¹School of electrical engineering,Anhui Polytechnic University,Wuhu Anhui province,China
²Electronic science and technology, Southeast University,Nanjing Jiangsu province,China

---

Abstract—Harris corner detection algorithm called Harris corner detector is a very effective corner algorithm for gray-scale images. The corners extracted by Harris corner detector are stable, reliable, homogeneous and reasonable. However, it has own inevitable limitations. For the shape recognition of parts, an improved Harris corner detector is proposed in this paper. Based on the analysis of Harris corner detector, B-spline function is chosen as smooth filter instead of Gaussian function. And then the convolution template of B-spline function is provided. Some experiment results indicate that the improved Harris corner detector is effective and superior.

Index Terms—hape recognition, Harris corner detector, smooth filter, Gaussion function, B-spline function, convolution template.

[PDF]

Cite: Huicheng Yang, Ying Ma, Hui Yang, Mingshu Li, "Parts Shape Recognition Based on Improved Harris Corner Detection Algorithm," Journal of Computers vol. 9, no. 10, pp. 2371-2378, 2014.