论文信息 - EVOLUTION OF DIGITAL CIRCUITS OPERATING AS IMAGE FILTERS IN DYNAMICALLY CHANGING ENVIRONMENT

EVOLUTION OF DIGITAL CIRCUITS OPERATING AS IMAGE FILTERS IN DYNAMICALLY CHANGING ENVIRONMENT

This paper deals with an automatic design of image filters at hardware level in dynamic environment. The environment is modeled using eight different fitness functions representing eight types of noise. Various properties of adaptation process have been measured when these fitness functions were applied for a constant time. The resulting filters operate in average much better than the conventional solution.

Lukáš Sekanina | L. Sekanina

[1] Lukáš Sekanina,et al. AUTOMATIC DESIGN OF IMAGE OPERATORS USING EVOLVABLE HARDWARE , 2002 .

[2] James A. Foster,et al. Special Purpose Image Convolution with Evolvable Hardware , 2000, EvoWorkshops.

[3] Lukás Sekanina,et al. Image Filter Design with Evolvable Hardware , 2002, EvoWorkshops.

[4] Mehrdad Salami,et al. Evolvable hardware at function level , 1997, Proceedings of 1997 IEEE International Conference on Evolutionary Computation (ICEC '97).

[5] Jim Torresen,et al. Possibilities and Limitations of Applying Evolvable Hardware to Real-World Applications , 2000, FPL.

[6] Julian Francis Miller,et al. Cartesian genetic programming , 2000, GECCO '10.

[7] J. Urgen Branke. Evolutionary Approaches to Dynamic Optimization Problems -a Survey , 1999 .

[8] Lukas Sekanina,et al. DESIGN OF THE SPECIAL FAST RECONFIGURABLE CHIP USING COMMON FPGA , 2001 .

[9] Kazuyuki Murase,et al. Effect of Fitness for the Evolution of Autonomous Robots in an Open-Environment , 2001, ICES.

[10] Marco Tomassini,et al. Towards Evolvable Hardware: The Evolutionary Engineering Approach , 1996 .

[11] Andrew M. Tyrrell,et al. Simulation of Evolable Hardware to Solve Low Level Image Processing Tasks , 1999, EvoWorkshops.