. Venkatesh. Joint learning and dictionary
construction for pattern recognition. In CVPR, 2008. [40]Meng Yang,Zhang, D.Xiangchu Feng,Zhang.Fisher
Discriminative Dictionary Learning for Sparse Represenatation.ICCV,2011
[41]https://www.wendangku.net/doc/351031913.html,/lifeclef/2015/plant
Authors’ Profiles
Mrs. Suchit S. Purohit is currently
working as Asst. Professor in Department
of Computer Science, Gujarat University,
Ahmedabad, India. She earned her master’s
degree from M.B.M. Engineering College
Jodhpur, Rajasthan. She is pursuing her
Ph.D. from Department Of Computer
Science, Gujarat University. The area of research is object recognition and Image processing applied to planetary images.
She is a member of IEEE Geoscience and Remote sensing Society and Indian Society of Geomatics. She is currently is Co-Principal Investigator research projects funded by ISRO/DOS, India. She is coordinating elearning content development under project funded by MHRD, India. She has many publications in national and International peer reviewed journals. She is serving as a reviewer in many international journals and member of TPC in International conferences.
Dr Savita Gandhi is Professor & Head at
the Department of Computer .She is M.Sc.
(Mathematics Mathematics), Ph.D (Science,
Gujarat University) and A.A.S.I.(Associate
Member of Actuarial Society of India by
the virtue of having completed the "A"
group examinations comprising six subjects
conducted by Institute of Actuaries , London).
She is active member of many professional bodies and senior member of IEEE. She has been actively associated with IEEE activities. Recently, she has been elected as fellow member of GSA .She has served as Technical Committee Chair in IEEE Executive Committee. She has published several research papers in reputed national and international journals and has travelled widely in India and abroad to awarded International Who's Who of Professional and Business participate and present papers in conferences. She was Women for significant career achievements and contribution to society.
