一种基于充分卷积的边缘检测算法An edge detection algorithm based on full convolution
谢晓飞;来毅;刘颖;
摘要(Abstract)：
针对基于卷积神经网络的图像边缘检测算法忽略中间层而丢失图像细节信息的问题,提出一种基于充分卷积的边缘检测算法。在视觉几何组16骨干网络上剪切掉所有的全连接层和池化层以构建全卷积网络;在全卷积网络每个阶段的1×1×21卷积层后边连接累加层获取每个阶段中的特征信息;通过融合层替换原来位置剪切掉的全连接层,在融合层的后边连接卷积层和损失函数层,并重新计算损失函数训练网络参数。实验结果表明,该算法的边缘检测性能优于人眼的平均性能,也比其他边缘检测算法性能更优。
关键词(KeyWords)： 深度学习;卷积神经网络;边缘检测;特征提取
基金项目(Foundation):
作者(Author): 谢晓飞;来毅;刘颖;
Email:
DOI: 10.13682/j.issn.2095-6533.2020.05.009
参考文献(References)：
- [1] WANG X,MA H,CHEN X Z,et al.Edge preserving and multi-scale contextual neural networkfor salient object detection[J].IEEE Transactions on Image Processing,2018,27(1):121-134.DOI:10.1109/TIP.2017.2756825.
- [2] 王殿伟,何衍辉,李大湘,等.改进的YOLOv3红外视频图像行人检测算法[J].西安邮电大学学报,2018,23(4):48-52.DOI:10.13682/j.issn.2095-6533.2018.04.008.
- [3] MARMANIS D,SCHINDLER K,WEGNER J D,et al.Classification with an edge:Improving semantic image segmentation with boundary detection[J].ISPRS Journal of Photogrammetry and Remote Sensing,2018,135:158-172.DOI:10.1016/j.isprsjprs.2017.11.009.
- [4] LIU Y,CHENG M M,HU X X,et al.Richer convolutional features for edge detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,41(8):1939-1946.DOI:10.1109/TPAMI.2018.2878849.
- [5] 张雪锋,韩志玲.一种改进BEMD的指纹边缘检测算法[J].西安邮电大学学报,2018,23(1):45-52.DOI:10.13682/j.issn.2095-6533.2018.01.007.
- [6] DOLLAR P,ZITNICK C L.Fast edge detectionusing structured forests[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(8):1558-1570.DOI:10.1109/TPAMI.2014.2377715.
- [7] HALLMAN S,FOWLKES C C.Oriente edge forests for boundary detection[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition.Boston:IEEE,2015:1732-1740.DOI:10.1109/CVPR.2015.7298782.
- [8] MARTIN D R,FOWLKES C C,MALIK J.Learning to detect natural image boundaries using local brightness,color,and texture cues[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(5):530-549.DOI:10.1109/TPAMI.2004.1273918.
- [9] ARBELáEZ P,MAIRE M,FOWLKES C,et al.Contour detection and hierarchical image segmentation[J].IEEE Transactions on PatternAnalysis and Machine Intelligence,2011,33(5):898-916.DOI:10.1109/TPAMI.2010.161.
- [10] BERTASIUS G,SHI J,TORRESANI L.DeepEdge:A multi-scale bifurcated deep network fortop-down contour detection[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition.Boston:IEEE,2015:4380-4389.DOI:10.1109/CVPR.2015.7299067.
- [11] SHEN W,WANG X G,WANG Y,et al.Deep Contour:A deep convolutional feature learned by positive-sharing loss for contour detection[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition.Boston:IEEE,2015:3982-3991.DOI:10.1109/CVPR.2015.7299024.
- [12] GANIN Y,LEMPITSKY V.N4-fields:Neural network nearest neighbor fields for image transforms[C]//Proceedings of Asian Conference on Computer Vision.[S.l.]:Springer,2014:536-551.DOI:10.1007/978-3-319-16808-1_36.
- [13] XIE S N,TU Z W.Holistically-nested edge detection[J].International Journal of Computer Vision,2017,125:3-18.DOI:10.1007/s11263-017-1004-z.
- [14] XU D,OUYANG W L,ALAMEDA-PINEDA X,et al.Learning deep structured multi-scale features using attention-gated CRFs for contourprediction[J].Computer Vision and Pattern Recognition,2018,125(1):3-18.
- [15] JIA Y Q,EVAN S,DONAHUE J,et al.Caffe:Convolutional architecture for fast feature embedding[C]//Proceedings of the 22nd ACM international conference on Multimedia.[S.l.]:ACM,2014:675-678.DOI:10.1145/2647868.2654889.
- [16] MOTTAGHI R,CHEN X J,LIU X B,et al.Therole of context for object detection and semantic segmentation in the wild[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition.Columbus:IEEE,2014:891-898.DOI:10.1109/CVPR.2014.119.
- [17] SILBERMAN N,HOIEM D,KOHLI P,et al.Indoor segmentation and support inference from RGBD images[C]//Proceedings of European Conference on Computer Vision.[S.l.]:Springer,2012:746-760.DOI:10.1007/978-3-642-33715-4_54.
- [18] MéLY D A,KIM J,MCGILL M,et al.A systematiccomparison between visual cues for boundarydetection[J].Vision Research,2016,120:93-107.DOI:10.1016/j.visres.2015.11.007.