Fumihiko Saitoh

Boundary extraction of brightness unevenness on LCD display using genetic algorithm based on perceptive grouping factors

This paper proposes a system and a method to detect brightness unevenness in LCD displays to automate the visual inspection of LCD. In the image that includes edge pixels to form the disconnected boundary of a brightness unevenness and noisy pixels, a visual continuous boundary is extracted using the genetic algorithm based on perceptive grouping factors in Gestalt psychology. The experimental results show that total 67 LCD displays including 25 LCD displays with brightness unevenness were inspected by the proposed method, and all brightness unevenness were detected successfully. Also, the extracted boundaries of brightness unevenness had similar forms to perceived brightness unevenness by the visual sense.