基于图表示和匹配的表单定位与提取
|
摘要
为了实现对不同类型、分辨率和方向的快递表单上用户感兴趣区域信息的获取,本文提出了一种基于图表示和匹配的表单定位与提取方法。选择参考表单中已有的印刷图案或字符等关键区域作为基准位置,进行图的表示。基于图像分割得到的候选关键区域对待处理表单进行图表示。然后,根据图的属性计算待处理表单与参考表单的相似度。最后,将最大相似度对应的同构图作为参考表单图的最优匹配,并建立同构图与参考表单图位置映射,定位出表单。本文实验数据集来源于真实场景下采集的快递包裹表单图像。实验结果表明:本文算法在快递包裹表单图像上具有良好的性能,对旋转、光照变化、局部遮挡具有较好的鲁棒性。
To obtain information of a user's interested region on express package images of different types, resolutions,and directions, a form location and extraction method based on graph representation and matching is proposed in this paper. A reference form is needed in this method. First, key regions such as the existing printed patterns or characters in the reference form are chosen as nodes to build the reference graph. Second, graph representation is conducted on the form to be processed based on the candidate key region derived from image segmentation. Then, the similarity between the reference form and the candidate form is calculated according to attributes of the graph. Finally, the isomorphic graph with the maximum similarity is chosen as the optimal matching of the reference form and graph, and the position mapping of the isomorphic graph and the reference form and test image is established to locate the form. The experimental datasets in this paper originate from express package images collected in practical scenarios. Experimental results indicate that the proposed algorithm has good performance on express form images. Especially, good robustness is achieved for rotated, illuminated, and partially shaded images.
To obtain information of a user's interested region on express package images of different types, resolutions,and directions, a form location and extraction method based on graph representation and matching is proposed in this paper. A reference form is needed in this method. First, key regions such as the existing printed patterns or characters in the reference form are chosen as nodes to build the reference graph. Second, graph representation is conducted on the form to be processed based on the candidate key region derived from image segmentation. Then, the similarity between the reference form and the candidate form is calculated according to attributes of the graph. Finally, the isomorphic graph with the maximum similarity is chosen as the optimal matching of the reference form and graph, and the position mapping of the isomorphic graph and the reference form and test image is established to locate the form. The experimental datasets in this paper originate from express package images collected in practical scenarios. Experimental results indicate that the proposed algorithm has good performance on express form images. Especially, good robustness is achieved for rotated, illuminated, and partially shaded images.
引文
[1]SHARMA D V, LEHAL G S. Form field frame boundary removal for form processing system in Gurmukhi script[C]//Proceedings of the 10th International Conference on Document Analysis and Recognition. Barcelona,Spain, 2009:256–260.
[2]CHEN J L, LEE H J. An efficient algorithm for form structure extraction using strip projection[J]. Pattern recognition, 1998, 31(9):1353–1368.
[3]LIU Wenyin, DORI D. From raster to vectors:extracting visual information from line drawings[J]. Pattern analysis and applications, 1999, 2(1):10–21.
[4]WATANABE T, LUO Qin, SUGIE N, et al. Layout recognition of multi-kinds of table-form documents[J]. IEEE transactions on pattern analysis and machine intelligence,1995, 17(4):432–445.
[5]LAM S W, SRIHARI S N. Multi-domain document layout understanding[C]//Proceedings of International Conference on Document Analysis and Recognition. 1991:112–120.
[6]SACHDEVA R, SHARMA D V. Data extraction from hand-filled form using form template[J]. International journal on recent and innovation trends in computing and communication, 2015, 3(8):5311–5317.
[7]NING L W, SIAH Y K, KHALID M, et al. Design of an automated data entry system for hand-filled forms[C]//Proceedings of 2000 TENCON. Kuala Lumpur, Malaysia,2000:162–166.
[8]BENSEFIA A. Extraction of Arabic handwriting fields by forms matching[J]. Journal of signal and information processing, 2015, 6(1):53424.
[9]CESARINI F, GORI M, MARINAI S, et al. INFORMys:a flexible invoice-like form-reader system[J]. IEEE transactions on pattern analysis and machine intelligence, 1998,20(7):730–745.
[10]CHO M, SUN Jian, DUCHENNE O, et al. Finding matches in a haystack:a max-pooling strategy for graph matching in the presence of outliers[C]//Proceedings of2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH, USA, 2014:2091–2098.
[11]SUH Yumin, ADAMCZEWSKI K, LEE K M. Subgraph matching using compactness prior for robust feature correspondence[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston,MA, USA, 2015:5070–5078.
