A Fast and Accurate Corner Detector Based on Harris Algorithm

Harris is one of the most widely used corner detection algorithms which is based on intensity. Because of the practice of Gaussian smoothing link, Harris algorithm has a good performance on its stability and robustness, but it is also the direct reason of the limitation of its computing speed. Furthermore, its positioning accuracy of T-type, L-type and Arrow-type corners is low. In this paper, an improved algorithm is presented to solve the efficiency and accuracy problem of Harris algorithm. Firstly, we integrated the corner response function of MIC algorithm into the Harris algorithm to reduce the calculation amount of Gaussian smoothing link, so that the computing speed is obviously increased. Then we investigate a 3X3 mask to calculate the number of the pixels which their gray values are similar to the central point of the mask. We found that for real corner, the number of its similar points is the minimum among its 8 neighborhoods. In view of this, we added a comparison function before the No Max Suppression step to exclude some disturbance points nearby the real corners. Hence the positioning accuracy is increased significantly. In order to compare the accuracy of the improved algorithm and Harris algorithm, an evaluation standard is also proposed. The experimental results show that the detection time of the improved algorithm is only 31.2% that of the original Harris algorithm, and also, the improvement on positioning accuracy of L-type, T-type and Arrow-type corners are realized.