Ulteriori informazioni
Content-based image retrieval is the set of techniques for retrieving relevant images from an image database on the basis of automatically derived image features. The need for efficient content-based image re trieval has increased tremendously in many application areas such as biomedicine, the military, commerce, education, and Web image clas sification and searching. In the biomedical domain, content-based im age retrieval can be used in patient digital libraries, clinical diagnosis, searching of 2-D electrophoresis gels, and pathology slides. I started my work on content-based image retrieval in 1995 when I was with Stanford University. The project was initiated by the Stan ford University Libraries and later funded by a research grant from the National Science Foundation. The goal was to design and implement a computer system capable of indexing and retrieving large collections of digitized multimedia data available in the libraries based on the media contents. At the time, it seemed reasonable to me that I should discover the solution to the image retrieval problem during the project. Experi ence has certainly demonstrated how far we are as yet from solving this basic problem.
Sommario
1. Introduction.- 1. Text-based image retrieval.- 2. Content-based image retrieval.- 3. Applications of CBIR.- 4. Summary of our work.- 5. Structure of the book.- 6. Summary.- 2. Background.- 1. Introduction.- 2. Content-based image retrieval.- 3. Image semantic classification.- 4. Summary.- 3. Wavelets.- 1. Introduction.- 2. Fourier transform.- 3. Wavelet transform.- 4. Applications of wavelets.- 5. Summary.- 4. Statistical Clustering and Classification.- 1. Introduction.- 2. Artificial intelligence and machine learning.- 3. Statistical clustering.- 4. Statistical classification.- 5. Summary.- 5. Wavelet-Based Image Indexing and Searching.- 1. Introduction.- 2. Preprocessing.- 3. Multiresolution indexing.- 4. The indexing algorithm.- 5. The matching algorithm.- 6. Performance.- 7. Limitations.- 8. Summary.- 6. Semantics-Sensitive Integrated Matching.- 1. Introduction.- 2. Overview.- 3. Image segmentation.- 4. Image classification.- 5. The similarity metric.- 6. System for biomedical image databases.- 7. Clustering for large databases.- 8. Summary.- 7. Image Classification by Image Matching.- 1. Introduction.- 2. Industrial solutions.- 3. Related work in academia.- 4. System for screening objectionable images.- 5. Classifying objectionable websites.- 6. Summary.- 8. Evaluation.- 1. Introduction.- 2. Overview.- 3. Data sets.- 4. Query interfaces.- 5. Characteristics of IRM.- 6. Accuracy.- 7. Robustness.- 8. Speed.- 9. Summary.- 9. Conclusions and Future Work.- 1. Summary.- 2. Limitations.- 3. Areas of future work.- References.
Riassunto
Content-based image retrieval is the set of techniques for retrieving relevant images from an image database on the basis of automatically derived image features. The need for efficient content-based image re trieval has increased tremendously in many application areas such as biomedicine, the military, commerce, education, and Web image clas sification and searching. In the biomedical domain, content-based im age retrieval can be used in patient digital libraries, clinical diagnosis, searching of 2-D electrophoresis gels, and pathology slides. I started my work on content-based image retrieval in 1995 when I was with Stanford University. The project was initiated by the Stan ford University Libraries and later funded by a research grant from the National Science Foundation. The goal was to design and implement a computer system capable of indexing and retrieving large collections of digitized multimedia data available in the libraries based on the media contents. At the time, it seemed reasonable to me that I should discover the solution to the image retrieval problem during the project. Experi ence has certainly demonstrated how far we are as yet from solving this basic problem.
