Content based Video frame Image Retrieval (CBVFIR) systems are used to retrieve useful contents from a massive amount of video frames. A proposed novel technique for video frame image retrieval using GWO_SVM classifier with multi-features such as HOG (Histogram of Oriented Gradient), Color moment, Gabor and wavelet. Initially, the color feature is extracted from the satellite image using the peculiar color moments and are invariant to scaling and rotation. Texture features are extracted using dominant HOG, Gabor and Wavelet then the feature selection methods are separately classified. In the existing system, the video frames are first retrieved and then classified. In the proposed method, the video frames retrieval time is less since it has to search the whole database for performing the retrieval. Moreover the retrieval rates obtained by the existing techniques are not satisfactory. Hence in this paper proposed a novel Multi feature based GWO-SVM technique is used in that initially classifies the different class from the database and get the similar retrieval image based upon the feature of the query image. Thus by finding the retrieval rate after performing the classification, it is evident that output retrieval rate is better by comparing with other models. The fundamental performance metrics like accuracy, sensitivity and specificity are taken into comparison. The proposed method has higher accuracy when it is compared to the accuracy of other feature based SVM.
Volume 12 | 01-Special Issue
Pages: 760-774
DOI: 10.5373/JARDCS/V12SP1/20201127