Designing and Performance Assessment of a Two Level Color Image Compression Technique using SVD & DCT

Nowadays, computer technology is mostly concerned with storage capacity and performance. Compression of digital images has become a fundamental aspect of their transmission and storage. Due to storage and bandwidth constraints, it has become necessary to compress images before to transmission and storage. Not only can image compression techniques help reduce storage space requirements, they also aid increase transmission bandwidth.Color images are in trend these days during communication. Most of the researchers have worked only on grayscale images. Some efficient compression research for color images has not been done yet. This research proposes a hybrid approach that encompasses two state-of-the-art image compression methods: Discrete Cosine Transform (DCT) and Singular Value Decomposition (SVD). This research involves the advantages and strength of state-of-the-art image compression methods that enable us to compress the color images without additional cost incomputation, space and time. Here in this research, for experimental purposes, seven standard images have been used for compression using a proposed hybrid method is done. Performance analysis of the proposed method is done using the performance evaluation matrices, i.e., Size after Compression, Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), Normalized Co-relation (NC), Compression Ratio, and % space-saving. The proposed methodperformance is also correlated with the two latest image compression methods, i.e., Discrete Cosine Transform Block Truncation (DCTBT) and Discrete Cosine Transform - Vector Quantization (DCT-VQ). The results validate that the hybrid proposed color image compression method is much better as compared to existing latest methods in terms of compressed image quality (PSNR, MSE, and NC) and compressed files size (Compression Ratio and % space-saving).