Automatic Segmentation of Product Bottle Label Based on GrabCut Algorithm
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In this paper, we propose a method to build an accurate initial trimap for the GrabCut algorithm without the need for human interaction. First, we identify a rough candidate for the label region of a bottle by applying a saliency map to find a salient area fromthe image. Then, the Hough Transformation method is used to detect the left and right borders of the label region, and the k-means algorithm is used to localize the upper and lower borders of the label of the bottle. These four borders are used to build an initial trimap for the GrabCut method. Finally, GrabCut segments accurate regions for the label. The experimental results for 130 wine bottle images demonstrated that the saliency map extracted a rough label region with an accuracy of 97.69% while also removing the complex background. The Hough transform and projection method accurately drew the outline of the label from the saliency area, and then the outline was used to build an initial trimap for GrabCut. Finally, the GrabCut algorithm successfully segmented the bottle label with an average accuracy of 92.31%. Therefore, we believe that our method is suitable for product label recognition systems that automatically segment product labels. Although our method achieved encouraging results, it has some limitations in that unreliable results are produced under conditions with varying illumination and reflections. Therefore, we are in the process of developing preprocessing algorithms to improve the proposed method to take into account variations in illumination and reflections.
Abstract
In this paper, we propose a method to build an accurate initial trimap for the GrabCut algorithm without the need for human interaction. First, we identify a rough candidate for the label region of a bottle by applying a saliency map to find a salient area fromthe image. Then, the Hough Transformation method is used to detect the left and right borders of the label region, and the k-means algorithm is used to localize the upper and lower borders of the label of the bottle. These four borders are used to build an initial trimap for the GrabCut method. Finally, GrabCut segments accurate regions for the label. The experimental results for 130 wine bottle images demonstrated that the saliency map extracted a rough label region with an accuracy of 97.69% while also removing the complex background. The Hough transform and projection method accurately drew the outline of the label from the saliency area, and then the outline was used to build an initial trimap for GrabCut. Finally, the GrabCut algorithm successfully segmented the bottle label with an average accuracy of 92.31%. Therefore, we believe that our method is suitable for product label recognition systems that automatically segment product labels. Although our method achieved encouraging results, it has some limitations in that unreliable results are produced under conditions with varying illumination and reflections. Therefore, we are in the process of developing preprocessing algorithms to improve the proposed method to take into account variations in illumination and reflections.
참고문헌 (28)
- S. W. Hong, "Automatic Flowers Recognition Using Segmentation", Korea Computer Congress, 38(1), pp.463~465 (2011)
- J. S. Lee, "Recognition of Text in Wine Label Images", IEEE Pattern Recognition on Chinese Conferen, pp.1~5 (2009)
- N. Otsu, "A Threshold Selection Method from Gray-Level Histograms", IEEE Transactions on Systems, Man, and Cybernetics, 9(1), pp.62~66 (1979)
- J. B. MacQueen, "Some Methods for Classification and Analysis of Multiplicate Observations", Proceedings of 5th Berkeley Symposium on Mathematical Statistics and Probability, pp.281~297 (1967), Berkeley, University of California Press
- D. Comaniciu, "Mean Shift : A Robust Approach Toward Feature Space Analysis", IEEE Transactions on PAMI, 24(5), pp.1~17 (2002)
- Jong Hyun Park, "Color image segmentation using adaptive mean shift and statistical model-based method", Computers and mathematics with Applications, 57(6), pp.970~980 (2009)
- T. F. Chan, "Active Contours Without Edge", IEEE Transactions on Image Processing, 10(2), pp.266~277 (2001)
- A. Tasi, "Curve Evolution Implementation of the Mumford-Shah Functional for Image Segmentation, Depositing, Interpolation and Margination", Institute of Electrical and Electronics Engineers Transactions on Image Processing, 10(8), pp.1169~1186 (2001)
- D. Cremers, "A multiphase level set framework for variational motion segmentation", In Scale Space Methods in Computer Vision, 2695, pp.599~614 (2003)
- C. Li, "Level set evolution without reinitialization : A new variational formulation", Institute of Electrical and Electronics Engineers Conference on Computer Vision and Pattern Recognition, 1, pp.430~436 (2005)
- C. Li, "Implicit Active Contours Driven by Local Binary Fitting Energy", IEEE Conference on Computer Vision and Pattern Recognition, pp.1~7 (2007)
- V. Caselles, "A geometric model for active contours in image processing", Nummerische Mathematik, (66), pp.1~31 (1993)
- M. Rousson, "A Variational Framework for Active and Adapt active Segmentation of Vector Valued Images", Proceeding of IEEE Workshop on Motion and Video Computing (2002)
- J. B. Shi, "Normalized Cuts and Image Segmentation", IEEE Transactions on pattern analysis and machine intelligence, 22(8), pp.888~905 (2000)
- Y. Boykov, "An Experimental Comparison of Min-Cut", Flow Algorithms for Energy Minimization in Vision, 2004, pp.26(9), 1124~1137
- Y. Boycov, "Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images", In Proc. IEEE Int. Conf. on Computer Vision, In ICCV, pp.105~112 (2001)
- C. Rother, "GrabCut:interactive for foreground using iterate graph cuts", SCM Transaction on Graphics(TOG) (2004)
- Justin F. Talbot, "Implementing GrabCut", Brigham Yong University Revised, Apr. 7, 2006, ~ (2006)
- "GrabCut-Interactive Foreground Extraction"[URL]
- B. C. Ko, "Object-of-interest image segmentation based on human attention and semantic region", Optical Society of Society of America, 23, pp.2462~2470 (2006)
- L. Itti, "A Model of Saliency-Based Visual Attention for Rapid Scene Analysis", Institute of Electrical and Electronics Engineers Transactions on Pattern Analysis and Machine Intelligence, 20, pp.1254~1259 (1998)
- L. Itti, "Automatic Foveation for Video Compression Using a Neurobiological Model of Visual Attention", Institute of Electrical and Electronics Engineers Transactions on Image Processing, 13(10), pp.1304~1318 (2004)
- L. Elazary, "Interesting objects are visually salient", Journal of Vision, 8(33), pp.1~15 (2008)
- L. Itti, "Computational modeling of visual attention", Nature Reviews Neuroscience, 2(3), pp.194~203 (2001)
- J. Harel, "Graph-based visual saliency, in Advances in Neural Information Processing System 19", pp.545~552 (2007), MIT Press
- D. Ballard, "Generalizing the Hough Transform to Detection Arbitrary Shape", Pattern Recognition, 13(2), pp.111~122 (1981)
- R. Duda, "Use of the Hough Transformation to Detect Line and Curves in picturers", Communication of the ACM, 15(1), pp.11~15 (1972)
- R. C. Gonzalez, "Digital Image Processing using MATLAB" (2002), Publishing House of Electronics Industry