Title :
Automatic counting of packaged wafer die based on machine vision
Author :
Hsuan-Ting Chang ; Ren-Jie Pan
Author_Institution :
Dept. of Electr. Eng., Nat. Yunlin Univ. of Sci. & Technol., Yunlin, Taiwan
Abstract :
This paper presents a robust method to automatically determine the number of packaged dies in the residual wafer image, in which most dies have been removed and packaged. We propose the die segmentation region detection algorithm based on vertically and horizontally cumulative histograms and die detection algorithm based on YCbCr color space. The abnormal cases of fractional dies in the wafer boundary and dropped dies during packaging are considered in the proposed method as well. In the experimental results, the proposed method achieves 100% accuracy in counting the number of packaged dies in the ten test cases.
Keywords :
computer vision; image colour analysis; image segmentation; production engineering computing; wafer level packaging; YCbCr color space; automatic counting; die detection algorithm; die segmentation region detection algorithm; horizontally cumulative histogram; machine vision; packaging; residual wafer image; vertically cumulative histogram; wafer die packaging; Conferences; Gray-scale; Histograms; Image color analysis; Image recognition; Image segmentation; Machine vision; IC packaging; YCbCr color space; die; optical inspection; wafer;
Conference_Titel :
Information Security and Intelligence Control (ISIC), 2012 International Conference on
Conference_Location :
Yunlin
Print_ISBN :
978-1-4673-2587-5
DOI :
10.1109/ISIC.2012.6449759