She is Principal Investigator for MHRD nation wide NME_ICT project u nder UGC namely “ePG Pathshala” for e-content development in the subject of Information Technology. She is also Principal Investigator of project on data analysis of Chandrayaan -1 funded by ISRO.
How to cite this paper: Suchit Purohit, Savita R. Gandhi," Application of Sparse Coded SIFT Features for Classification of Plant Images", International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.9, No.10, pp. 50-59, 2017.DOI: 10.5815/ijigsp.2017.10.06
植物特征总结
第一部分：植物分类 植物分类之草坪类（以下均为禾本科） 暖季型草坪：地毯草 狗牙根（百慕大、爬地草、绊根草、蟋蟀草、铁线草）； 假俭草（蜈蚣草、小牛鞭草、苏州阔叶子草、死攀茎草、百足草、）； 结缕草（锥子草、细叶结缕草/天鹅绒草、半细叶结缕草/马尼拉）； 冷季型草坪：黑麦草 高羊茅（羊茅属） 植物分类之竹类（以下均为禾本科） 单轴散生竹：刚竹属之毛竹（楠竹），桂竹，刚竹（槽里黄刚竹、黄皮绿筋竹），粉绿竹（淡竹），早园竹（早竹/雷竹），罗汉竹，紫竹（黑竹/乌竹，筠竹，斑竹），黄槽竹（金镶玉竹），哺鸡竹，灰竹，水竹。 合轴丛生竹：簕竹属之佛肚竹（密节竹），孝顺竹（慈孝竹/蓬莱竹，凤凰竹/观音竹），黄金间碧玉竹（青丝金竹）；单竹属之粉单竹；苦竹属之苦竹，菲白竹；箬竹属之阔叶箬竹。 蜜源植物：银杏，枇杷，乌桕，暴马丁香等。 易移栽成活植物：银杏，鹅耳枥等。 先花后叶的植物：银芽柳，蜡梅，迎春，山桃，梅，杏，李，玉兰，泡桐，贴梗海棠，紫藤，紫荆，榆叶梅，金缕梅，结香，连翘，白榆，木棉（广州市花）等。 具枝刺的植物： 贴梗海棠—蔷薇科， 椤木石楠—蔷薇科， 山楂———蔷薇科， 蔷薇———蔷薇科， 两面针——芸香科， 花椒———芸香科， 柑橘———芸香科， 酸橙———芸香科， 枳————芸香科（枸橘）， 枣树———鼠李科 刺槐———豆科，
皂荚———豆科， 紫叶小檗—小檗科， 假连翘——马鞭草科马缨丹属， 龙牙花——蝶形花科刺桐属， 阳性植物：落叶松属，松属（华山松，红松除外），杉木，落羽杉，水杉，铺地柏，粗榧，桦木属，桉属，杨属，柳属，栎属的多种，台湾相思，臭椿，乌桕，泡桐，枣树，柿树，以及草原，沙漠及旷野中的多种草本植物等。 阴性植物：臭冷杉，金松，竹柏，瑞香，扶芳藤，万年青，刻叶紫堇，大吴风草，人参，三七，秋海棠等。 中性偏阳性植物：榆属，朴属，榉属，樱花，枫杨等。 中性稍耐荫植物：罗汉松，杨梅，喜树——珙桐科喜树属，连翘，女贞，茉莉，迎春，凌霄，栀子，珊瑚树，槐，木荷，圆柏，珍珠梅属，七叶树，元宝枫，五角枫，黑麦草，山麦冬，玉竹，鸭跖草，石蒜，肾蕨，八仙花等。 中性强耐荫植物：冷杉属，云杉属，建柏属，铁杉属，粗榧属，红豆杉属，椴属，杜英，大叶槠，甜槠，阿丁枫，荚蒾属，八角金盘，桃叶珊瑚，常春藤，八仙花，六月雪，山茶，枸骨，海桐，杜鹃，忍冬，罗汉松，紫楠，棣棠，香榧等。 其他喜光植物：油杉，毛白杨，构树，木兰，狗牙根，假俭草，结缕草，千屈菜，香蒲，再力花，半支莲—马齿苋科，白三叶，兰花三七，巴西木，常夏石竹，金叶过路黄，宿根福禄考，美女樱，野菊，宿根天人菊，银叶菊，叶子花等。 深根性植物：银杏，白皮松，油松，黑松，杨梅，核桃，枫杨，薄壳山核桃，板栗，麻栎，白榆，榔榆，榉树，朴树，桑科，香樟，枫香——金缕梅科，杏，台湾相思，紫藤，国槐，臭椿，香椿，黄连木——漆树科黄连木属，七叶树，栾树，无患子，枣树，葡萄，木棉，梧桐（青桐）——梧桐科梧桐属，油茶，茶，木荷，柽柳，柿树等。 浅根性植物：雪松，构树，刺槐，华山松（主根不明显、根系较浅），红松，冷杉，臭冷杉，杉松，云杉，红皮云杉，白杄，鱼鳞云杉，雪松，侧柏，柏木，柳杉，东北红豆杉，南方红豆杉，构树，无花果，榕树，大叶榕，菩提榕，高山榕，橡胶榕，八角，杜仲，大山樱，樱花（樱花类都是浅根性），桃，李，玫瑰，刺槐，黄槐，枸橘，雀舌黄杨，漆树（主根不明显），火炬树，南酸枣，沙枣，沙棘，油橄榄，番石榴，君迁子，洋白蜡，水曲柳，棕榈，竹类等。
