During the testing and sorting of LED chips, traditional methods do not exclude the polycrystalline and fragmentary LED chips from the normal chips well. The purpose of this paper is to propose a new algorithm to solve this problem. The algorithm consists of three steps. Firstly, present a simple but efficient image segmentation method to get blobs. Secondly, analyze the blobs to exclude abnormal blobs and predict the pose (position and orientation) of the potential object based on the pose of the minimum enclosing rectangle (MER) of each remained blob. Finally, according to the predicted poses, locate the LED chips precisely in the originally captured image based on gradient orientation features. Experiments show that the algorithm is not only robust to illumination variation but also can locate the LED chips and exclude the polycrystalline and fragmentary chips efficiently.
This is a preview of subscription content, log in to check access.
Buy single article
Instant access to the full article PDF.
Price includes VAT for USA
Subscribe to journal
Immediate online access to all issues from 2019. Subscription will auto renew annually.
This is the net price. Taxes to be calculated in checkout.
Steele RV (2010) High-brightness LED market overview. Proc. SPIE 4445,Solid State Lighting and Displays, doi:10.1117/12.450027
B. L. L. W. Tao WU (2010) Automatic detect and match of LED dies basing on position. Processings of the Ninth International Conference on Machine Learning and Cybernetics,Qindao
Li Q, Zhang B (2006) A fast matching algorithm based on image gray value. J Softw 17:216–222
Ayache N, Faugeras OD (1986) A new approach for the recognition and positioning of two-dimensional objects. IEEE Trans Pattern Anal Mach Intell, pp. 44–54
Grimson WEL, Lozano-Perez T (1987) Localizing overlapping parts by searching the interpretation tree. IEEE Trans Pattern Anal Mach Intell, pp. 469–482
Koch MW, Kashyap RL (1987) Using polygons to recognize and locate partially occluded objects. IEEE Trans Pattern Anal Mach Intell, pp. 483–494
Ventura JA, Wan W (1997) Accurate matching of two-dimensional shapes using the minimal tolerance zone error. Image Vis Comput 15:889–899
Marimon D, Ebrahimi T (2007) Efficient rotation-discriminative template matching. Progress in Pattern Recognition, Image Analysis and Applications, pp. 221–230
Ullah F, Kaneko S (2004) Using orientation codes for rotation-invariant template matching. Pattern Recogn 37:201–209
X. Xu, P. van Beek and X. Feng (2014) High-speed object matching and localization using gradient orientation features. Proc. SPIE 9025, Intelligent Robots and Computer Vision XXXI: Algorithms and Techniques, 902507.
Cho H–J (2010) Wavelet transform based image template matching for automatic component inspection. Int J Adv Manuf Technol 50:1033–1039
Crispin AJ, Rankov V (2007) Automated inspection of PCB component using a genetic algorithm template-matching approach. Int J Adv Manuf Technol 35:293–300
Anbu A, Agarwal G, Srivastava G (2002) A fast object detection algorithm using motion-based region-of-interest determination. 14th Int Conf Digital Signal Process 2:1105–1108
Forssen PE, Moe A (2005) View matching with blob features. The 2nd Canadian Conference on Computer and Robot Vision, pp. 228–235
Goel S, Dabas S (2013) Vehicle registration plate recognition system using template matching. 2013 International Conference on in Signal Processing and Communication (ICSC), pp. 315–318
Otsu N (1975) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 11:23–27
Di Stefano L, Mattoccia S, Mola M (2003) An efficient algorithm for exhaustive template matching based on normalized cross correlation. 12th International Conference on Image Analysis and Processing, pp. 322–327
About this article
Cite this article
Zhong, F., He, S. & Li, B. Blob analyzation-based template matching algorithm for LED chip localization. Int J Adv Manuf Technol 93, 55–63 (2017). https://doi.org/10.1007/s00170-015-7638-5
- Gradient orientation
- Image segmentation
- Minimum enclosing rectangle