Neuro-Wavelet based Efficient Image Compression using Vector Quantization

Abstract

In the last few decades, Digital image compression has received significant attention of researchers. Recently, based on wavelets there has been many compression algorithms. In comparison to other compression techniques, image compression using wavelet based algorithms lead to high compression ratios. In this paper, we have proposed a image compression algorithm which combines the feature of both wavelet transform and Radial Basis Function Neural Network along with vector quantization. First the images are decomposed into a set of subbands having different resolution with respect to different frequency bands using wavelet filters. Based on their statistical properties, different coding and quantization techniques are employed. The Differential Pulse Code Modulation (DPCM) is used to compress the low frequency band coefficients and Radial Basis Function Neural Network (RBFNN) is used to compress the high frequency band coefficients. The hidden layer coefficients of RBFNN subsequently are vector quantized so that without much degradation of the reconstructed image, the compression ratio can be increased. In terms of peak signal to noise ratio (PSNR) and computation time (CT), a large compression ratio has been achieved with satisfactory reconstructed images in relation to the existing methods by using the proposed technique.

Hybrid Schemes Based on Wavelet Transform and Convolutional Auto-Encoder for Image Compression

“…Digital image compression is a topical research area in image processing domain as it is employed in several applications such as aerial surveillance, recognition, medicine, multimedia… Moreover, every day the number of images handled keeps growing which requires more and more efficiency image compression methods that output images visually acceptable and occupied less storage space. In recent years and thanks to Machine Learning advances, different image compression techniques combining multi-resolution aspect of wavelets to parallel processing of data and training process of neuronal networks emerged for instance Zang and Beneveniste (1992), Osowski et al (2006), Zhang (1997), Singh et al (2012), Ahmadi et al (2015). In fact, neural network implementation during each stage of an image compression process has received an important attention from scientists and many works have been developed during last years as in Krishnanaik et al (2013), Denk et al (1993), Dimililer and Khashman (2008), Alexandridis and Zapranis (2013).…”