An FPGA Implementation of a Hopfield Optimized Block Truncation Coding

This paper presents an implementation for image compression using variable block truncation coding (BTC) on a field programmable gate array (FPGA). The compression technique is improved by employing a cost function obtained using Hopfield neural network (HNN), upon which a block is classified as either a high- or a low-detail block. Accordingly, different blocks are coded with different bit rates and thus better compression ratios are achieved. The paper formulates the utilization of HNN within the BTC algorithm in such a way that a viable FPGA implementation is produced. The Xilinx Virtex EBTC implementation has shown to provide a processing speed of about 1.113 times 106 of pixels per second with a compression ratio which varies between 1.25 and 2 bits per pixel, according to the image homogeneity

[1]  Salwa M. Nassar,et al.  FPGA implementation of block truncation coding algorithm for gray scale and color images , 2003, CCECE 2003 - Canadian Conference on Electrical and Computer Engineering. Toward a Caring and Humane Technology (Cat. No.03CH37436).

[2]  Barry G. Evans,et al.  Hardware structure for Walsh-Hadamard transforms , 1998 .

[3]  J. J. Hopfield,et al.  “Neural” computation of decisions in optimization problems , 1985, Biological Cybernetics.

[4]  T. J. Terrell,et al.  Image compression by a variable block size BTC technique using Hopfield neural networks , 1992 .

[5]  Mohamed S. Kamel,et al.  Image compression by variable block truncation coding with optimal threshold , 1991, IEEE Trans. Signal Process..

[6]  Sunggu Lee.  Design of Computers and Other Complex Digital Devices , 1999 .

[7]  Hazem M. Abbas,et al.  FPGA implementation of block truncation coding algorithm for gray scale images , 2003, Proceedings of the 2003 International Symposium on Circuits and Systems, 2003. ISCAS '03..

[8]  H. B. Mitchell,et al.  Block truncation coding using Hopfield neural network , 1992 .

[9]  Ernest Jamro,et al.  Implementation of multipliers in FPGA structures , 2001, Proceedings of the IEEE 2001. 2nd International Symposium on Quality Electronic Design.

[10]  David A. Patterson,et al.  Computer Architecture: A Quantitative Approach , 1969 .

[11]  T. J. Terrell,et al.  Variable bit rate block truncation coding for image compression using Hopfield neural networks , 1993 .

[12]  Laxmi N. Bhuyan,et al.  High-performance computer architecture , 1995, Future Gener. Comput. Syst..

[13]  Long-Wen Chang,et al.  Image compression using optimal variable block truncation coding , 1999, 1999 IEEE Third Workshop on Multimedia Signal Processing (Cat. No.99TH8451).

[14]  Roger F. Woods,et al.  An investigation of reconfigurable multipliers for use in adaptive signal processing , 2000, Proceedings 2000 IEEE Symposium on Field-Programmable Custom Computing Machines (Cat. No.PR00871).

[15]  Marcus Randall,et al.  FPGA based custom computing machines for irregular problems , 1998, Proceedings 1998 Fourth International Symposium on High-Performance Computer Architecture.

[16]  Michael J. Wirthlin.  Constant Coefficient Multiplication Using Look-Up Tables , 2004, J. VLSI Signal Process..