Object Recognition Using DRLTP for Image Retrieval Systems

Abstract: With many potential practical applications, Object Recognition has attracted substantial attention during the past few years. A variety of relevance feedback (RF) schemes have been developed as a powerful tool to bridge the semantic gap between low-level visual features and high-level semantic concepts, and thus to improve the performance of IR systems. The project presents the robust object recognition using edge and texture feature extraction. The system proposes new approach in extension with local ternary pattern called DRLTP. By using these methods, the category recognition system will be developed for application to image retrieval. The category recognition is to classify an object into one of several predefined categories. The discriminative robust local ternary pattern (DRLTP) is used for different object texture and edge contour feature extraction process. we discuss the fundamental aspects, visual features and techniques for fast searching and retrieval of images from the database. These features are useful to distinguish the maximum number of samples accurately and it is matched with already stored image samples for similar category classification. The simulated results will be shown that used discriminative robust local ternary pattern has better discriminatory power and recognition accuracy compared with prior approaches.

Keywords: Test image, Preprocessing, Feature Extraction, Database Training, Classification, Parameter analysis.