Parts Shape Recognition Based on Improved

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.

[1]  Yu-Ping Wang,et al.  Scale-Space Derived From B-Splines , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Yong Wang,et al.  An Efficient Vehicle Model Recognition Method , 2013, J. Softw..

[3]  I. J. Schoenberg,et al.  Cardinal interpolation and spline functions , 1969 .

[4]  Pengfei Li,et al.  The Research of Automatic Registering Detection of Rotary Screen Printing Machine Based on MeanShift and Fast Block-Matching Algorithm , 2012, J. Comput..

[5]  Peter Rockett,et al.  Performance assessment of feature detection algorithms: a methodology and case study on corner detectors , 2003, IEEE Trans. Image Process..

[6]  Huang Xin.  A Feature Detection Method Based on Harris Corner and Difference of Gaussian , 2008 .

[7]  Junhua Tong,et al.  Development of automatic system for the seedling transplanter based on machine vision technology , 2012, 2012 IEEE International Conference on Computer Science and Automation Engineering (CSAE).

[8]  Xavier Descombes,et al.  A Multiresolution Approach for Shape from Shading Coupling Deterministic and Stochastic Optimization , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Qingyong Li,et al.  A Real-Time Visual Inspection System for Discrete Surface Defects of Rail Heads , 2012, IEEE Transactions on Instrumentation and Measurement.

[10]  Paijit Kochakornjarupong,et al.  Trademark image retrieval by local features , 2011 .

[11]  Bo Fu,et al.  Cascade Classifier Using Combination of Histograms of Oriented Gradients for Rapid Pedestrian Detection , 2013, J. Softw..