Invariant Color Features Detector and Descriptor using Fast Explicit Diffusion in Nonlinear Scale Spaces
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In recent years, there have been significant research on robust feature extraction methods. Most state-of-the-art methods operate on grayscale images to decrease the computational expenses. We observe that this conversion can cause information loss and effect the matching performance. In this study, a multi-scale 2D invariant color detector and descriptor in nonlinear scale spaces is proposed. The algorithm exploits color information in HLS (Hue, Lightness, and Saturation) space. Nonlinear scale spaces are built separately for each color channel and adaptive Hessian responses are calculated for keypoint extraction. Fast Explicit Diffusion (FED) scheme is used for locally adaptive blurring to the image data. FED reduces image noise while preserving important edges. This aids in superior keypoint localization accuracy and feature distinctiveness. In addition, a Color Modified-Local Difference Binary (CM-LMB) descriptor is proposed. It combines HLS color information with gradient information in nonlinear scale space. Our proposed system (HLS-AKAZE) shows comparable performance in standard image datasets and good performance improvements in certain images (Less-Informative Grayscale Images). HLS-AKAZE is rotation, scale, and illumination invariant.
Abstract
In recent years, there have been significant research on robust feature extraction methods. Most state-of-the-art methods operate on grayscale images to decrease the computational expenses. We observe that this conversion can cause information loss and effect the matching performance. In this study, a multi-scale 2D invariant color detector and descriptor in nonlinear scale spaces is proposed. The algorithm exploits color information in HLS (Hue, Lightness, and Saturation) space. Nonlinear scale spaces are built separately for each color channel and adaptive Hessian responses are calculated for keypoint extraction. Fast Explicit Diffusion (FED) scheme is used for locally adaptive blurring to the image data. FED reduces image noise while preserving important edges. This aids in superior keypoint localization accuracy and feature distinctiveness. In addition, a Color Modified-Local Difference Binary (CM-LMB) descriptor is proposed. It combines HLS color information with gradient information in nonlinear scale space. Our proposed system (HLS-AKAZE) shows comparable performance in standard image datasets and good performance improvements in certain images (Less-Informative Grayscale Images). HLS-AKAZE is rotation, scale, and illumination invariant.
참고문헌 (21)
- 김지인, "스티칭 알고리즘을 이용한 차량 주변 영상 정합 방법", 한국차세대컴퓨팅학회 논문지, 11(6), pp.61~67 (2015), 한국차세대컴퓨팅학회
- 김경율, "영상 대비와 특징추출 알고리즘 성능평가의 관계 분석", 한국차세대컴퓨팅학회 논문지, 8(5), pp.6~20 (2012), 한국차세대컴퓨팅학회
- 최재인, "특징점 기반 카메라 트래킹을 이용한 손 움직임 보정 기법", 한국차세대컴퓨팅학회 논문지, 11(2), pp.6~13 (2015), 한국차세대컴퓨팅학회
- A. J. Davison, "MonoSLAM : Real-Time Single Camera SLAM", IEEE Trans Pattern Anal Mach Intell, 29(6), pp.1052~1067 (2007)
- C. Kanan, "Color-to-grayscale : does the method matter in image recognition?", PLoS One, 7(1), pp.e29740~ (2012)
- D. G. Lowe, "Distinctive image features from scale-invariant keypoints", Int J Comput Vis, 60(2), pp.91~110 (2004)
- H. Bay, "Speeded-up robust features(SURF)", Comput Vis Image Underst, 110(3), pp.346~359 (2008)
- S. Leutenegger, "BRISK : Binary robust invariant scalable keypoints", Proceedings of International Conference on Computer Vision, pp.2548~2555 (2011)
- E. Rublee, "ORB : An efficient alternative to SIFT or SURF", Proceedings of International Conference on Computer Vision, pp.2564~2571 (2011)
- P. F. Alcantarilla, "KAZE features", European Conference on Computer Vision, pp.214~227 (2012)
- P. F. Alcantarilla, "Fast explicit diffusion for accelerated features in nonlinear scale spaces", IEEE Trans Pattern Anal Mach Intell, 34(7), pp.1281~1298 (2011)
- X. Yang, "LDB: An ultra-fast feature for scalable augmented reality on mobile devices", 2012 IEEE International Symposium on Mixed and Augmented Reality, pp.49~57 (2012)
- D. A. R. Vigo, "The impact of color on bag-of-words based object recognition", Proceedings of 20th International Conference on Pattern Recognition, pp.1549~1553 (2010)
- K. Sande, "Evaluating color descriptors for object and scene recognition", IEEE Trans Pattern Anal Mach Intell, 32(9), pp.1582~1596 (2010)
- E. KOEN, "Evaluation of color descriptors for object and scene recognition", Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (2008)
- K. Mikolajczyk, "A comparison of affine region detectors", Int J Comput Vis, 65(1), pp.43~72 (2005)
- K. Mikolajczyk, "performance evaluation of local descriptors", IEEE Trans Pattern Anal Mach Intell, 27(10), pp.1615~1630 (2005)
- S. Salti, "Keypoints from symmetries by wave propagation", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.2898~2905 (2013)
- Z. Miao, "Interest point detection using rank order LoG filter", Pattern Recognition, 46(11), pp.2890~2901 (2013)
- J. Matas, "Robust wide-baseline stereo from maximally stable extremal regions", Image and vision computing, 22(10), pp.761~767 (2004)
- E. Salahat, "Extended mser detection", The IEEE International Symposium on Industrial Electronics, pp.3~5 (2015)