WAVELET TRANSFORM BASED ADAPTIVE IMAGE COMPRESSION ON FPGA

Abstract

Image processing systems can encode raw images with different degrees of precision, achieving varying levels of compression. Different encoders with different compression ratios can be built and used for different applications. The need to dynamically adjust the compression ratio of the encoder arises in many applications. One example involves the real-time transmission of encoded data over a packet switched network. To suitably adapt the encoder to varying compression requirements, adaptive adjustments of the compression parameters are required. This involves reconfiguring the encoder in an efficient manner. Our approach exploits the reconfigurable nature of Field Programmable Gate Arrays (FPGA), to adapt the encoder to the varying requirements in real time. A Wavelet transform based image compression scheme is implemented for encoding gray-scale frames of 512 by 512 pixels on FPGAs. By varying the zero thresholds, the encoder can achieve varying compression levels. The complete design of the encoder on FPGA is presented. Implementation details of the individual blocks are discussed in great detail. Finally, results from testing are reported and discussed.