Medical image mosaic based on low-overlapping regions

This paper focuses on the mosaicing of microscopic medical images. Different from regular application scene where the source images usually have an overlapping ratio between 30%∼50%, source images in this paper have a rather low overlapping ratio less than 15%. Performances of several generic feature-based registration methods are compared in order to explore which one is most appropriate for our application. This paper presents a novel mosaic algorithm as follows. Firstly, Speeded-up Robust Feature (SURF) points in the regions surrounding the overlapped are extracted and then roughly matching results of feature points are acquired. Secondly, mismatched pairs are eliminated according to spatial distance of matching points, and then geometrical relationship between reference image and target image is determined. Finally, registered images are blended into a composite image with modified weighted smooth algorithm. Experimental results demonstrate that the proposed method is effective to create a visually pleasant panoramic image.

[2]  Umesh C. Pati,et al.  A novel technique for mosaicing of medical images , 2014, 2014 Annual IEEE India Conference (INDICON).

[3]  Weon-Geun Oh,et al.  An analysis of the effect of different image preprocessing techniques on the performance of SURF: Speeded Up Robust Features , 2011, 2011 17th Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV).

[4]  S. Kumar,et al.  Image fusion of natural, satellite, and medical images using Undecimated Discrete Wavelet Transform and contrast visibility , 2015, 2015 National Conference on Recent Advances in Electronics & Computer Engineering (RAECE).

[5]  Tai-Tien Wang,et al.  Application and validation of simple image-mosaic technology for interpreting cracks on tunnel lining , 2013 .

[6]  Xu Jing,et al.  A new medical image mosaic algorithm base on regional features registration , 2012, 2012 IEEE International Conference on Computer Science and Automation Engineering (CSAE).

[7]  Weizheng Shen,et al.  UAV Remote Sensing Image Mosaic and Its Application in Agriculture , 2016 .

[8]  Brian Johnson.  Remote Sensing Image Fusion at the Segment Level Using a Spatially-Weighted Approach: Applications for Land Cover Spectral Analysis and Mapping , 2015, ISPRS Int. J. Geo Inf..

[9]  Daxiang Cui,et al.  Accurate Non-rigid Registration of Lung Images Based on Mutual Information , 2015 .

[10]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[11]  Nursuriati Jamil,et al.  Plant species identification by using Scale Invariant Feature Transform (SIFT) and Grid Based Colour Moment (GBCM) , 2013, 2013 IEEE Conference on Open Systems (ICOS).

[12]  Junzo Watada,et al.  Panoramic image mosaic based on SURF algorithm using OpenCV , 2015, 2015 IEEE 9th International Symposium on Intelligent Signal Processing (WISP) Proceedings.

[13]  Rohit M. Thanki,et al.  Multibiometric template generation using CS theory and discrete wavelet transform based fusion technique , 2015, 2015 5th Nirma University International Conference on Engineering (NUiCONE).

[14]  Shengping Zhang,et al.  Dynamic image mosaic via SIFT and dynamic programming , 2013, Machine Vision and Applications.

[15]  Purushottam G. Chilveri,et al.  Stereo image feature matching using Harris corner detection algorithm , 2016, 2016 International Conference on Automatic Control and Dynamic Optimization Techniques (ICACDOT).

[16]  Volkan Isler,et al.  Large Scale Image Mosaic Construction for Agricultural Applications , 2016, IEEE Robotics and Automation Letters.

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

[18]  Fang Tian,et al.  Image Mosaic using ORB descriptor and improved blending algorithm , 2014, International Congress on Image and Signal Processing.

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

[20]  Jignesh N. Sarvaiya,et al.  Implementation and analysis of template matching for image registration on DevKit-8500D , 2017 .