Abstract
Content-based image retrieval (CBIR) is a technique uses visual contents such as color, texture and shape to search images from large scale image databases according to users' interest. In a CBIR, visual image content is represented in form of image features, which are extracted automatically and there is no manual intervention, thus eliminating the dependency on humans in the feature extraction stage. Recent studies in CBIR get the similarity results and retrieve images based on one type of feature which are color, texture or shape. In this study authors proposed a fusion based retrieval model for merging results taken from color and texture image features based different fusion methods. After implementing our proposed retrieval model on Wang image dataset which widely used in CBIR, the results show that CombMEAN fusion approach has the best and high precision value and outperformed both individual color and texture retrieval model in both top10 and top20 retrieved images.