No abstract

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.

No abstract

No abstract

No abstract

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.

Intra-class recognition of fruits using image processing and pattern recognition techniques, is a challenging task mainly because sub-types of the same fruit show a large amount of similarities between each other and hence more difficult to distinguish than when different types of fruits are involved (inter-class). The problem becomes more acute when the camera viewpoint also changes which tend to change the known characteristics of the fruits like contour shape. To solve this problem, this paper proposes a view point invariant solution for intra-class recognition of fruits by combining color and texture features and using a Neural Network (NN) classifier. Experimentations done on a dataset of 270 fruit images show satisfactory performance across different fruit types and sub-types.

No abstract