Color patterns for pictorial content description

In this paper, we propose a new type of image feature, which consists of patterns of colors and intensities that capture the latent associations among images and primitive features in such a way that the noise and redundancy are minimized. Incorporating our feature model into a Content-based Image Retrieval (CBIR) system moves the research in image retrieval beyond simple matching of images based on their primitive features and creates a ground for learning image semantics from visual content. A system developed using our proposed feature model, will have the capability of learning associations between not only semantic concepts and images, but also between semantic concepts and patterns. We evaluated the performance of our system based on the retrieval accuracy and on the perceptual similarity order among retrieved images. When compared to standard image retrieval methods, our preliminary results show that, even if the feature space was reduced to a significantly lower dimensional sp...

• Type: Journal
• Year: 2002
• Where: SAC
• Authors: Daniela Stan, Ishwar K. Sethi
• Keywords: Applied Computing, Content-based Image Retrieval, Image, Image Retrieval, SAC 2002