植物分类学各主要科属特征
被子植物的分纲 1.木兰科： 1.单叶、互生，有环状托叶痕。 2.花单生、雌、雄蕊均为多数，离生，螺旋排列于伸长的花脱上， 1.草本，叶分裂或复叶， 2.两性花，辐射对称，五基数，花萼、花冠均离生，雄蕊、雌蕊多数，离生 3.螺旋排列。聚合瘦果。 3.桑科： 1.木本，常有乳汁，单叶互生， 2.花小，单性，集成各种花序，单被花，常4基数。 3.坚果、核果集合为各种具花果。 4.壳斗科： 1.单叶互生。 2.单性花，雌雄同株，单被花。雄花成柔荑花序。雌花2—3朵生于总苞中，子房下位。 1.落叶木本。单叶互生，羽状脉。 2.雌雄同株，具柔荑花絮。单被花或无花被。 6.石竹科： 1.草本，单叶对生， 4基数，特立中央胎座，蒴果。 1.草本，具泡状毛。 2.花小、单被，雄蕊对萼，雌蕊2—3心皮合生，子房1室，基生胎座。 1.草本，茎节膨大。 2.单叶，互生，全缘，托叶鞘包茎。 1.常绿木本。单叶互生。 2.花两性，辐射对称，5基数，雄蕊多数。多轮排列，常集为数束，着生于花瓣上， 3.子房上位，中轴胎座。 4.常为蒴果。 10.锦葵科： 纤维发达，两性花，辐射对称，5基数。有副萼，单体雄蕊，花药1室，花粉粒大，具刺。蒴果或分果。 11.葫芦科： 1.草质藤本，具卷须， 2.单性花，雄蕊常结合，
3.子房下位，侧膜胎座， 4.瓠果。 12.杨柳科： 1.木本。 2.单叶互生。 3.花单性，雌雄异株，雌雄花皆成柔荑花序，无花被，有花盘或蜜腺，侧膜胎座。 4.蒴果，种子微小，基部有多数丝状长毛。 13.十字花科： 草本,常有辛辣汁液。花两性，辐射对称，萼片4，十字形花冠，四强雄蕊，子房1室，有2个侧膜胎座，具假隔膜，角果。 14.蔷薇科： 叶互生。具托叶。花5数，通常具杯状、盘状、或坛状花筒，形成子房上位周位花；雄蕊多数，轮生。种子无胚如乳。 15.蝶形花科： 1.复叶，具托叶。 2.蝶形花冠，二体雄蕊。 3.荚果。 16.大戟科： 1.具乳汁。 2.单性花。子房上位，3室，中轴胎座。 3.蒴果。 17.芸香科： 1.叶通常为羽状复叶或单身复叶，叶常具透明腺点。 4—5室；花柱单一。 通常羽状复叶；花常杂性，花瓣内侧基部常有腺体或鳞片，花盘发达，位于雄蕊外方，心皮3。种子常具假种皮，无胚乳。 19.伞形科： 1.芳香草本。 2.叶具叶鞘。 3.复伞形花序，子房下位，具上位花盘。 1.多木本。 2.单伞形花序，5基数， 3.下位子房，每室具1胚珠。 4.浆果 21.茄科： 1.叶互生。 2.花辐射对称，雄蕊5， 3.子房2室，偏斜，多胚珠。 4.双韧维管束。 22.旋花科： 1.草质藤本，常具乳汁，双韧维管束。
地被植物的特点和种类
地被植物的特点和种类 地被植物是指用于覆盖地面、防止水土流失，能吸附尘土、净化空气、减弱噪音、消除污染并具有一定观赏和经济价值的植物。随着我国园林绿化事业的不断发展，地被植物已被广泛应用于环境的绿化美化，尤其是在园林配置中，其艳丽的花果能起到画龙点睛的作用。一般来讲，地被植物应具备如下主要特性： 1．多年生植物，常绿或绿色期较长，以延长观赏和利用的时间。 2．具有美丽的花朵或果实，而且花期越长，观赏价值越高。 3．具有独特的株型、叶型、叶色和叶色的季节性变化，从而给人以绚丽多彩的感觉。 4．具有匍匐性或良好的可塑性，这样可以充分利用特殊的环境造型。 5．植株相对较为低矮。在园林配置中，植株的高矮取决于环境的需要，可以通过修剪人为地控制株高，也可以进行人工造型。 6．具有较为广泛的适应性和较强的抗逆性，耐粗放管理，能够适应较为恶劣的自然环境。 7．具有发达的根系，有利于保持水土以及提高根系对土壤中水分和养分的吸收能力，或者具有多种变态地下器官，如球茎、地下根茎等，以利于贮藏养分，保存营养繁殖体，从而具有更强的自然更新能力。 8．具有较强或特殊净化空气的功能，如有些植物吸收二氧化硫和净化空气能力较强，有些则具有良好的隔音和降低噪音效果。 9．具有一定的经济价值，如可用作药用、食用或为香料原料，可提取芳香油等，以利于在必要或可能的情况下，将建植地被植物的生态效益与经济效益结合起来。 10．具有一定的科学价值，主要包括两个方面，一是有利于植物学及其相关知识的普及和推广，二是与珍稀植物和特殊种质资源的人工保护相结合。 上述特性并非每一种地被植物都要全部具备，而是只要具备其中的某些特性即可。