A Real-time Auto-recognition Method for Pointer-meter under Uneven Illumination
Yuan Rao, Fei Yan, Zhuang Yan, Guojian He · 2019
Traditional pointer-type meters are widely applied in different environments for its excellent stability. The results of indication recognition limit the progress of the whole industrial process directly. However, gross and random errors often occur in manual reading of precision pointer-type meters. In this paper, we proposed a real time auto-recognition method for pointer-meter which can cope with uneven light and adapt to different environments by using computer vision and image processing technology. Experimental results show that the proposed method is able to recognize pointer meter readings under uneven illumination with high recognition accuracy in a short time.