Image Dense Matching Method Based on Wavelet Edge Detection and Region Growing

Abstract:

Aiming at the computer vision image, firstly, image edge feature is obtained using the edge detection algorithm based on wavelet analysis, selecting some seed points, comparing the gray similarity of seeds, the result of the initial match is based on the SIFT matching algorithm. The weighted SSD (Sum of Squared Difference) series, as the objective function, spread the seeds to the rest of the image matching area with the original growing strategy. Experimental results show that the algorithm was effective to large parallax pictures, images without calibration, and images which textures are sparse.

• Periodical: Applied Mechanics and Materials (Volumes 44-47)
• Pages: 3230-3234
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.44-47.3230
• Online since: December 2010
• Authors: Li Guo Zhang, Hong Jie Kou, Yu Chun Zhao
• Keywords: Edge Detection, Region Growing, SIFT (Scale Invariant Feature Transform) Matching, Wavelet Transform (WT)

References

[1] Yongjun Wu and Qinye Yin: Journal of Xi'An jiaotong University Vol. 35(2001), pp.1227-1232, in Chinese.

[2] Zitnick C.L. and Kanade T: CMU Technical Report: CMU-RI-98-30, Vol. 1(1998)pp.98-103.

[3] Lhuillier and M. Quan L: In Proceeding of the 7th Europe Conference on Computer Vision, Copenhagen. Vol. 1(2002), pp.125-139.

[4] Li Tang and Chengke Wu: Chinese journal of computers Vol. 7(2004), pp.937-942, in Chinese.

[5] Hanchen Song and Yingmei Wei: Computer Engineering Vol. 21(2005), pp.148-150, in Chinese.

[6] Guomei Wang and Xiaowei Chen: Journal of Yancheng Iinstitute of Technology Naturl Science Edition Vol. 2(2007), p . 1-5, in Chinese.

[7] Chuanbin Deng and Lei Guo: Chinese Journal of Sensors and Actuators Vol. 12(2009), pp.1742-1746, in Chinese.

[8] Rongfeng Deng and Xiying Li: Journal of Computer Applications Vol. 6(2009), pp.219-221, in Chinese.

[9] Fengxian Huang and Baobao Wang: Computer Simulation Vol. 21(2004), pp.155-157, in Chinese.