Multipurification of matching pairs based on ORB feature and PCB alignment case study

Abstract. To address the scale invariance and the mismatching problems of ORB (oriented FAST and rotated BRIEF), an improved algorithm based on multipurification was put forward and applied in PCB matching and positioning. ORB feature points were initially extracted from both the template image and the target image. Rough matching was then performed by the combination of k-nearest neighbor (k-NN) algorithm and best bin first search algorithm. Considering the existence of a large number of mismatches, the multipurification that consists of neighborhood ratio, bidirectional matching, and cosine similarity was used to purify the set of matching pairs. Finally, the affine matrix between the two images was solved by progressive sample consensus. The experimental results showed that the matching accuracy was significantly improved after the purification by the proposed method. The improved algorithm outperformed original ORB under the condition of image rotation and scaling. The mean rotation angle error was just 1/10th of that of original ORB. The time overhead of the improved algorithm was comparable to that of original ORB, which was about six times faster than that of speeded up robust features and 30 times faster than that of scale-invariant feature transform. The enhanced algorithm demonstrated great advantages in the improvement of accuracy, time overhead, and robustness for the PCB alignment.

[1]  Stefan Winkler,et al.  A general framework for image feature matching without geometric constraints , 2016, Pattern Recognit. Lett..

[2]  Pierre Vandergheynst,et al.  FREAK: Fast Retina Keypoint , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Amin Sedaghat,et al.  Very high resolution image matching based on local features and k-means clustering , 2015 .

[4]  Alexandre Bernardino,et al.  Shape Context for soft biometrics in person re-identification and database retrieval , 2015, Pattern Recognit. Lett..

[6]  Nayoung Lee,et al.  High-precision and ultrafast UV laser system for next-generation flexible PCB drilling , 2016 .

[7]  Andrea Sanna,et al.  Intensity variation function and template matching-based pedestrian tracking in infrared imagery with occlusion detection and recovery , 2015 .

[8]  A. Vinay,et al.  Feature Extractionusing ORB-RANSAC for Face Recognition , 2015 .

[9]  Praveen Ranjan Srivastava.  A cooperative approach to optimize the Printed Circuit Boards drill routing process using Intelligent Water Drops , 2015, Comput. Electr. Eng..

[10]  Md. Jan Nordin,et al.  Deformation invariant image matching based on dissimilarity of spatial features , 2016, Neurocomputing.

[11]  Gad M. Landau,et al.  Sequence similarity measures based on bounded hamming distance , 2016, Theor. Comput. Sci..

[12]  Vincent Lepetit,et al.  BRIEF: Binary Robust Independent Elementary Features , 2010, ECCV.

[13]  Kun-Huang Chen,et al.  A new particle swarm feature selection method for classification , 2013, Journal of Intelligent Information Systems.

[14]  Erez Farhan,et al.  Geometric Expansion for Local Feature Analysis and Matching , 2015, SIAM J. Imaging Sci..

[15]  György Kovács,et al.  A self-calibrating approach for the segmentation of retinal vessels by template matching and contour reconstruction , 2016, Medical Image Anal..

[16]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[17]  Cordelia Schmid,et al.  An Affine Invariant Interest Point Detector , 2002, ECCV.

[18]  Benjamin Balas,et al.  Invariant texture perception is harder with synthetic textures: Implications for models of texture processing , 2015, Vision Research.

[19]  Giuseppe Pirlo,et al.  Cosine similarity for analysis and verification of static signatures , 2013, IET Biom..

[20]  Fernando Puente León,et al.  Comparison of Fourier and normal angle descriptors for the content-based image retrieval , 2016 .

[21]  Tom Drummond,et al.  Faster and Better: A Machine Learning Approach to Corner Detection , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Te-Hsiu Sun,et al.  Automated thermal fuse inspection using machine vision and artificial neural networks , 2016, J. Intell. Manuf..

[23]  Dippal Israni,et al.  An efficient technique for subpixel accuracy using integrated feature based image registration , 2017, 2017 2nd International Conference for Convergence in Technology (I2CT).

[24]  Adrian Hilton,et al.  Order Statistics of RANSAC and Their Practical Application , 2015, International Journal of Computer Vision.

[25]  David G. Lowe,et al.  Shape indexing using approximate nearest-neighbour search in high-dimensional spaces , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[26]  Cordelia Schmid,et al.  A Performance Evaluation of Local Descriptors , 2005, IEEE Trans. Pattern Anal. Mach. Intell..

[27]  Jun-mo Jeong,et al.  An implementation of the real-time panoramic image stitching using ORB and PROSAC , 2015, 2015 International SoC Design Conference (ISOCC).

[28]  Bok-Suk Shin,et al.  Accurate and Robust Line Segment Extraction Using Minimum Entropy With Hough Transform , 2015, IEEE Transactions on Image Processing.

[29]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[30]  Yan Ke,et al.  PCA-SIFT: a more distinctive representation for local image descriptors , 2004, CVPR 2004.

[31]  Hala M. Ebeid,et al.  Fusing directional wavelet local binary pattern and moments for human action recognition , 2016, IET Comput. Vis..

[32]  Gary R. Bradski,et al.  ORB: An efficient alternative to SIFT or SURF , 2011, 2011 International Conference on Computer Vision.

[33]  Roland Siegwart,et al.  BRISK: Binary Robust invariant scalable keypoints , 2011, 2011 International Conference on Computer Vision.

[34]  Lihi Zelnik-Manor,et al.  Template Matching with Deformable Diversity Similarity , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  Yukihiko Yamashita,et al.  Affine-transformation and 2D-projection invariant k-NN classification of handwritten characters via a new matching measure , 2016, Pattern Recognit..

[36]  Zhao Yang,et al.  Detection method of PCB component based on automatic optical stitching algorithm , 2015 .

[37]  D. Wilner,et al.  PROSAC: a submillimeter array survey of low-mass protostars - II. The mass evolution of envelopes, disks, and stars from the class 0 through I stages , 2009, 0909.3386.

[38]  Pawel Strumillo,et al.  Unbiased evaluation of keypoint detectors with respect to rotation invariance , 2017, IET Comput. Vis..