Content?based image retrieval using a fusion of global and local features

Color, texture, and shape act as important information for images in human recognition. For content-based image retrieval, many studies have combined color, features to improve the retrieval performance. However, there not been powerful methods combining all features. This study proposes a method that uses local global of shape. The color are extracted from autocorrelogram; texture magnitude complete binary pattern Gabor correlation revealing characteristics; singular value decomposition reflects characteristics. In this work, an experiment is performed compare proposed with those use our partial some existing techniques. results show average precision 19.60% higher than 9.09% recent ones. conclusion, superior over other terms