Research on adaptive fusion algorithm for image stitching

An adaptive multi-direction image fusion algorithm is proposed to solve the problem that one fusion algorithm is not suitable for many kinds of image stitching, and there will be significant seam-line at the boundary of the overlap region after image fusion. According to the positional relation of the two images in the coordinate system after projection deformation, we divide the image stitching into two types. We design different image fusion algorithm against the characteristics of each type of stitching, and seam-line be in all boundary direction is eliminated. The algorithm can estimate the type of image stitching rapidly and accurately and perform the corresponding multi-direction image fusion and eventually eliminate the seam-line. Adding brightness adjustment before stitching will make the final result achieve consistency in brightness if the two images for stitching have a considerable difference in brightness.

[1]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[2]  Sally J. Gocker.  The Essential Physics of Medical Imaging. by Jerrold T. Bushberg, J. Anthony Seibert, Edwin M. Leidholdt, Jr., and John M. Bonne , 1995 .

[3]  Shutao Li,et al.  Image Fusion With Guided Filtering , 2013, IEEE Transactions on Image Processing.

[4]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[5]  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).

[6]  Richard Szeliski,et al.  Image Alignment and Stitching , 2006, Handbook of Mathematical Models in Computer Vision.

[7]  Ananda S. Chowdhury,et al.  Steerable local frequency based multispectral multifocus image fusion , 2015, Inf. Fusion.

[8]  T. Grantcharov,et al.  Randomized clinical trial of virtual reality simulation for laparoscopic skills training , 2004, The British journal of surgery.

[9]  Jirí Mekyska,et al.  Multi-focus thermal image fusion , 2013, Pattern Recognit. Lett..

[10]  J. Bushberg.  The Essential Physics of Medical Imaging , 2001 .

[11]  Wang Xiang-jun.  Applications of multispectral/hyperspectral imaging technologies in military , 2007 .

[12]  Michael S. Brown,et al.  As-Projective-As-Possible Image Stitching with Moving DLT , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Somaya Adwan,et al.  A new approach for image stitching technique using Dynamic Time Warping (DTW) algorithm towards scoliosis X-ray diagnosis , 2016 .

[14]  Yoichi Sato,et al.  Shape-Preserving Half-Projective Warps for Image Stitching , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Dong Sik Kim,et al.  Joint Optimization of Image Registration and Comparametric Exposure Compensation Based on the Lucas-Kanade Algorithm , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[16]  Shutao Li,et al.  Performance comparison of different multi-resolution transforms for image fusion , 2011, Inf. Fusion.

[17]  J. Strzelczyk.  The Essential Physics of Medical Imaging , 2003 .