Modified Holoentropy based arithmetic coding for ROI based image compression and data transmission
Sarath V. Sankaran, J. D. Dorathi Jayaseeli · The Imaging Science Journal · 2025
This Paper proposes a modified Holoentropy Based Arithmetic coding (AC) for ROI image compression. Here, the ROI extraction is done under two compressions they are lossless and lossy compression. First, the lossless compression on the ROI region is applied using Lembel-Ziv-Welch (LZW). Meanwhile, the lossy compression on the Non-ROI region is applied by using forward transform and Quantization. Then, the modified Holoentropy-based AC is applied to obtain a compressed bit stream in both scenarios. The two compressed bit streams are fused with the label to generate the compressed data. In the decompression phase, inverse LZW, Inverse modified AC, Inverse Quantization and Inverse transform are applied to generate a non-ROI image. The generated RoI image and non-RoI image are fused to obtain the original image. The proposed method has a minimum Mean Squared Error of 0.055, a Peak Signal-to-Noise Ratio (PSNR) of 43.451 dB, and a Structural Similarity Index (SSIM) of 0.975.