Read more
The field of content-based image retrieval (CBIR) focuses on the analysis of image content and the development of tools to represent the visual content in a way that can be efficiently searched and compared. The main aim of this work is to improve the retrieval performance of medical images retrieval methodology that is based on various types of visual features (such as color, texture and shape). The improvement is based on a new multi-level retrieval scheme that deals with different types of medical databases. Within the two phases of the system (i.e., enrollment and retrieval) some new features are introduced. Also, to reach high precision and recall levels, various methods are combined; such as the similarity measures based on Euclidian distance and the artificial neural network trained using back propagation algorithm.
About the author
B.Sc. in Computer Science, University of Mosul, Iraq, M.Sc. and Ph.D. in Computer Science, University of Sulaimani, Iraq. Research interests:Artificial Neural networks, CBIR, Database, Fractals, FPGA, Image Processing, Wireless Communication.
