Effective and Efficient Video Compression by the Deep Learning Techniques

作     者：Karthick Panneerselvam K.Mahesh V.L.Helen Josephine A.Ranjith Kumar 

作者机构：Department of Computer ApplicationsAlagappa UniversityKaraikudiIndia Department of Computer Science and Engineeringlovely professional UniversityPhagwaraPunjabIndia School of Business and ManagementChrist UniversityBengaluruKarnatakaIndia 

出 版 物：《Computer Systems Science & Engineering》 (计算机系统科学与工程（英文）)

年 卷 期：2023年第45卷第5期

页      面：1047-1061页

核心收录：

学科分类：0810[工学-信息与通信工程] 0808[工学-电气工程] 08[工学] 0701[理学-数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Convolutional neural networks(CNN) generative adversarial network(GAN) singular value decomposition(SVD) K-nearest neighbours(KNN) stochastic gradient descent(SGD) long short-term memory(LSTM) 

摘      要：Deep learning has reached many successes in Video *** has become a growing important part of our daily digital *** advancement of better resolution content and the large volume offers serious challenges to the goal of receiving,distributing,compressing and revealing highquality video *** this paper we propose a novel Effective and Efficient video compression by the Deep Learning framework based on the flask,which creatively combines the Deep Learning Techniques on Convolutional Neural Networks(CNN)and Generative Adversarial Networks(GAN).The video compression method involves the layers are divided into different groups for data processing,using CNN to remove the duplicate frames,repeating the single image instead of the duplicate images by recognizing and detecting minute changes using GAN and recorded with Long Short-Term Memory(LSTM).Instead of the complete image,the small changes generated using GAN are substituted,which helps with frame-level *** wise comparison is performed using K-nearest Neighbours(KNN)over the frame,clustered with K-means and Singular Value Decomposition(SVD)is applied for every frame in the video for all three colour channels[Red,Green,Blue]to decrease the dimension of the utility matrix[R,G,B]by extracting its latent *** frames are packed with parameters with the aid of a codec and converted to video format and the results are compared with the original *** experiments on several videos with different sizes,duration,Frames per second(FPS),and quality results demonstrated a significant resampling *** normal,the outcome delivered had around a 10%deviation in quality and over half in size when contrasted,and the original video.