基于学习主动中心轮廓模型的场景文本检测

doi:10.19678/j.issn.1000-3428.0060828

摘要/Abstract

摘要： 在场景文本检测领域，存在由于文本尺寸波动较大导致的小文本漏检、大文本欠检测和多尺度文本边界检测错误的情况。针对上述问题，提出一种基于学习主动中心轮廓模型的场景文本检测网络。在残差网络ResNet的基础上构建多尺度特征权重融合模型，对输入的场景文本图片进行多尺度特征提取和权重融合，并计算出最终的特征融合图，适应场景文本长宽比变化较大的情况。在此基础上，将融合后的特征图输入到学习主动中心轮廓模型预测文本框的中心点和边界，该模型为场景文本检测提供丰富先验知识，以解决多尺度文本检测框包含过多背景或部分包围文本造成的边界检测错误问题。在MSRA-TD500、IC13、IC15和IC17MLT数据集上的实验结果表明，该网络能够提高多尺度场景文本检测的准确率，其中在MSRA-TD50数据集上F-measure为0.83，相较于MSR方法提升1%，在IC13数据集上F-measure为0.91，相较于PixelLink网络提升2%，在IC15数据集上F-measure值为0.87，相较于PSENet网络提升1%，在IC17MLT数据集上F-measure值为0.74，相较于TridentNet网络提升1%。

关键词: 场景文本检测, 多尺度特征提取, 权重融合, 主动轮廓模型, 学习主动中心轮廓模型

Abstract: In the field of scene text detection, there are several problems such as missing small text and insufficient precision for large text and multi-scale text boundary detection errors caused by large text size fluctuation.To solve the above problems, a scene text detection network based on a Learning Active Center Contour(LACC) model is proposed. First, the Multi-scale Feature Weight Fusion(MSWF) model is constructed on the basis of a Residual Network(ResNet) to extract multi-scale features and fuse weights of the input scene text images.Then the final feature fusion map is calculated to adapt to the situation where the aspect ratio of the scene text changes significantly.Finally the feature fusion map is then input into the LACC model to predict the center point and boundary of the text box, which provides rich prior knowledge for scene text detection to solve the problem of boundary detection errors caused by multi-scale text detection boxes containing too many backgrounds or partially enclosing text.Experimental results on MSRA-TD500, IC13, IC15 and IC17MLT datasets show that this network can improve the accuracy of text detection in multi-scale scenarios.The F-measure on MSRA-TD50 datasets is 0.83, which is 1% higher than the MSR method.The F-measure on IC13 datasets is 0.91, which is 2% higher than the PixelLink network.The F-measure on IC15 datasets is 0.87, which is 1% higher than PSENet.The F-measure on IC17MLT datasets is 0.74, which is 1% higher than TridentNet.

Key words: scene text detection, multi-scale feature extraction, weight fusion, active contour model, Learning Active Center Contour(LACC) model

中图分类号:

TP391

谢斌红, 秦耀龙, 张英俊. 基于学习主动中心轮廓模型的场景文本检测[J]. 计算机工程, 2022, 48(3): 244-252,262.

XIE Binhong, QIN Yaolong, ZHANG Yingjun. Scene Text Detection Based on Learning Active Center Contour Model[J]. Computer Engineering, 2022, 48(3): 244-252,262.

