Image Object Localization Based on Multiple Image Segmentation Scoring
SHEN Xiang-Jun1, MU Lei1, ZHA Zheng-Jun2, GOU Jian-Ping1, ZHAN Yong-Zhao1
1.School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang 212013 2.Nuclear Environment Based Teleoperation Robot Laboratory, Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei 230031
Abstract:Image objects localization detects object regions accurately and therefore it can improve accuracies of image objects recognition and classification. In this paper, an image object localization method based on multiple segmentation regions scoring is proposed. Through the image of the multi-level segmentation, the semantic constraints among different image regions through multi-level segmentation results is confirmed. By these constraints, frequent itemset mining and scoring strategy are applied on different levels of object region pattern. According to pattern scores of regions, important regions in each segmentation levels are merged successively to localize the whole image object region. Experimental results on MSRC and GRAZ datasets show that the proposed method can localize image foreground object accurately, and its validity is verified on Caltech256 dataset.
[1] Cao J. Representation and Recognition of the Image Target. Beijing, China: China Machine Press, 2012 (in Chinese) (曹 健.图像目标的表示与识别.北京:机械工业出版社, 2012) [2] Sutherland N S. Object Recognition // Edward C, Carterette M P F, eds. China Handbook of Perception: Biology of Perceptual Systems. New York, USA: Elsevier, 2012, 3: 157-185 [3] Deng J, Berg A C, Li K, et al. What Does Classifying More than 10000 Image Categories Tell Us? // Proc of the 11th European Conference on Computer Vision. Heraklion, Greece, 2010: 71-84 [4] Fang S W, Qu Y Y, Chen C, et al. Object Localization Based on Discriminative Visual Words // Proc of the International Conference on Machine Learning and Cybernetics. Xi'an, China, 2012, III: 1111-1117 [5] Guillaumin M, Ferrari V. Large-Scale Knowledge Transfer for Object Localization in ImageNet // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Providence, USA, 2012: 3202-3209 [6] Lampert C H, Blaschko M B, Hofmann T. Efficient Subwindow Search: A Branch and Bound Framework for Object Localization. IEEE Trans on Pattern Analysis and Machine Intelligence, 2009, 31(12): 2129-2142 [7] Wojek C, Dorkó G, Schulz A, et al. Sliding-Windows for Rapid Object Class Localization: A Parallel Technique // Proc of the 30th DAGM Symposium on Pattern Recognition. Munich, Germany, 2008: 71-81 [8] Gould S, Rodgers J, Cohen D, et al. Multi-class Segmentation with Relative Location Prior. International Journal of Computer Vision, 2008, 80(3): 300-316 [9] Singaraju D, Vidal R. Using Global Bag of Features Models in Random Fields for Joint Categorization and Segmentation of Objects // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Providence, USA, 2011: 2313-2319 [10] Russell B C, Freeman W T, Efros A A, et al. Using Multiple Segmentations to Discover Objects and Their Extent in Image Collections // Proc of the IEEE Computer Society Conference on Compu-ter Vision and Pattern Recognition. New York, USA, 2006, II: 1605-1614 [11] Malisiewicz T, Efros A A. Recognition by Association via Learning Per-exemplar Distances // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, USA, 2008. DOI: 10.1109/CVPR.2008.4587462 [12] Shi J B, Malik J. Normalized Cuts and Image Segmentation. IEEE Trans on Pattern Analysis and Machine Intelligence, 2000, 22(8): 888-905 [13] Han J W, Cheng H, Xin D, et al. Frequent Pattern Mining: Cu-rrent Status and Future Directions. Data Mining and Knowledge Discovery, 2007, 15(1): 55-86 [14] Yan Y J, Li Z J, Chen H W, Frequent Item Sets Mining Algorithms. Computer Science, 2004, 31(3): 112-114, 124 (in Chinese) (颜跃进,李舟军,陈火旺.频繁项集挖掘算法.计算机科学, 2004, 31(3): 112-114, 124) [15] Sivic J, Russell B C, Efros A A, et al. Discovering Objects and Their Location in Images // Proc of the 10th IEEE International Conference on Computer Vision. Beijing, China, 2005, I: 370-377 [16] Lowe D G. Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision, 2004, 60(2): 91-110 [17] Borgelt C. Efficient Implementations of Apriori and Eclat // Proc of the 1st IEEE ICDM Workshop on Frequent Item Set Mining Implementations. Melbourne, USA, 2003: 90 [18] Cheng H, Yan X F, Han J W, et al. Discriminative Frequent Pa-ttern Analysis for Effective Classification // Proc of the 23rd IEEE International Conference on Data Engineering. Istanbul, Turkey, 2007: 716-725 [19] Kullback S, Leibler R A. On Information and Sufficiency. The Annals of Mathematical Statistics, 1951, 22(1): 79-86 [20] Boughorbel S, Tarel J P, Boujemaa N. Generalized Histogram Intersection Kernel for Image Recognition // Proc of the IEEE International Conference on Image Processing. Genova, Italy, 2005, III: 161-164 [21] Fulkerson B, Vedaldi A, Soatto S. Class Segmentation and Object Localization with Superpixel Neighborhoods // Proc of the 12th IEEE International Conference on Computer Vision. Kyoto, Japan, 2009: 670-677 [22] Dellaert F, Frahm J M, Pollefeys M, et al. Outdoor and Large-Scale Real-World Scene Analysis. Berlin, Germany: Springer, 2012 [23] Liang J Z, Corso N, Turner E, et al. Image Based Localization in Indoor Environments // Proc of the 4th International Conference on Computing for Geospatial Research and Application. San Jose, USA, 2013: 70-75 [24] Kim S, Jin X, Han J W. DisIclass: Discriminative Frequent Pa-ttern-Based Image Classification[EB/OL]. [2014-02-24]. http://web.engr.illinois.edu/~hanj/pdf/mdm10_skim.pdf [25] Zhang H, Berg A C, Maire M, et al. SVM-KNN: Discriminative Nearest Neighbor Classification for Visual Category Recognition // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, USA, 2006, II: 2126-2136