同时，在园林配置中，要善于观察和选择，充分利用这些特性，并结合实际需要进行有机组合，从而达到理想的效果。地被植物的种类很多，可以从不同的角度加以分类，一般多按其生物学、生态学特性，并结合应用价值进行分类，将其分为：灌木类地被植物，如杜鹃花、栀子花、枸杞等；草本地被植物，如三叶草、马蹄金、麦冬等；矮生竹类地被植物，如凤尾竹、鹅毛竹等；藤本及攀援地被植物，如常春藤、爬山虎、金银花等；蕨类地被植物，如凤尾蕨、水龙骨等；其他一些适应特殊环境的地被植物，如适宜在水边湿地种植的慈姑、菖蒲等，以及耐盐碱能力很强的蔓荆、珊瑚菜和牛蒡等。 我国具有丰富的地被植物种质资源，但到目前为止，对于地被植物生物学、生态学特性，尤其是保护和净化环境的功能以及经济用途等方面的研究还很不够，通过今后更深入的研究，将会逐步从现有地被植物和地被植物资源中选育出更多更好、能够应用于不同地区、不同环境条件和不同需要，具有良好环境效益和一定经济价值、科学价值的新地被植物。
校园植物的识别与分类
校园植物的识别与分类 一、目的与要求 1、通过对校园植物的调查研究，使学生熟悉观察、研究区域植物及其分类的基本方法。 2、了解校园植物种和科的识别特征。 3、编制校园植物检索表，并对植物进行归纳。 二、材料与器具 放大镜、镊子、铅笔、笔记本、检索表及相关工具书 三、常见庭院植物的物种识别与分类 现在的大学校园绿化比较好，栽培及自然生长的植物种类很多。在积累了被子植物的系统分类的基础理论知识后，可以充分利用校园的绿化优势，通过调查研究校园内植物的种类，熟悉观察、研究区域植物及其分类的基本方法，为其后的野外实习做准备。为保证实验的质量和效果，实验前指导教师可以根据学校的实际情况把学校分成不同的区域，学生可分成多个小组对不同校园区域的植物（包括栽培及自然生长的植物）进行调查研究。 （一）基础性实验——校园植物形态特征的观察与科学描述 对植物的形态特征进行科学的描述是进行物种识别与分类的基础，学生在野外实习之前一定要学会植物形态特征的科学描述方法。 植物种类的识别、鉴定必须在严谨、细致的观察研究后进行。在对植物进行观察研究时，首先要观察清楚每一种植物的生长环境，然后再观察植物具体的形态结构特征。植物形态特征的观察应起始于根（或茎的基部），结束于花、果实或种子。先用眼睛进行整体观察，细微、重要部分须借助放大镜观察，并能按以下特征进行观察和科学描述。 1、植物的性状——乔木；灌木亚灌木；草木（包括一、二年生或多年生），茎的形状、颜色、被毛或滑；直立；平卧，匍伏；攀援；缠绕或其他。 2、叶——单叶或复叶；叶形，有无叶柄？对生或互生，或轮生。叶面及叶背颜色如何？被毛或其它，网状脉或平行脉有托叶或无托叶？ 3、花序——总状类花序（如穗状、总状、园锥、伞形等花序）或聚伞类花序（如轮伞、聚伞花序）或花单生等。 4、花的各部分：观察、研究要极为细致、全面，从花柄开始，通过花萼、花冠、雄蕊，最后到雌蕊。必要时要对花进行解剖，分别作横切和纵切，观察花各部分的排列情况、子房位置、组成雌蕊的心皮数目、子房室数及胎座类型等。 （1）苞片——形状、颜色、数目、被毛或其他。 （2）花萼——萼片形状、颜色、数目、离生或合生、被毛或无毛。 （3）花冠——花瓣形态、颜色、数目、离生或合生、被毛或无毛。 （4）雄蕊——数目、花丝离生或合生，雄蕊与花瓣，萼片对生或互生。花药的着生情况和开裂方式。 （5）雌蕊——花柱数目、柱头分裂数或不裂或浅裂。 ①子房上位、下位或半下位； ②子房室的数目； ③胎座式（如中轴胎座、特立中央胎座、侧膜胎座等）； ④胚珠数目——少数或多数或定数。 （6）果实——属于何种果实？开裂或不开裂，果实的形状大小和颜色。
草地植物的类别及其特征教学提纲
草地植物的类别及其 特征
第二章第一节草地植物的类别及其特征 一、饲用植物的生活型 1、生活型定义：指植物长期适应综合的外界环境条件而在外貌上表现的类型。换句话说：生活型是植物在漫长的系统发育过程中对生态因素的综合适应结果。同一生活型的植物，在外部形态特征、对生活条件的要求及对环境条件的适应等方面具有相同或相似的地方。根据植物的生活型，可以认识植物的外貌和一般性状、生活习性及环境条件之间的联系，有助于对草地植物群落特征的分析和描述，也是划分草地类型的重要依据。 2 、植物的生活型 划分植物的生活型的方法很多，我们采用德国学者克涅尔的划分方法，根据外貌将植物生活型划分为四大类。 ⑴乔木： 多年生木本植物，具有本质化主干，一般在4—60M以上，热带多数树种25M，上端形成枝叶扩展的树冠。乔木的特点是枝条冬季不死亡，叶全部或部分死亡，树根深在10M左右，由于枝条上芽离地面较高，也叫高位芽植物 乔木分为带绿乔木（针叶）和夏绿乔木（阔叶） A、常绿的：松树、云杉、侧柏，常绿乔木的树叶中含有有机酸、生物碱、单宁等物质。青绿时家畜一般不采食，可加工后利用。 B、夏绿的：如，杨树、榆树、沙枣树，夏绿乔木的叶片可作饲料，它其中粗CP含量较多，营养价值可与优良干草相比。 ⑵灌木： 多年生木本植物，没有主干，在地面基部就开始分枝，枝条呈丝状。高度在
