Gray-level image recognition on a dynamically reconfigurable vision architecture

Recently, for use in autonomous vehicles and robots, demand has been increasing for high-speed image recognition that is superior to that of the human eye. However, to recognize numerous images quickly, such system requires many template images to be read out dynamically from memory. They must then be sent to a processor quickly. Realizing such high-speed real-time image recognition operation is difficflt because of the bottleneck of transfer speed between the memory and the processor. Therefore, to improve the bottleneck, a dynamically reconfigurable vision architecture that can recognize binarized images has been presented. However, to date, no dynamically reconfigurable vision architecture that can recognize gray-level images has ever been presented. Therefore, this paper presents experimentation related to a more advanced dynamically reconfigurable vision architecture that can recognize gray-level images.