Page 1
Page 1
Content based image retrieval systems
With an advent of technology, huge collection of digital images is formed as repositories on crime prevention, medical diagnosis, military, face finding, satellites and remote sensing. The task of searching for similar images in the repository is difficult. The data is growing enormously which makes it difficult to store and manage. The traditional image retrieval technique is inefficient in retrieving these images. Content-based image retrieval is an approach from data mining community, which provides the solution of managing this huge quantity of data. In this research, a Content-Based Image Retrieval (CBIR) system has been developed using color and texture as retrieval features from the image repository. The system allows the user to search for an image based on any of the two features alone or in combination by assigning weights to the features. The histogram and color moments approach is used to extract the color feature, texture feature is extracted using statistical moments and co-occurrence matrix method and the shape feature is extracted using the morphological operations. The images and the extracted feature vectors are stored in the Pickle file. The system is robust as it provides search based on the multiple features. The performance of the system was evaluated by analyzing the retrieval results using precision and recall.
Advances in systems, computing sciences and software engineering ; Proceedings of SCSS 2005
Advances in Systems, Computing Sciences and Software Engineering This book includes the proceedings of the International Conference on Systems, Computing Sciences and Software Engineering (SCSS'05). The proceedings are a set of rigorously reviewed world-class manuscripts addressing and detailing state-of-the-art research projects in the areas of computer science, software engineering, computer engineering, systems sciences and engineering, information technology, parallel and distributed computing and web-based programming.
