الخلاصة

ABSTRACT - In spite of the great development, that has taken place in image retrieval systems. There is an urgent need to find a system that capable of distinguish and recognize objects in the artistic images which also called painting images. This interest dreams remains as long as there are many attentions in the field of art and history. Painting images does not contain a unique structure or color spaces as in real images. Therefore, the implement of such image processing techniques are very difficult when painting images are used. This paper introduced a new approach for detection, recognition and then retrieving painting images that involves the query object. SURF algorithm has modified and adopted in our work to extract the feature vectors, and then Hash function used to index it in database. Al-Qazvin dataset has used to provide a system that able to recognize and retrieve painting images for the selected dataset based on user query. End user feedback also considered to correct the result of retrieving in forthcoming tasks. The main goal of this paper is to provide a new approach for perception the painting images based on its contents. This perception of certainly it can help search engines to include painting images. F-measure, Precision and Recall used to evaluate the proposed system.