4—5米，寿命在20—30年，树干与枝条的芽不死，属于地上芽植物。 它可以分为常绿与夏绿两种： 夏绿：拧条、紫穗槐（阔叶）、红柳 常绿：沙冬青、杜鹃、翠柏（针叶） ⑶、半灌木 分枝从基部开始，无主干，基部本质化，上部为草质，一般冬季叶和枝条死亡，高度在0.2—0.5m。如沙蒿，地肤。 半灌木多分在干草原或荒漠半荒漠地区，是冬春季家畜主要饲草。 小半灌木指矮生的半灌木，高度在0.2m以下。如冷蒿。 亚灌木状草本指茎有一定幅度木质化的草本，仍然是草质。如枝儿条（牛枝子）、白里香、干草。 藤本具有的长的蔓茎，缠绕或以特殊的器官（吸盘）附着与其它物体上。 A：草质的藤本例如：田旋花、牵牛、野豌豆。 B：本质的藤本例如：葡萄 ⑷多年生草类： 草本植物，生命在一年以上，冬季地上部分枯死，根部一般不死，靠地面芽或地下芽过冬，春季复生，多数以营养繁殖为主，种子繁殖为辅。多年生草类是草地植被的主体。多年生草类还包括了短命多年生植物，它一般仅在春季完成生育期，生育期非常短，如鳞茎早熟禾。多年生植物主要分布在草原、荒漠、半荒漠地区。 ⑸一年生草类：
草地植物的类别和特征
第二章第一节草地植物的类别及其特征 一、饲用植物的生活型 1、生活型定义：指植物长期适应综合的外界环境条件而在外貌上表现的类型。换句话说：生活型是植物在漫长的系统发育过程中对生态因素的综合适应结果。同一生活型的植物，在外部形态特征、对生活条件的要求及对环境条件的适应等方面具有相同或相似的地方。根据植物的生活型，可以认识植物的外貌和一般性状、生活习性及环境条件之间的联系，有助于对草地植物群落特征的分析和描述，也是划分草地类型的重要依据。 2 、植物的生活型 划分植物的生活型的方法很多，我们采用德国学者克涅尔的划分方法，根据外貌将植物生活型划分为四大类。 ⑴乔木： 多年生木本植物，具有本质化主干，一般在4—60M以上，热带多数树种25M，上端形成枝叶扩展的树冠。乔木的特点是枝条冬季不死亡，叶全部或部分死亡，树根深在10M左右，由于枝条上芽离地面较高，也叫高位芽植物 乔木分为带绿乔木（针叶）和夏绿乔木（阔叶） A、常绿的：松树、云杉、侧柏，常绿乔木的树叶中含有有机酸、生物碱、单宁等物质。青绿时家畜一般不采食，可加工后利用。 B、夏绿的：如，树、榆树、沙枣树，夏绿乔木的叶片可作饲料，它其中粗CP含量较多，营养价值可与优良干草相比。 ⑵灌木： 多年生木本植物，没有主干，在地面基部就开始分枝，枝条呈丝状。高度在4—5米，寿命在20—30年，树干与枝条的芽不死，属于地上芽植物。 它可以分为常绿与夏绿两种： 夏绿：拧条、紫穗槐（阔叶）、红柳 常绿：沙冬青、杜鹃、翠柏（针叶） ⑶、半灌木 分枝从基部开始，无主干，基部本质化，上部为草质，一般冬季叶和枝条死亡，高度在0.2—0.5m。如沙蒿，地肤。
植物分类学各主要科属特征
精心整理 被子植物的分纲 1.木兰科： 1.单叶、互生，有环状托叶痕。 2.花单生、雌、雄蕊均为多数，离生，螺旋排列于伸长的花脱上， 位。 3.坚果，外具壳斗。 5.桦木科： 1.落叶木本。单叶互生，羽状脉。 2.雌雄同株，具柔荑花絮。单被花或无花被。
6.石竹科： 1.草本，单叶对生， 2.花5或4基数，特立中央胎座，蒴果。 7.藜科： 1.草本，具泡状毛。 具刺。蒴果或分果。 11.葫芦科： 1.草质藤本，具卷须， 2.单性花，雄蕊常结合， 3.子房下位，侧膜胎座，
4.瓠果。 12.杨柳科： 1.木本。 2.单叶互生。 3.花单性，雌雄异株，雌雄花皆成柔荑花序，无花被，有花盘或蜜腺，侧膜胎座。 1 2.单性花。子房上位，3室，中轴胎座。 3.蒴果。 17.芸香科： 1.叶通常为羽状复叶或单身复叶，叶常具透明腺点。 2.花盘发达，位于雄蕊内侧。雄蕊常具两轮，外轮对瓣；子房常4—5室；花柱单一。
通常羽状复叶；花常杂性，花瓣内侧基部常有腺体或鳞片，花盘发达，位于雄蕊外方，心皮3。种子常具假种皮，无胚乳。 19.伞形科： 1.芳香草本。 22.旋花科： 1.草质藤本，常具乳汁，双韧维管束。 2.花冠旋转折扇状排列。 3.中轴胎座。 4.种子子叶折叠。
1.草本，含挥发性芳香油。茎四棱。 2.叶对生。 3.轮伞花序，唇形花冠，二强雄蕊， 4.2.子房4深裂。花柱基生。 草本。杆三楞柱形，实心，无节，有封闭的叶鞘，叶三列，小坚果 29.禾本科：Poaceae 草本。茎杆圆筒形，节间中空，叶二列互生，叶由叶片、叶鞘和叶舌三部分组成。叶片带形，叶鞘开口。小穗是构成花序的基本单位，每个小穗由小穗轴、颖片和小花组成，每个小花由外稃、内稃和花组成。颖果。其中以第3点最为重要。
