Color histogram based image retrieval technique for diabetic retinopathy detection

摘要

Diabetic Retinopathy (DR) is the critical and most common eye related disease. Early detection of DR is the best solution to prevent from this disease. This paper proposes an Image Retrieval technique that search and retrieve the query image from retinal Database. A retrieval process will be developed by extracting color histogram feature and then find the feature vector of desired size by setting the number of bins in histogram. For checking similarity Euclidean distance will be calculated between the query and database image. The color histogram retrieval system in HSV color space will provide better performance than in RGB color space. The presented system will reduces the professionals work to analyze every fundus image rather than diabetic affected image and develop a prototypical DR image management system to improve diagnostic performance.