Linear Transformation Pre-Filtering with VGG Frame-work Based on ANN for CBMIR

A comprehensive feature selection and weighting combination method with novel learning of ANN were introduced, for biomedical RETINA images retrieval. Modified Radon, and modified Hu Moments operators with weighting combinational methods were proposed for achieving higher percentage of retrieval. Besides that, these characteristics are re-composed for presenting outstanding statistic specification and spatial signals. This spatial and frequency information is obtained for all RETINA image dataset. Composition of shape & Textural features present robust vectors for retrieval of biomedical database. In addition, a ANN framework is proposed and applied to measure the similarity between the query and biomedical database. This novel scheme illustrates higher and better specialty in the RETINAI dataset. The results were compared and understood to be remarkable.