Bilateral anisotropic Gabor wavelet transformation based deep stacked auto encoding for lossesless image compression

Abstract

SummaryA highly challenging aspect of the data compression technique is maintaining the quality of data that reconstructs in high compression rates. To overcome these limitations, a bilateral anisotropic Gabor wavelet transformation with deep stacked auto encoding (BAGWT‐DSAE) technique based lossesless image compression is proposed in this article to save the storage space and processing time during transferring the images. The proposed method contains three main processes namely preprocessing, compression and decompression. Initially input aerial image and digital image are taken and these images are given bilateral filter based preprocessing for eliminates the different types of noises and also multiple artifacts. Then the preprocessed images are given to anisotropic Gabor wavelet transformation based deep stacked auto encoding to compress and decompress the wavelet transform's sensitive sub‐bands effectually. In DSAE, the decoder of the auto encoder achieves a better quality decompressed image. The proposed method is implemented in MATLAB simulations run in PC through Intel Core, 8 GB of RAM, 2.50 GHz CPU and Windows 8. Then, the simulation performance of proposed BAGWT‐DSAE‐LIC method provides 20.23%, 24.85%, and 38.56% low compression ratio and 26.48%, 21.23%, and 12.53% lower computational time, 4.56%, 7.68%, and 8.34% high space saving than the existing methods.