Heuristic hybrid genetic algorithm based shape matching approach for the pose detection of backlight units in LCD module assembly

Abstract

Backlight unit (BLU) and open cell are two critical parts of the liquid crystal display (LCD) module (LCM) which is the most significant component of LCD TV. To place the open cell into a BLU automatically using an assembly robot, this paper proposes a heuristic hybrid genetic algorithm (HHGA) based shape matching approach to detect the pose (orientation and position) of the BLU. The approach takes advantages of line structures of the BLUs to avoid the most time-consuming exhaustive search. Firstly, obtain initial orientation of a BLU by the dominant orientations which can be obtained with the statistical gradient orientation histograms. Secondly, search the optimal pose through the HHGA which mainly consists of local search strategy, crossover strategy, clone strategy, and mutation strategy. Local search strategy is designed according to the rising trend of matching features around the optimal pose and along the lines. Crossover and clone are heuristic strategies designed according to the distribution characteristics of local maxima to produce new meaningful offspring. Mutation is a necessary strategy to keep the diversity of the population. The performance of the proposed approach has been tested on an image database acquired from the LCM assembly lines and compared with standard hybrid GA and exhaustive search by a new statistical indicator. Experimental results show that the proposed approach has a high efficiency within limited time and is suitable for the pose detection of the BLUs.