http://www.ecice06.com/CN/Y2022/V48/I3/244

图/表 9

20220401123309

20220401123312

20220401123316

20220401123400

20220401123410

20220401123413

20220401123417

20220401123420

20220401123425

参考文献

[1] 姜维, 张重生, 殷绪成.基于深度学习的场景文字检测综述[J].电子学报, 2019, 47(5):1152-1161. JIANG W, ZHANG C S, YIN X C.Deep learning based scene text detection:a survey[J].Acta Electronica Sinica, 2019, 47(5):1152-1161.(in Chinese)
[2] 王建新, 王子亚, 田萱.基于深度学习的自然场景文本检测与识别综述[J].软件学报, 2020, 31(5):1465-1496. WANG J X, WANG Z Y, TIAN X.Review of natural scene text detection and recognition based on deep learning[J].Journal of Software, 2020, 31(5):1465-1496.(in Chinese)
[3] SINGH B, DAVIS L S.An analysis of scale invariance in object detection-SNIP[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:3578-3587.
[4] 杨玲玲, 叶东毅.一种基于图像矩和纹理特征的自然场景文本检测算法[J].小型微型计算机系统, 2016, 37(6):1313-1317. YANG L L, YE D Y.Moment and texture based algorithm for text detection in natural scene Images[J].Journal of Chinese Computer Systems, 2016, 37(6):1313-1317.(in Chinese)
[5] 尹芳, 陈德运, 吴锐.改进的Gabor小波变换特征提取方法[J].计算机工程, 2012, 38(15):145-147. YIN F, CHEN D Y, WU R.Improved Gabor wavelet transformation feature extraction method[J].Computer Engineering, 2012, 38(15):145-147.(in Chinese)
[6] YAO C, BAI X, LIU W Y, et al.Detecting texts of arbitrary orientations in natural images[C]//Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2012:1083-1090.
[7] SHI C Z, WANG C H, XIAO B H, et al.Scene text recognition using part-based tree-structured character detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2013:2961-2968.
[8] TIAN Z, HUANG W L, HE T, et al.Detecting text in natural image with connectionist text proposal network[C]//Proceedings of European Conference on Computer Vision.Berlin, Germany:Springer, 2016:56-72.
[9] JIANG Y Y, ZHU X Y, WANG X B, et al.R2CNN:rotational region CNN for orientation robust scene text detection[EB/OL].[2021-01-05].https://arxivpreprintarxiv:1706.09579.
[10] LIAO M H, SHI B G, BAI X, et al.TextBoxes:a fast text detector with a single deep neural network[C]//Proceedings of AAAI Conference on Artificial Intelligence.[S.1.]:AAAI Press, 2017:235-136.
[11] HE P, HUANG W L, HE T, et al.Single shot text detector with regional attention[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2017:3047-3055.
[12] SZEGEDY C, LIU W, JIA Y, et al.Going deeper with convolutions[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2015:1-9.
[13] LIN T Y, DOLLAR P, GIRSHICK R, et al.Feature pyramid networks for object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:2117-2125.
[14] WANG W H, XIE E Z, LI X, et al.Shape robust text detection with progressive scale expansion network[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:9336-9345.
[15] XUE C H, LU S J, ZHANG W.MSR:multi-scale shape regression for scene text detection[EB/OL].[2021-01-05].https://arxivpreprintarxiv:1901.02596.
[16] HE T, HUANG W L, QIAO Y, et al.Accurate text localization in natural image with cascaded convolutional text network[EB/OL].[2021-01-05].https://arxivpreprintarxiv:1603.09423.
[17] ZHOU X Y, YAO C, WEN H, et al.EAST:an efficient and accurate scene text detector[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:2642-2651.
[18] DENG D, LIU H F, LI X L, et al.Pixellink:detecting scene text via instance segmentation[C]//Proceedings of AAAI Conference on Artificial Intelligence.[S.1.]:AAAI Press, 2018:358-367.
[19] HE K M, ZHANG X Y, REN S Q, et al.Identity mappings in deep residual networks[C]//Proceedings of European Conference on Computer Vision.Berlin, Germany:Springer, 2016:630-645.
[20] ZHU X, HU H, LIN S, et al.Deformable ConvNets V2:more deformable, better results[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:9300-9308.
[21] LI Y H, CHEN Y T, WANG N Y, et al.Scale-aware trident networks for object detection[C]//Proceedings of IEEE/CVF International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2019:6053-6062.
[22] YU F, KOLTUN V.Multi-scale context aggregation by dilated convolutions[EB/OL].[2021-01-05].https://arxivpreprintarxiv:1511.07122.
[23] WANG G R, WANG K, LIN L.Adaptively connected neural networks[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:1781-1790.
[24] KASS M, WITKIN A, TERZOPOULOS D.Snakes:active contour models[J].International Journal of Computer Vision, 1988, 1(4):321-331.
[25] BRESSON X, ESEDOGLU S, VANDERGHEYNST P, et al.Fast global minimization of the active contour/snake model[J].Journal of Mathematical Imaging and Vision, 2007, 28(2):151-167.
[26] LIN T Y, GOYAL P, GIRSHICK R, et al.Focal loss for dense object detection[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2017:2999-3007.
[27] LAW H, DENG J.CornerNet:Detecting objects as paired keypoints[C]//Proceedings of European Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2018:734-750.
[28] KARATZAS D, SHAFAIT F, UCHIDA S, et al.ICDAR 2013 robust reading competition[C]//Proceedings of the 12th International Conference on Document Analysis and Recognition.Washington D.C., USA:IEEE Press, 2013:1484-1493.
[29] KARATZAX D, GOMEZ-BIGORDA L, NICOLAOU A, et al.ICDAR 2015 competition on robust reading[C]//Proceedings of the 13th International Conference on Document Analysis and Recognition.Washington D.C., USA:IEEE Press, 2015:1156-1160.
[30] NAYEF N, YIN F, BIZID I, et al.ICDAR 2017 robust reading challenge on multi-lingual scene text detection and script identification-RRC-MLT[C]//Proceedings of the 14th IAPR International Conference on Document Analysis and Recognition.Washington D.C., USA:IEEE Press, 2017:1454-1459.
[31] DENG J, DONG W, SOCHIR R, et al.ImageNet:a large-scale hierarchical image database[C]//Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2009:248-255.
[32] KINGMA D P, BA J.Adam:a method for stochastic optimization[EB/OL].[2021-01-05].https://arxivpreprintarxiv:1412.6980.
[33] REN S, HE K, GIRSHICK R, et al.Faster R-CNN:towards real-time object detection with region proposal networks[EB/OL].[2021-01-05].https://arxivpreprintarxiv:1506.01497.
[34] SHI B, BAI X, BELONGIE S.Detecting oriented text in natural images by linking segments[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:3482-3490.
[35] LONG S B, RUAN J Q, ZHANG W J, et al.TextSnake:a flexible representation for detecting text of arbitrary shapes[C]//Proceedings of European Conference on Computer Vision.Berlin, Germany:Springer, 2018:20-36.
[36] LIAO M H, ZHU Z, SHI B G, et al.Rotation-sensitive regression for oriented scene text detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:5909-5918.
[37] LYU P, YAO C, WU W, et al.Multi-oriented scene text detection via corner localization and region segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:7553-7563.
[38] LIU X B, LIANG D, YAN S, et al.FOTS:fast oriented text spotting with a unified network[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:5676-5685.
[39] ZHONG Z Y, SUN L, HUO Q.An anchor-free region proposal network for Faster R-CNN-based text detection approaches[J].International Journal on Document Analysis and Recognition, 2019, 22(3):315-327.

选择文件类型/文献管理软件名称

选择包含的内容