[12]SHARMA A, HORAUD R, CECH J, et al. Topologicallyrobust 3D shape matching based on diffusion geometry and seed growing[C]//Proceedings of 2011 IEEE Conference on Computer Vision and Pattern Recognition.Providence, RI, USA, 2011:2481–2488.
[13]DUCHENNE O, JOULIN A, PONCE J. A graph-matching kernel for object categorization[C]//Proceedings of2011 IEEE International Conference on Computer Vision.Barcelona, Spain, 2011:1792–1799.
[14]ZHANG Quanshi, SONG Xuan, SHAO Xiaowei, et al.Attributed graph mining and matching:an attempt to define and extract soft attributed patterns[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH, USA, 2014:1394–1401.
[15]ZHANG Quanshi, SONG Xuan, SHAO Xiaowei, et al.Object discovery:soft attributed graph mining[J]. IEEE transactions on pattern analysis and machine intelligence,2016, 38(3):532–545.
[16]LEORDEANU M, SUKTHANKAR R, Hebert M, et al.Unsupervised learning for graph matching[J]. International journal of computer vision, 2012, 96(1):28–45.
[17]UIJLINGS J R R, VAN DE SANDE K E A, GEVERS T,et al. Selective search for object recognition[J]. International journal of computer vision, 2013, 104(2):154–171.
[2]CHEN J L, LEE H J. An efficient algorithm for form structure extraction using strip projection[J]. Pattern recognition, 1998, 31(9):1353–1368.
[3]LIU Wenyin, DORI D. From raster to vectors:extracting visual information from line drawings[J]. Pattern analysis and applications, 1999, 2(1):10–21.
[4]WATANABE T, LUO Qin, SUGIE N, et al. Layout recognition of multi-kinds of table-form documents[J]. IEEE transactions on pattern analysis and machine intelligence,1995, 17(4):432–445.
[5]LAM S W, SRIHARI S N. Multi-domain document layout understanding[C]//Proceedings of International Conference on Document Analysis and Recognition. 1991:112–120.
[6]SACHDEVA R, SHARMA D V. Data extraction from hand-filled form using form template[J]. International journal on recent and innovation trends in computing and communication, 2015, 3(8):5311–5317.
[7]NING L W, SIAH Y K, KHALID M, et al. Design of an automated data entry system for hand-filled forms[C]//Proceedings of 2000 TENCON. Kuala Lumpur, Malaysia,2000:162–166.
[8]BENSEFIA A. Extraction of Arabic handwriting fields by forms matching[J]. Journal of signal and information processing, 2015, 6(1):53424.
[9]CESARINI F, GORI M, MARINAI S, et al. INFORMys:a flexible invoice-like form-reader system[J]. IEEE transactions on pattern analysis and machine intelligence, 1998,20(7):730–745.
[10]CHO M, SUN Jian, DUCHENNE O, et al. Finding matches in a haystack:a max-pooling strategy for graph matching in the presence of outliers[C]//Proceedings of2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH, USA, 2014:2091–2098.
[11]SUH Yumin, ADAMCZEWSKI K, LEE K M. Subgraph matching using compactness prior for robust feature correspondence[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston,MA, USA, 2015:5070–5078.
[12]SHARMA A, HORAUD R, CECH J, et al. Topologicallyrobust 3D shape matching based on diffusion geometry and seed growing[C]//Proceedings of 2011 IEEE Conference on Computer Vision and Pattern Recognition.Providence, RI, USA, 2011:2481–2488.
[13]DUCHENNE O, JOULIN A, PONCE J. A graph-matching kernel for object categorization[C]//Proceedings of2011 IEEE International Conference on Computer Vision.Barcelona, Spain, 2011:1792–1799.
[14]ZHANG Quanshi, SONG Xuan, SHAO Xiaowei, et al.Attributed graph mining and matching:an attempt to define and extract soft attributed patterns[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH, USA, 2014:1394–1401.
[15]ZHANG Quanshi, SONG Xuan, SHAO Xiaowei, et al.Object discovery:soft attributed graph mining[J]. IEEE transactions on pattern analysis and machine intelligence,2016, 38(3):532–545.
[16]LEORDEANU M, SUKTHANKAR R, Hebert M, et al.Unsupervised learning for graph matching[J]. International journal of computer vision, 2012, 96(1):28–45.
[17]UIJLINGS J R R, VAN DE SANDE K E A, GEVERS T,et al. Selective search for object recognition[J]. International journal of computer vision, 2013, 104(2):154–171.