植物特性分类
喜光： 香樟、广玉兰、女贞、雪松、桂花、月桂、油茶、茶梅、金叶含笑、枇杷、石楠、法国冬青、蚊母、苦槠、法国梧桐、加杨、池杉、水杉、榉树、栾树、无患子、喜树、银杏、合欢（畏曝晒）、马褂木、垂柳、白玉兰、国槐、桑树、朴树、构树、枫香、枫杨、青桐、厚朴、紫薇、紫荆、红枫（弱）、三角枫（弱）、梅花、垂丝海棠、西府海棠、东京樱花、日本晚樱、紫玉兰、木槿、木芙蓉、红花刺槐、桃树、紫叶李、石榴、意杨、枣树、乌桕、白花泡桐、紫花泡桐（强）、桂花、栀子花、大叶黄杨、雀舌黄杨、月季、金叶女贞、小叶女贞、云南黄馨、火棘、洒金柏、龙柏、海桐、夹竹桃、金丝桃、枸骨、玫瑰、毛叶丁香、山麻杆、红瑞木、贴梗海棠、李叶绣线菊、粉花绣线菊、绣线菊、木本绣球、蜡梅、连翘、金钟花、扶桑、矮紫薇、红叶小檗、溲疏、杜鹃、叶子花、迎春、美人蕉、风信子、金边龙舌兰、萱草、彩叶草、常夏石竹、地肤、万寿菊、茑萝、芍药、石竹、太阳花、向日葵、虞美人、羽衣甘蓝、矮牵牛、蜀葵、凌霄、油麻藤、金银花、葡萄、木香、紫藤、络石、白三叶、红花酢浆草、葱兰、花叶蔓长春、旱伞草、水葱、睡莲、荷花、千屈菜、香蒲、孝顺竹、 耐荫： 半荫：罗汉松、加拿利海枣、栾树、红枫、木槿、山茶、红继木、厚朴、南天竹、棣棠、结香、杜鹃、风信子、萱草、万寿菊、三色堇、葱兰、花叶蔓长春、吉祥草、凤尾竹 稍：杜英、女贞、雪松、桂花、杨梅、月桂、茶梅、枇杷、石楠、蚊母、苦槠、无患子、喜树、白玉兰、国槐、紫薇、木芙蓉、白花泡桐、桂花、小叶女贞、海桐、金丝桃、枸骨、毛叶丁香、山麻杆、贴梗海棠、李叶绣线菊、粉花绣线菊、木本绣球、蜡梅、矮紫薇、红叶小檗、溲疏、迎春、芍药、凌霄、油麻藤、紫藤 较强：金松、金叶含笑、棕榈（较强）、桃叶珊瑚、栀子花、八角金盘、大花六道木、六月雪、十大功劳、阔叶十大功劳、雀舌黄杨、洒金柏、棕竹、八仙花（较强）、连翘、金钟花、春羽、肾蕨、玉簪、夏堇、一叶兰、金银花、络石、水葱 强：广玉兰、洒金桃叶珊瑚、龙柏、二月兰、常春藤、麦冬、旱伞草、菲白竹 不耐荫： 池杉、红花刺槐、紫花泡桐、金边龙舌兰、白三叶、香蒲、西府海棠、垂丝海棠、玫瑰、 耐寒： 雪松（稍）、金松、柑橘（稍）、月桂、含笑（－13℃）、深山含笑、乐昌含笑、金叶含笑（－10℃）、石楠、棕榈（强）、加杨（强）、水杉、栾树、银杏（强）、马褂木、垂柳、白玉兰（强）、黄金槐（－30℃）、桑树、枫杨、紫荆、三角枫、梅花、西府海棠、东京樱花、日本晚樱、木槿（强）、桃树、石榴、紫花泡桐、柑橘（稍强）、大花六道木、山茶（－10℃）、红继木、小叶女贞、洒金柏、金森女贞（－9.7℃）、玫瑰、毛叶丁香、红瑞木、贴梗海棠、李叶绣线菊、粉花绣线菊、绣线菊、木本绣球（强）、蜡梅、连翘、金钟花、红叶小檗、溲疏、迎春、二月兰（强）、风信子（强）、金边龙舌兰（稍）、玉簪、萱草、金盏菊、雏菊、三色堇、芍药（强）、石竹（强）、蜀葵、油麻藤（－5℃）、常春藤、木香、紫藤、白三叶、金叶过路黄（－10℃）、吉祥草（－5℃）、芦苇、水葱、荷花、千屈菜（强）、香蒲、刚竹（－18℃）、毛竹（－16.7℃）、 不耐寒： 香樟（－18℃）、杜英、女贞、桂花、杨梅、枇杷、法国冬青、蚊母、苏铁（0℃）、无患子、喜树、合欢（稍）、青桐、厚朴、紫薇、红枫、垂丝海棠、紫玉兰、木芙蓉、白花泡桐、桃
植物分类与观赏特性-全
园林植物的分类 1、乔木 形体高大，主干明显，分枝点高。 可分为：大乔（>20m）、中乔（界于20m与8m之间）、小乔（<8m） 2、灌木 空间尺度亲切，与视线较为接近。没有明显的主干，多呈丛生状态，或自基部分枝。 可分为： 大灌木（>2m） 中灌木（界于2m与1m之间） 小灌木（<1m） 3、藤本 具有细长茎蔓，并借助卷须、缠绕茎、吸盘或攀缘根等特殊器官，依附于其他物体才能使自身攀缘上升的植物。 