Reading Recognition of Automobile Dashboard

A recognition scheme based on RGB color space image processing is proposed to recognize the representation number of car pointer. The color characteristics of the center and pointer of the car dashboard are obvious. After analyzing the histograms of R, G and B components, the Euclidean distance method of the three components is used to divide the center and pointer of the car dashboard. Then, using the thinning method to extract the skeleton of the center of the circle and obtain the coordinates of the center of the circle. Taking the coordinates of the center of the circle as the origin to establish a new coordinate system. Finally, the coordinates of the centroid of the pointer are calculated by using the method of minimum external rectangle. The centroid and the center of the circle are connected to determine a straight line. The reading of the pointer is identified by the Angle between the line and the reference line. The method is applied to the reliability experiment of automobile instrument, and the results show that the accuracy of identifying pointer indicator is relatively high and the working efficiency can be improved.