A subjective-contour generation LSI system with expandable pixel-parallel architecture for vision systems

Since each part along the visual pathway in the brain has typical functions, developing dedicated LSIs for such functions is important. Ultimately, brain-like VLSI vision systems can be realized by combining such LSIs and digital media processors. The key to achieve brain-like artificial vision systems is the interaction between low- and high-level processing parts (e.g. V1-IT) by means of feedforward/feedback connections, and therefore massively parallel architecture and connectivity are essential for real-time operation.