Automated design of image recognition in capturing environment

作者：Ogata Taiki^*; Yukisawa Taigo; Arai Tamio; Ueyama Tsuyoshi; Takada Toshiyuki; Ota Jun

来源：IEEJ Transactions on Electrical and Electronic Engineering, 2017, 12: S49-S55.

DOI：10.1002/tee.22551

• image recognition
• image-acquisition environment
• automated design
• picking system
• camera distance
• illumination strength

This study aims at automating the design of the image-recognition algorithm and the image-acquisition environment for an industrial picking system. Here for the image-recognition algorithm, a preprocessing image parameter and a discriminator using local features in images are targeted. For the image-acquisition environment, the camera distance from the target objects and the illumination strength of each RGB color are considered. The problem is formulated as an optimization problem, and a method is proposed to derive solutions using a two-phase random multistart local optimization for the image-acquisition environment and the image-recognition algorithm. In addition, experiment-based optimization is made to deal with the uncertainty of the capturing environment. Furthermore, positions and angles are considered in a robot coordinate system to simplify the image-acquisition process. The three evaluation experiments targeting objects with different surface characteristics are conducted. The results show that the proposed system successfully designed parameter sets for the image-acquisition environment and the image-recognition algorithm that suited the characteristics of the target objects. The object recognition rate, that is, F measure, is 1 for all objects in all the three experiments.

• 出版日期2017-12