Image Features Evaluation Using New Algorithm Proposed For Reducing Image Feature Number & Size Stored In Database

Abstract

This study proposes technique that capable of reducing image features size andnumber stored in the database. The proposed technique depends on the image contentof numerical values for the three basic colors (red, green and blue) and then stores it inthe database and to be used for image retrieval. This technique has been developedbased on recent image retrieval procedures that include Color Descriptor Matrix,YCbCr Color Space and Discrete Cosine Transform. Those procedures have beenapplied sequentially on the image and finally Kekre’s Transform has been applied inthe last stage of this technique to evaluate image features and reduce its stored size inthe database. The validity and accuracy of the proposed technique have beenevaluated through experiments by applying Kekre’s Transform on Color DescriptorMatrix instead of using Kekre’s Transform directly on the image in order to reduce itsfeature stored size. Another experiments have been tested and evaluated that includethe application of YCbCr Color Space on the Color Descriptor Matrix andfinally Kekre’s Transform to be executed and explore the image features size andcompare it with the previous stage. The effect of applying the Discrete CosineTransform on the YCbCr Color Space and finally the Kekre’s Transform on the imagefeatures size has been studied and compared with the previous step. It is concluded thatthe best reduction in image features size stored in the database can be obtained onlywhen Kekre’s Transform applied in the last step of the proposed technique withunchanged threshold based image retrieval ratios. Parametric study has been conductedto investigate the effect of applying the new algorithm on both isolated and mixedimage groups. Good precision ratios of 82% and 65% have been obtained for theisolated and mixed image groups respectively.