NOVEL CONTENT -BASED IMAGE RETRIEVAL TECHNIQUES FOR MEDICAL DATABASE
Priyanka N. Munje, Deepak D. Kapgate · 2014
Content based image retrieval (CBIR) become a challenging problem due to large size of the image database because difficulty in recognizing images, difficulty in devising a query and evaluating results in terms of semantic gap, computational load to manage large data files and overall retrieval time. To solve this problems Feature extraction is initial and important step in the design of content based image retrieval system. Feature extraction means extracting unique and valuable information from the image, this features are termed as signature of image. In CBIR system, feature extraction of the image in the database is done offline therefore it does not contribute significantly in computational complexity. Generally Human eyes tend to differentiate images based on color, therefore mostly color features are used in CBIR. When image contain just an object, Color moment is mostly used to represent color features especially. Regularity, directionality, smoothness and coarseness are some of the texture properties perceived by human eye. Gabor filter and wavelet transform for texture feature extraction has proved to be very effective in describing visual content via multi-resolution analysis. The paper mainly gives result of CBIR using combination color moment for color feature and Gabor wav late for texture feature. Also paper gives retrieval of images from medical database.