摘要
针对图像匹配问题进行了研究,提出了一种改进BRIEF算法的特征点匹配算法。该算法利用随机点与特征点之间的差分大小和差分幅值关系来生成特征点描述算子。针对BRIEF对噪声敏感问题,因为小的像素幅值差分更易受到噪声影响,为了抑制噪声,通过设置小像素差分阈值,差分在阈值内的设置为不确定位,然后通过其邻域均值来决定不确定位的值。特征点匹配使用描述算子之间的汉明距离进行比较来完成。实验将BRIEF和ORB算法进行了比较,证明该算子具有更高的判别性,计算简单且具有很好的噪声抑制性能,运行速度快,匹配准确率更高。
This paper researched image matching issue and proposed a feature point matching algorithm to improve the BRIEF algorithm. The proposed algorithm generated the feature point description operator according to the difference signs and the difference magnitudes relation between the random point and the feature point. BRIEF was sensitive to noise because the small difference magnitude was more susceptible to the noise. To solve this problem,this paper determined a small pixel difference threshold by the neighborhood mean value of the BRIEF. Comparing the Hamming distance between descriptions realized the feature points matching. Compared with BRIEF and ORB algorithm,the experiments prove that the operator has higher discriminant,simple calculation and good noise suppression performance. And the matching accuracy is higher.
引文
[1] Satpathy A,Jiang Xudong,Eng H L. LBP-based edge-texture features for object recognition[J]. IEEE Trans on Image Processing,2014,23(5):1953-1964.
[2] Ren Jianfeng,Jiang Xudong,Yuan Junsong,et al. LBP encoding schemes jointly utilizing the information of current bit and other LBP bits[J].IEEE Signal Processing Letters,2015,22(12):2373-2377.
[3] Chen Dong,Cao Xudong,Wen Fang,et al. Blessing of dimensionality:high-dimensional feature and its efficient compression for face verification[C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition. Piscataway,NJ:IEEE Press,2013:3025-3032.
[4] Deshmukh A,Sirpotdar P,Sheikh J,et al. High accuracy face recognition system based on SIFT[J]. International Journal of Advanced Research in Computer Engineering&Technology,2015,4(6):2626-2628.
[5] Li Wei,Chen Chen,Su Hongjun,et al. Local binary patterns and extreme learning machine for hyperspectral imagery classification[J].IEEE Trans on Geoscience and Remote Sensing,2015,53(7):3681-3693.
[6] Xiao Yang,Wu Jianxin,Yuan Junsong,et al. m CENTRIST:a multichannel feature generation mechanism for scene categorization[J].IEEE Trans on Image Processing,2014,23(2):823-836.
[7] Zhao Guoying,Ahonen T,Matas J,et al. Rotation-invariant image and video description with local binary pattern features[J]. IEEE Trans on Image Processing,2011,21(4):1465-1477.
[8] Guo Zhenhua,Zhang Lei,Zhang D,et al. A completed modeling of local binary pattern operator for texture classification[J]. IEEE Trans on Image Processing,2010,19(6):1657-1663.
[9] Song Tiecheng,Li Hongliang,Meng Fanman,et al. Noise-robust texture description using local contrast patterns via global measures[J].IEEE Signal Processing Letters,2014,21(1):93-96.
[10]Wang Kai,Bichot C E,Zhu Chao,et al. Pixel to patch sampling structure and local neighboring intensity relationship patterns for texture classification[J]. IEEE Signal Processing Letters,2013,20(9):853-856.
[11]Liao S,Law M W K,Chung A C S,et al. Dominant local binary patterns for texture classification[J]. IEEE Trans on Image Processing,2009,18(5):1107-1118.
[12]Kwak J T,Xu Sheng,Wood B J,et al. Efficient data mining for local binary pattern in texture image analysis[J]. Expert Systems with Applications,2015,42(9):4529-4539.
[13]Calonder M,Lepetit V,Ozuysal M,et al. BRIEF:computing a local binary descriptor very fast[J]. IEEE Trans on Pattern Analysis and Machine Intelligence,2012,34(7):1281-1298.
[14]Moravec H P. Rover visual obstacle avoidance[C]//Proc of the 7th International Joint Conference on Artificial Intelligence. 1981:785-790.
[15]Harris C,Stephens M. A combined corner and edge detector[C]//Proc of the 4th Alvey Vision Conference. 1988:147-151.
[16]Lowe D G. Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[17]Mikolajczyk K,Schmid C. A performance evaluation of local descriptors[J]. IEEE Trans on Pattern Analysis and Machine Intelligence,2005,27(10):1615-1630.
[18]Hua Gang,Brown M,Winder S. Discriminant embedding for local image descriptors[C]//Proc of the 11th IEEE International Conference on Computer Vision. Piscataway,NJ:IEEE Press,2007:1-8.
[19] Bay H,Tuytelaars T,Van Gool L. SURF:speeded up robust features[C]//Proc of International Conference on Computer Vision. Berlin:Springer,2006:404-417.
[20]初守艳,席志红.结合SURF的数字稳像技术[J].计算机辅助设计与图形学学报,2014,26(2):241-247.(Chu Shouyan,Xi Zhihong. Digital image stabilization based on SURF[J]. Journal of Computer-Aided Design&Computer Graphics,2014,26(2):241-247.)
[21]陈小丹,杜宇人,高秀斌,等.一种基于SURF的图像特征点快速匹配算法[J].扬州大学学报:自然科学版,2012,15(4):64-67.(Chen Xiaodan,Du Yuren,Gao Xiubin,et al. A fast algorithm of image feature points matching based on SURF[J]. Journal of Yangzhou University:Natural Science Edition,2012,15(4):64-67.)
[22]Leutenegger S,Chli M,Siegwart R Y. BRISK:binary robust invariant scalable keypoints[C]//Proc of International Conference on Computer Vision. Piscataway,NJ:IEEE Press,2011:2548-2555.
[23] Alahi A,Ortiz R,Vandergheynst P. FREAK:fast retina keypoint[C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition. Piscataway,NJ:IEEE Press,2012:510-517.
[24]Rublee E,Rabaud V,Konolige K,et al. ORB:an efficient alternative to SIFT or URF[C]//Proc of International Conference on Computer Vision. 2011:2564-2571.
[25] Ojala T,Pietikainen M,Harwood D. A comparative study of texture measures with classification based on featured distributions[J]. Pattern Recognition,1996,29(1):51-59.
[26]Ojala T,Pietikainen M,Maenpaa T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2002,24(7):971-987.
[27]Weinberger M J,Rissanen J J,Arps R B,et al. Applications of universal context modeling to lossless compression of gray-scale images[J].IEEE Trans on Image Processing,1996,5(4):575-586.