4、竹类 5、草坪与地被 6、花卉 园林植物的观赏特性 依树木的观赏特性分类 一、赏花树木类（花木类）： 1、季节 （1）春季开花植物： 结香、迎春、金钟花、云南黄馨、黑荆、山茶、茶梅、玉兰、紫玉兰、 继木、日本早樱、日本晚樱、樱花、紫叶李、桃花、榆叶梅、 垂丝海棠、湖北海棠、贴梗海棠、西府海棠、棣棠、杜鹃、紫藤、 紫荆、海桐、含笑、牡丹、蔷薇、木瓜、麻叶绣线菊、石楠、火棘、 泡桐、刺槐、粉花绣线菊、珍珠花、小蜡、小叶女贞、 （2）夏季开花植物： 石榴、六月雪、探春、海仙花、斗球（木本绣球）、金银花、 夹竹桃、广玉兰、合欢、栀子、紫薇、梧桐、栾树、木槿、 凌霄、国槐、凤尾兰、八仙花、金丝桃 （3）秋季开花植物：桂花、木芙蓉、枇杷 （4）冬季开花植物：梅花、腊梅 （5）二度开花现象及一年多次开花（如四季桂、月季） 开花类别：先花后叶（纯式花相）与花叶同放（衬式花相） 结香、迎春、金钟花、云南黄馨、山茶、茶梅、玉兰、紫玉兰、继木日本早樱、日本晚樱、樱花、紫叶李、桃花、榆叶梅、垂丝海棠、湖北海棠、贴梗海棠、西府海棠、棣棠、杜鹃、紫藤、紫荆、海桐、含笑、牡丹、蔷薇、木瓜、麻叶绣线菊、石楠、火棘、泡桐、刺槐、粉花绣线菊、珍珠花、石榴、小蜡、小叶女贞、黑荆、六月雪、探春海仙花、斗球（木本绣球）广玉兰、合欢、夹竹桃、栀子、紫薇、梧桐、栾树、木槿、凌霄、金银花、国槐、凤尾兰、八仙花、金丝桃桂花、枇杷、木芙蓉、梅花、腊梅 2、花色 红色系 黄色系 蓝色系 白色系
植物分类学各主要科属特征
植物分类学各主要科属 特征 集团文件发布号：（9816-UATWW-MWUB-WUNN-INNUL-DQQTY-
被子植物的分纲 1.木兰科： 1.单叶、互生，有环状托叶痕。 2.花单生、雌、雄蕊均为多数，离生，螺旋排列于伸长的花脱上， 3.聚合骨突果。 2.毛茛科： 1.草本，叶分裂或复叶， 2.两性花，辐射对称，五基数，花萼、花冠均离生，雄蕊、雌蕊多数，离生 3.螺旋排列。聚合瘦果。 3.桑科： 1.木本，常有乳汁，单叶互生， 2.花小，单性，集成各种花序，单被花，常4基数。 3.坚果、核果集合为各种具花果。 4.壳斗科： 1.单叶互生。 2.单性花，雌雄同株，单被花。雄花成柔荑花序。雌花2—3朵生于总苞中，子房下位。 3.坚果，外具壳斗。 5.桦木科： 1.落叶木本。单叶互生，羽状脉。 2.雌雄同株，具柔荑花絮。单被花或无花被。
6.石竹科： 1.草本，单叶对生， 2.花5或4基数，特立中央胎座，蒴果。 7.藜科： 1.草本，具泡状毛。 2.花小、单被，雄蕊对萼，雌蕊2—3心皮合生，子房1室，基生胎座。 3.胞果，胚弯曲。 8.蓼科： 1.草本，茎节膨大。 2.单叶，互生，全缘，托叶鞘包茎。 3.花两性，单被，萼片花瓣状。 9.山茶科： 1.常绿木本。单叶互生。 2.花两性，辐射对称，5基数，雄蕊多数。多轮排列，常集为数束，着生于花瓣上， 3.子房上位，中轴胎座。 4.常为蒴果。 10.锦葵科： 纤维发达，两性花，辐射对称，5基数。有副萼，单体雄蕊，花药1室，花粉粒大，具刺。蒴果或分果。 11.葫芦科： 1.草质藤本，具卷须，
2.单性花，雄蕊常结合， 3.子房下位，侧膜胎座， 4.瓠果。 12.杨柳科： 1.木本。 2.单叶互生。 3.花单性，雌雄异株，雌雄花皆成柔荑花序，无花被，有花盘或蜜腺，侧膜胎座。 4.蒴果，种子微小，基部有多数丝状长毛。 13.十字花科： 草本,常有辛辣汁液。花两性，辐射对称，萼片4，十字形花冠，四强雄蕊，子房1室，有2个侧膜胎座，具假隔膜，角果。 14.蔷薇科： 叶互生。具托叶。花5数，通常具杯状、盘状、或坛状花筒，形成子房上位周位花；雄蕊多数，轮生。种子无胚如乳。 15.蝶形花科： 1.复叶，具托叶。 2.蝶形花冠，二体雄蕊。 3.荚果。 16.大戟科： 1.具乳汁。 2.单性花。子房上位，3室，中轴胎座。
植物分类学考题
大题、名词解释 种 是生物分类的基本单位，它具有一定的自然分布区和一定的形态特征和生理 性的生物类群。（同种中的个体有相同的遗传性状，而彼此杂交可产生性状相同的 新个体的生物群体 称为种或物种） 自然分类法：根据植物亲缘关系的远近对植物进行分门别类的方法称之为自然分类法。 双名法：是指对每一种植物（或动物、微生物） 的名称，都由2个拉丁词（或拉丁化形式的词） 所组成, 前面一个词为属名，第二个词为种加词。一个完整的学名，双名的后面还应附加上命名人的姓名或姓名 的缩写。 主模式标本： 是由命名人指定的模式标本，即着者发表新分类群时据以命名、描述和绘图的那一份标本 等模式标本：系与主模式标本同为一采集者在同一地点与时间所采集的同号复份标本。 主模式标本：是由命名人指定的模式标本，即著者发表新分类群时据以命名、描述和绘图的那一份标本。 合模式标本：著者在发表一分类群时未曾指定主模式而引证了 2个以上的标本或被著者指定为模式的标本， 其数目在2个以上时，此等标本中的任何 1份，均可称为合模式标本。 后选模式标本：当发表新分类群时，著作未曾指定主模式标本或主模式已遗失或损坏时，是后来的作者根据 原始资料，在等模式或依次从合模式、副模式、新模式和原产地模式标本中，选定 1份作为命名模式的标 本，即为后选模式标本。 副模式标本：对于某一分类群，著者在原描述中除主模式、等模式或合模式标本以外同时引证的标本，称 为副模式标本。 