Hybridized Feature Descriptor (HFD) for Content Based Image Retrieval on Large Image Database

Objectives: The hybridized feature descriptor is constructed to describe the relevance between the query and database images in the database. The input query is in the form of text keywords, specifications, image properties, color/ texture patterns or image itself. Method: The layered approach has been used to design experimental model, which helps to match the image features one after one to prepare the final image ranking. The similarity factor is calculated by SVM based learning model. It can achieve very good results under the limited feature matching paradigm. Findings: The existing model is defeated by this model because of its hybrid feature descriptor solution, proposed by the amalgamation of the color and low ranked features computed with feature fitness validation. The performance has been evaluated by using various performance parameters like accuracy, ranking/index building time, library lookup time, precision, recall etc. Improvement: The proposed model has resulted in effective content based image retrieval system. The experimental result shows the efficiency and robustness of this model.