Due to the explosion of video based information proliferating in the world due to the ubiquitous usage of video cameras the amount of video based information that is currently being generated around the world is huge. And due to security purposes it is becoming imperative that these video data needs to be stored in computer memory for an extended period of time for referrals by security agencies. Because of the advancement of imaging technologies that is being used nowadays it is possible to capture extremely detailed high definition images. But it is not physically possible to store all these high-definition images in computer memories for a long time because infrastructure providers will run out of memory. Image compression is a technology which assists us in this regard. Nowadays this technology has moved from image compression to video compression to compression of 3- dimensional videos which is now becoming more and more popular due to the ever increasing usage of Augmented Reality, Virtual Reality and Ec The quantity of image data produced in modern surveillance networks is rising exponentially year on year which necessitated development of novel schemes for reducing the sizes of the images captured by CCTV cameras while not compromising on the image quality increases when the images are decompressed. This paper proposed a novel Deep Neural Network based method of compressing images in which the image accuracy is not lost but the space it occupies in the memory storage of the computes is reduced greatly compared to other image compression schemes, this proposed scheme is best suited for usage in CCTVs and other networks using Internet of Things which record images and videos continuously.

Shivganga Patil, Lakshmi Patil
Sharnbasva University, India

S-BHM, Slimming Encoders, Image Compression
Yearly Full Views
Published By :
Published In :
ICTACT Journal on Image and Video Processing
( Volume: 14 , Issue: 4 , Pages: 3301 - 3304 )
Date of Publication :
May 2024
Page Views :
Full Text Views :

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.