Automatic LED chips defect inspection using level set method of image segmentation

Several types of defects in the LED chips may be caused from the manufacturing environments, these defects can result in the degradations of the parameters and performance. Hence it is very necessary to perform the defect detection of LED chips for effectively enhancing the production quality. In this paper, a new method is presented for the defect inspection of LED chips. The method makes use of both the support vector machine and the image segmentation based on level set to acquire the features of LED chip images and to carry out the inspection. First of all, the support vector machine is used to perform the clustering for the original LED images, the margin of region clustering is used as the initial contour curve. Secondly, the segmentation using level set is implemented for the LED images. The features of LED images are extracted, then the database of features is constructed. Therefore, an automatic inspection system for LED chip is built, the system can recognize the defective LED chips. The experimental results demonstrate that the presented method in this paper is able to detect the defects in the LED chips accurately.

[1]  Hong-Dar Lin,et al.  A Wavelet-Based Neural Network Applied to Surface Defect Detection of LED Chips , 2007, ISNN.

[2]  G. Meneghesso,et al.  Analysis of Defect-Related Localized Emission Processes in InGaN/GaN-Based LEDs , 2012, IEEE Transactions on Electron Devices.

[3]  Divya Tomar,et al.  An effective Weighted Multi-class Least Squares Twin Support Vector Machine for Imbalanced data classification , 2015, Int. J. Comput. Intell. Syst..

[4]  MuDer Jeng,et al.  Radial Basis Function Neural Networks for LED Wafer Defect Inspection , 2007, Second International Conference on Innovative Computing, Informatio and Control (ICICIC 2007).

[5]  Changming Wang,et al.  Narrow Band Region-Based Active Contours Model for Noisy Color Image Segmentation , 2014, TheScientificWorldJournal.

[6]  Chuan-Yu Chang,et al.  Learning Vector Quantization Neural Networks for LED Wafer Defect Inspection , 2007, Second International Conference on Innovative Computing, Informatio and Control (ICICIC 2007).

[7]  Xuehui Tao.  Performance Characterization and Theoretical Modeling of Emitted Optical Power for High-Power White-LED Devices , 2015, IEEE Transactions on Electron Devices.

[8]  Seung-Ryol Maeng,et al.  Thermal characteristics for chip on metal package of LED lighting module , 2015 .

[9]  D. Wuu,et al.  Analysis of the Thickness Effect of Undoped Electron-Blocking Layer in Ultraviolet LEDs , 2014, IEEE Transactions on Electron Devices.

[10]  Mian Tao,et al.  Effect of die attach adhesive defects on the junction temperature uniformity of LED chips , 2012, 2012 35th IEEE/CPMT International Electronics Manufacturing Technology Conference (IEMT).

[11]  E. Rosseel,et al.  Gan-on-Si process defect detection and analysis for HB-LEDs and power devices , 2013, ASMC 2013 SEMI Advanced Semiconductor Manufacturing Conference.

[12]  Ron Kimmel,et al.  Multi-Region Active Contours with a Single Level Set Function , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  MuDer Jeng,et al.  Application of Two Hopfield Neural Networks for Automatic Four-Element LED Inspection , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[14]  C. Tan,et al.  Systematic Root Cause Analysis for GaP Green Light LED Degradation , 2013, IEEE Transactions on Device and Materials Reliability.

[15]  Chung-Feng Jeffrey Kuo,et al.  Automatic inspection system of LED chip using two-stages back-propagation neural network , 2014, J. Intell. Manuf..