Acquisition of Images using Neural Network

Abstract

The application of computer vision to the image retrieval problem is Content-based image retrieval (CBIR). The interest in digital images is growing day by day. Users in professional fields are make use of the opportunities offered by the ability to access and manipulate remotely-stored images in different ways. The problems in image retrieval are becoming widely accepted, and the finding solution is an active area for research and development. This dissertation work aims at developing a hybrid scheme for intelligent image retrieval system using neural networks. Each image in the database is indexed by a visual feature vector, which is extracted using color moments and discrete cosine transform coefficients. The query is characterized by a set of predefined semantic labels. A novel method of similarity measure using dot product is used for ranking and retrieval for improved performance of the system
DOI: 10.17762/ijritcc2321-8169.150503