Ranjan Parekh

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.

Using Texture Analysis for Medical Diagnosis

An automated system for recognizing human skin disease conditions analyzes skin texture images using texture recognition techniques based on gray-level co-occurrence and wavelet decomposition matrices.

A secure keyless image steganography approach for lossless RGB images

This paper proposes an improved steganography approach for hiding text messages within lossless RGB images. The objective of this work is to increase the security level and to improve the storage capacity while incurring minimal degradation of the image. The security level is increased by distributing the message over the entire image instead of clustering within specific image portions, as also by including a password authentication scheme to ensure that the message can be retrieved only by the intended recipient. Storage capacity is increased by utilizing all the color channels for storing information instead of reserving one of the channels as pixel indicator. Image degradation is minimized by changing only one LSB bit per color channel for hiding the information thereby incurring the least change in the original image. Experimentations done for analyzing the storage capacity and quality degradation, establish the superiority of the proposed approach vis-à-vis contemporary existing approaches.

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

Character Recognition using Dynamic Windows

This paper proposes a scheme for recognition of English characters based on features derived from partitioning the character image into non-overlapping cells. A dynamic sliding window moves over each cell and pixel counts obtained from the image portion within the boundaries of the window, contribute towards generation of the feature vector. A total of four passes of the window over the image each with a different window size leads to the generation of a 30-element feature vector. A neural network (multi-layered perceptron) is used for classifying the 26 alphabets of the English language. Accuracies obtained are demonstrated to have been improved upon with respect to contemporary works.

Extending GLCM to include Color Information for Texture Recognition

This paper proposes an automated system for texture recognition using an extended form of Grey Level Co‐occurrence Matrix (GLCM). GLCM provides a popular statistical method for texture recognition, however its basic limitation is that it can only capture information from grey‐scale images. To improve recognition accuracies this paper studies the possibilities of including color information from color texture images. Color information is captured by applying GLCM to each of the color channels r, g, b, both individually and in pairs providing 9 Color GLCM (C‐GLCM) combinations i.e. rr, gg, bb, rg, rb, gr, gb, br, bg. Symmetrical normalized C‐GLCMs computed along four directions 0°, 45°, 90° and 135°, from each of the 9 combinations are used to compute two features viz. GLCM Contrast and GLCM Mean, which are used for texture recognition. Experimental results indicate that C‐GLCMs provide better recognition accuracies as compared to standard GLCMs on greyscale images.

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.

Improved Iris Recognition in 2D Eigen Space

This paper a new biometric method for personal identification is been presented by iris identification of a person in lower dimensionality and reduced template size than the other previous approaches in 2D Eigen space, so that it can be use for verification in application areas . Here the iris images are expressed in lower dimension, re-tending its features by using covariance matrix and Eigen matrix to a covariant-Eigen space vector. The proposed approach is also suitable to work on half iris image. The proposed approach shows high accurate result. General Terms Pattern Recognition, Texture.