Automatic Inspection of Small Component on Loaded PCB Based on Mean-Shift and Support Vector Machine

Automatic inspection of small components on loaded Printed Circuit Board (PCB) is difficult due to the requirements of precision and high speed. In this paper, a mean-shift and Support Vector Machine (SVM) based method for inspection of small components on loaded PCB is presented. Firstly, the images of small components are smoothened using mean-shift method and then their binary images are obtained by adaptive segmentation algorithm. Next, some features are extracted from the binary images and are input to a trained SVM to diagnose whether the small components are located correctly. The experimental results show that the proposed approach is effective and feasible to inspect small components on loaded PCB.

[1]  Shan Zeng,et al.  Hand-written numeral recognition based on Zernike moment , 2008, 2008 International Conference on Wavelet Analysis and Pattern Recognition.

[2]  Yoshihiko Hamamoto,et al.  Normalization techniques of handwritten numerals for Gabor filters , 1997, Proceedings of the Fourth International Conference on Document Analysis and Recognition.

[3]  R. Brereton,et al.  Support vector machines for classification and regression. , 2010, The Analyst.

[4]  Robert Sabourin,et al.  On the performance of wavelets for handwritten numerals recognition , 2002, Object recognition supported by user interaction for service robots.

[5]  J. Platt.  Sequential Minimal Optimization : A Fast Algorithm for Training Support Vector Machines , 1998 .

[6]  David Burshtein,et al.  Support Vector Machine Training for Improved Hidden Markov Modeling , 2008, IEEE Transactions on Signal Processing.

[7]  Ching Y. Suen,et al.  Computer recognition of unconstrained handwritten numerals , 1992, Proc. IEEE.

[8]  M.M. Ali,et al.  An Efficient Fuzzy Method for Bangla Handwritten Numerals Recognition , 2006, 2006 International Conference on Electrical and Computer Engineering.

[9]  John D. Lee,et al.  Real-Time Detection of Driver Cognitive Distraction Using Support Vector Machines , 2007, IEEE Transactions on Intelligent Transportation Systems.

[10]  Yizong Cheng,et al.  Mean Shift, Mode Seeking, and Clustering , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  V. Vapnik.  Estimation of Dependences Based on Empirical Data , 2006 .

[12]  You-dong Ding,et al.  Performance Analysis of Handwritten Numerals Recognition Based on Multiwavelet Neural Network , 2008, 2008 Congress on Image and Signal Processing.

[13]  Marimuthu Palaniswami,et al.  Support Vector Machines for Automated Recognition of Obstructive Sleep Apnea Syndrome From ECG Recordings , 2009, IEEE Transactions on Information Technology in Biomedicine.

[14]  Faruq A. Al-Omari.  Handwritten Indian numeral recognition system using template matching approaches , 2001, Proceedings ACS/IEEE International Conference on Computer Systems and Applications.

[15]  Karim Faez,et al.  Feature extraction with wavelet transform for recognition of isolated handwritten Farsi/Arabic characters and numerals , 2002, 2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628).

[16]  Wei Lu,et al.  Handwritten Numeral Recognition Based on DCT Coefficients and Neural Network , 2005, 2005 International Conference on Neural Networks and Brain.

[17]  Yan Wang,et al.  Automatic inspection of small component on loaded PCB based on SVD and SVM , 2006, SPIE Optics + Photonics.

[18]  Larry D. Hostetler,et al.  The estimation of the gradient of a density function, with applications in pattern recognition , 1975, IEEE Trans. Inf. Theory.

[19]  Ching Y. Suen,et al.  Extraction of hybrid complex wavelet features for the verification of handwritten numerals , 2004, Ninth International Workshop on Frontiers in Handwriting Recognition.

[20]  Madasu Hanmandlu,et al.  Input Fuzzy Modeling for the Recognition of Handwritten Hindi Numerals , 2007, Fourth International Conference on Information Technology (ITNG'07).

[21]  Alireza Alaei,et al.  Using Modified Contour Features and SVM Based Classifier for the Recognition of Persian/Arabic Handwritten Numerals , 2009, 2009 Seventh International Conference on Advances in Pattern Recognition.

[22]  Seong-Whan Lee,et al.  A dependency-based framework of combining multiple experts for the recognition of unconstrained handwritten numerals , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[23]  Jun Sun,et al.  An SVM-Based High-accurate Recognition Approach for Handwritten Numerals by Using Difference Features , 2007 .

[24]  Yoshihiko Hamamoto,et al.  Recognition of handwritten numerals using Gabor features , 1996, Proceedings of 13th International Conference on Pattern Recognition.