Deep Features and Clustering Based Keyframes Selection with Security

Abstract

The digital world is developing more quickly than ever. Multimedia processing and distribution, however become vulnerable issues due to the enormous quantity and significance of vital information. Therefore, extensive technologies and algorithms are required for the safe transmission of messages, images, and video files. This paper proposes a secure framework by acute integration of video summarization and image encryption. Three parts comprise the proposed cryptosystem framework. The informative frames are first extracted using an efficient and lightweight technique that make use of the color histogram-clustering (RGB-HSV) approach's processing capabilities. Each frame of a video is represented by deep features, which are based on an enhanced pre-trained Inception-v3 network. After that summary is obtain using the K-means optimal clustering algorithm. The representative keyframes then extracted using the clusters highest possible entropy nodes. Experimental validation on two well-known standard datasets demonstrates the proposed methods superiority to numerous state-of-the-art approaches. Finally, the proposed framework performs an efficient image encryption and decryption algorithm by employing a general linear group function GL_n (F). The analysis and testing outcomes prove the superiority of the proposed adaptive RSA.