A Novel Image Compression Algorithm Based on Autoencoder for Biometric Template Protection Scheme

Abstract

Objectives: To evaluate the proposed deep learning-based method for biometric template protection schemes with other existing image compression methods. Methods: In this study, four image compression methods such as JPEG_LS, Vector quantization (VQ), Run-length encoding (RLE), and the Autoencoder methods are implemented. The experimental results are compared with the different performance parameters that are applied over the CASIA I iris dataset possessing 756 images. Findings: The proposed autoencoder method algorithm offered enhanced results in terms of PSNR, SSIM, MSE, and CR when compared to other transform methods. The deep neural network-based autoencoder algorithm achieved the highest compression ratio of 89.05 percent, while the conventional algorithms achieved the highest image quality rate of 94.05 percent. Novelty: A novel autoencoder-based image compression model has been proposed in this study. The proposed Autoencoder (AE) method incorporates five stages like Initialization, Learning compression representations, Generation of chaotic sequence, Image encryption and decryption, and Image reconstruction. The generation of the chaotic sequence using the stochastic logistic map, as well as the learning compression representations contributes towards the novelty of this study. Keywords: Image compression; Autoencoder; Runlength encoding (RLE); Vector quantization