Complete approach to automatic identification and subpixel center location for ellipse feature

Abstract

To meet the need of automatic image features extraction with high precision in visual inspection, a complete approach to automatic identification and sub-pixel center location for similar-ellipse feature is proposed. In the method, the feature area is identified automatically based on the edge attribute, and the sub-pixel center location is accomplished with the least-square algorithm. It shows that the method is valid, practical, and has high precision by experiment. Meanwhile this method can meet the need of instrumentation of visual inspection because of easy realization and without man-machine interaction.

References

[1] XueT., WuB., ZhuJ.-g., YeS.-h.. Sensors and Actuators A: Physical, 2007, 135: 185

[2] QuanW., WangZ.-q., ZhangC.-s., MuG.-g.. Journal of Optoelectronics Laser, 2002, 13: 1148

[3] LiuX., WuL.-f., LinJ.. Signal Processing, 2004, 20: 623

[4] ZouY.-m., WangB.. Journal of System Simulation, 2006, 18: 1935

[5] DuanR.-l., LiY.-h., LiQ.-x., JiaH.-b.. Journal of Optoelectronics Laser, 2006, 17: 871

[6] HuM.. IRE Transaction on Information Theory, 1962, 8: 179

[7] ChenC. C.. Pattern Recognition, 1993, 26: 683

[8] MoreJ. J.WatsonG. A.. Numeriacal Analysis, 1977, Berlin, Springer-Verlag, 105

[9] ZhangZ. Y.. IEEE Trans PAMI, 2000, 22: 1330