Jyotismita Chaki

Plant Leaf Recognition using Shape Based Features and Neural Network Classifiers

This paper proposes an automated system for recognizing plant species based on leaf images. Plant leaf images corresponding to three plant types, are analyzed using two different shape modeling techniques, the first based on the Moments-Invariant (M-I) model and the second on the Centroid- Radii (C-R) model. For the M-I model the first four normalized central moments have been considered and studied in various combinations viz. individually, in joint 2-D and 3-D feature spaces for producing optimum results. For the C-R model an edge detector has been used to identify the boundary of the leaf shape and 36 radii at 10 degree angular separation have been used to build the feature vector. To further improve the accuracy, a hybrid set of features involving both the M-I and C-R models has been generated and explored to find whether the combination feature vector can lead to better performance. Neural networks are used as classifiers for discrimination. The data set consists of 180 images divided into three classes with 60 images each. Accuracies ranging from 90%-100% are obtained which are comparable to the best figures reported in extant literature. Keywords-plant recognition; moment invariants; centroid-radii model; neural network; computer vision.

Plant leaf recognition using texture and shape features with neural classifiers

This paper proposes a novel methodology of characterizing and recognizing plant leaves using a combination of texture and shape features. Texture of the leaf is modeled using Gabor filter and gray level co-occurrence matrix (GLCM) while shape of the leaf is captured using a set of curvelet transform coefficients together with invariant moments. Since these features are in general sensitive to the orientation and scaling of the leaf image, a pre-processing stage prior to feature extraction is applied to make corrections for varying translation, rotation and scaling factors. Efficacy of the proposed methods is studied by using two neural classifiers: a neuro-fuzzy controller (NFC) and a feed-forward back-propagation multi-layered perceptron (MLP) to discriminate between 31 classes of leaves. The features have been applied individually as well as in combination to investigate how recognition accuracies can be improved. Experimental results demonstrate that the proposed approach is effective in recognizing leaves with varying texture, shape, size and orientations to an acceptable degree. Methodology for plant leaf recognition using shape and texture features is proposed.Features are made invariant to scaling and orientation of leaf images.Classification is done using two different types of neural classifiers.System is tested using both known and unknown classes of leaf images.System is also designed to handle images with small amounts of deformations.

Plant Leaf Recognition using Gabor Filter

This paper proposes an automated system for recognizing plant species based on leaf images. Plant leaf images of three plant types are analyzed using Gabor Filter by varying the filter parameters. Leaf images are convolved with Gabor filters followed by a separation of the real and imaginary portions of the signal. Absolute difference between the real and imaginary signals form the scalar feature value used for discrimination. Associated parameters like filter size, standard deviation, phase shift and orientation are varied to investigate which combination provides the best recognition accuracies. Classification is done by subtracting the test samples from the mean of the training set. The data set consists of 120 images divided into 3 classes. Accuracy obtained is comparable to the best results reported in literature. General Terms Pattern Recognition, Texture, Shape

Plant Leaf Recognition Using Ridge Filter and Curvelet Transform with Neuro-Fuzzy Classifier

The current work proposes an innovative methodology for the recognition of plant species by using a combination of shape and texture features from leaf images. The leaf shape is modeled using Curvelet Coefficients and Invariant Moments while texture is modeled using a Ridge Filter and some statistical measures derived from the filtered image. As the features are sensitive to geometric orientations of the leaf image, a pre processing step is performed to make features invariant to geometric trans-formations. To classify images to pre-defined classes, a Neuro fuzzy classifier is used. Experimental results show that the method achieves acceptable recognition rates for images varying in texture, shape and orientation.

Recognition of whole and deformed plant leaves using statistical shape features and neuro-fuzzy classifier

This paper proposes a methodology for recognition of plant species by using a set of statistical features obtained from digital leaf images. As the features are sensitive to geometric transformations of the leaf image, a pre processing step is initially performed to make the features invariant to transformations like translation, rotation and scaling. Images are classified to 32 pre-defined classes using a Neuro fuzzy classifier. Comparisons are also done with Neural Network and k-Nearest Neighbor classifiers. Recognizing the fact that leaves are fragile and prone to deformations due to various environmental and biological factors, the basic technique is subsequently extended to address recognition of leaves with small deformations. Experimentations using 640 leaf images varying in shape, size, orientations and deformations demonstrate that the technique produces acceptable recognition rates.

Translation and Retrieval of Image Information to and from Sound

the rapid growth of both Internet and Multimedia the subject of hidden exchange of information has gained a great importance. The current work is based on translation of information of a digitized image into a sound file. Later the image file can be retrieved by authorized personnel by performing the reverse process on the sound file. The three dimensional RGB image matrix is converted into a two dimensional sound file. During the retrieving time, the reverse procedure is performed on the sound file in order to get back the original image file.

An Efficient Fragmented Plant Leaf Classification Using Color Edge Directivity Descriptor

Plant species identification is one of the most important research branches of botanical science. The current work proposes an efficient methodology for recognition of plant species from whole as well as fragmented digital leaf images. The situation becomes challenging when only a partial portion of the leaf can be obtained. Since leaves are fragile and prone to be fragmentation due to various environmental and biological factors, the paper studies how recognition of fragmented leaves can be effectively done. In this study the combination of texture and color based method (Color Edge Directivity Descriptor) is used to extract the feature and Euclidean distance is used as the classifier for the classification of the fragmented as well as whole leaf images.

Automated Classification of Echo-Cardiography Images Using Texture Analysis Methods

This work studies the prospects and efficacy of identifying and classifying disease conditions from digital medical images by applying image processing and pattern recognition techniques. Specifically echo-cardiography images showing the left ventricle of the human heart are being used to identify three cardiac conditions viz. normal, dilated cardiomyopathy and hypertrophic cardiomyopathy. To differentiate between the classes, texture information extracted from the images are used to generate data models using three different approaches : by using a complex Gabor filter, by using Hu invariant moments and by using Law’s texture detection method. In all cases the system is first trained in a supervised manner using training samples for each class, and then the system is tested using similar but not identical testing samples. Each test sample is classified in an automated manner by computing differences with the trained samples of each class and identifying which class produces the least average difference. Each approach is studied by varying associated parameters to find out optimum performance levels. Recognition accuracies produced are found to be comparable with the best results reported in extant literature.