Abstract: Content based image retrieval (CBIR) has been an active and fast growing research area in both image processing and data mining. Thedynamic nature of CBIRcomplements the drawbacks of Text Based Image Retrieval (TBIR).Malaysia has been recognized with a rich marine ecosystem. Challenges of these images are low resolution, translation, and transformation invariant. In this paper, we have designed anautomated CBIR system to characterize the species for future research.We compared various image descriptors and the combination of multiple features. Our results show that the combination of shape and colour features yields higher precision and recall value. We also proposed segmentation as pre-processing step for our CBIR system. For the automated segmentation, we use the saliency and the region growing methods. Our findings show that the region-growing method has better accuracy.

• Publication Date: 05-May-2013
• DOI: 10.15224/978-981-07-6261-2-37
• Views: 0
• Downloads: 0

Abstract: The topic of quantum chaos has begun to draw increasing attention in recent years. Dissipative quantum maps can be characterized by sensitive dependence on initial conditions,like classical maps. By using significant properties of quantum chaotic map such as ergodicity, sensitivity to initial condition and control parameter, one-way computation and random like behavior, we present a new scheme for image encryption. Based on all analysis and experimental results, it can be concluded that, the proposed scheme is efficient and secure. Although the chaotic map presented in this paper aims at image encryption, it is not just limited to this area and can be widely applied in other information security fields.

• Publication Date: 05-May-2013
• DOI: 10.15224/978-981-07-6261-2-36
• Views: 0
• Downloads: 0