新模式标本：当主模式、等模式、合模式、副模式标本均有错误、损坏或遗失时，根据原始资料从其他标本 中重新选定岀来充当命名模式的标本。 原产地模式标本：当不能获得某种植物的模式标本时，便从该植物的模式标本产地采到同种植物的标本， 与原始资料核对，完全符合者以代替模式标本，称为原产地模式标本。 学名：林奈于1752年用两个拉丁单词作为一个植物的名称，第一个单词是属名，是名词，其第一个字母大 写；第二个单词为种名形容词，后边再写岀定名人的姓氏或姓氏缩写，这种国际上统一使用的名称。 有效发表 根据"法规"，植物学名之有效发表条件是发表作品一定要是印刷品，并可通过出售、交换或赠送， 到达公共图书馆或者至少一般植物学家能去的研究机构的图书馆。仅在公共集会上、手稿或标本上以及仅在 商业目录中或非科学性的新闻报刊上宣布的新名称，即使有拉丁文特征集要，均属无效。 合格发表：1个新分类群名称的发表，必须伴随有拉丁文描述或特征集要，否则不作为合格发表。自 1958年 1月1日以后，科或科级以下新分类群之发表，必须指明其命名模式，才算合格发表。 浆果：由一至数心皮组成，外果皮膜质，中果皮、内果皮肉质化，含一至数粒种子的果实 唇形花冠：花冠联合，略成上下二唇形的花冠类型，如一串红等。 大 题、选择题 经典的 植物分类学资料主要来自于植物的（ A.细胞遗传学 B.花粉学及胚胎学 C.生物化学与分子生物学 2、哪一组裸子植物都是落叶乔木？ A.红松、水杉、金钱松； B.水杉、柳杉、杉木; C.水杉、银杏、金钱松； D.金钱松、落叶松、杉木。 答：（ ) 3、下列具伞形花序的植物可能是（ ）。 A ?菊花 B ?蔷薇 C ?胡萝卜 D ?锦葵 4、具有侧膜胎座类型的植物是（ ）。 A .大豆 B .小麦 C ? 油菜 D ?石竹 5、下列具伞形花序的植物可能是（ ）。 得分 评阅人 ）方面的特征。 D.形态解剖学及地理学
植物的种类分类
矮牵牛：Petunia hybrida，Vilm 科属：茄科碧冬茄属 特性：全株具黏毛，匍匐状。叶质柔软，卵形，全缘，近无柄。花冠漏斗形，先端具波状浅裂，白色或紫色。花大色艳，培育良好，开花时不见茎叶。花期长，从4月至10月底可陆续开花不断。 习性：喜温暖，不耐寒。在干热的夏季开花繁茂。喜阳光充足，耐半荫。喜疏松、排水良好及微酸性土壤，忌积水雨涝。 应用：园林中常用大花型和多花型品种。适宜作吊盆的垂吊型品种在室内外广泛应用，还有花篱型品种。 芍药：Paenoia lactiflora 科属：毛茛科，芍药属 特性：地下具粗壮肉质纺锤形根，每年从其上发一年生的细根，在根颈部产生新芽。初生长时，茎叶或茎红色或有紫红晕。宵夜通常3深裂，椭圆形，绿色。花顶生茎上，有长花梗。春季开花。 习性：芍药适宜温暖湿润气候条件，具有喜光、喜温、喜肥和一定的耐寒特性。怕积水，宜肥沃、湿润及排水良好的砂质壤土，忌盐碱及低洼地。应用：专类园、花镜、花丛、花群、切花。 啤酒花：Humulus lupulus 科属： 特性：为多生缠绕草本，茎高2-5米，茎枝绿色，密被细毛和倒钩刺。单叶对生，纸质，卵形，主茎上叶常5深裂，侧支上上叶多3裂，花枝上叶常不裂，叶缘具有粗锯齿，叶面密生小刺毛。雌雄异株，雄花为圆锥形花序，雌花多穗状花序花期7-9月。果穗程球果状。雌雄异株；雄花细小，排成圆锥花序，花被片和雄蕊各5；雌花每两朵生于一苞片腋部，苞片复瓦状排列成近圆形的穗状花序。 习性：喜冷凉，耐寒畏热，生长适温14～25℃，要求无霜期120天左右。长日照植物，喜光，全年日照时数需1700～2600小时。不择土壤，但以土层深厚、疏松、肥沃、通气性良好的壤土为宜，中性或微碱性土壤均可。应用：用于攀援花架或篱棚。雌花序可制干花。花为酿造啤酒的原料。 矢车菊：Centaurea cyanus Linn科属：菊科，矢车菊属 特性：一二年草花，多分枝，茎叶具白色绵毛，叶线形，全缘；茎部常有齿或羽裂。头状花序顶生，边缘舌状花为漏斗状，花瓣边缘带齿状，中央花管状，呈白、红、蓝、紫等色，但多为蓝色。花期4-5月。 习性：适应性较强，喜欢阳光充足，不耐阴湿，须栽在阳光充足、排水良好的地方，否则常因阴湿而导致死亡。较耐寒，喜冷凉，忌炎热。喜肥沃、疏松和排水良好的沙质土壤。 应用：高性种植株挺拔，花梗长，适于作切花，也可作花坛、花径材料。矮型株仅高20厘米，可用于花坛、草地镶边或盆花观赏。大片自然丛植。 美女樱：Verbena hybrida Voss 科属：马鞭草科，马鞭草属。 特性：为多年生草本植物，常作1-2年生栽培。茎四棱、横展、匍匐状，低矮粗壮，全株具灰色柔毛，长30-50厘米。叶对生有短柄，长圆形、卵圆形或披针状三角形，边缘具缺刻状粗齿或整齐的圆钝锯齿，叶基部常有裂