基于改進級聯(lián)R-CNN的面料疵點檢測方法
點擊下方卡片,關注“新機器視覺”公眾號
重磅干貨,第一時間送達
文章編號 | 1009-265X(2022)02-0048-09
來源 | 《現(xiàn)代紡織技術》2022年第30卷,第2期,
作者 | 許勝寶1a,鄭飂默2,3,袁德成1b
( 1.沈陽化工大學, a.計算機科學與技術學院; b.信息工程學院,沈陽 ;2.中國科學院沈陽計算技術研究所,沈陽 ;3.沈陽中科數(shù)控技術股份有限公司,沈陽 )
作者簡介 | 許勝寶(1993-),男,遼寧丹東人,碩士研究生,主要從事計算機視覺方面的研究。
摘要 由于布匹疵點種類分布不均,部分疵點具有極端的寬高比,而且小目標較多,導致檢測難度大,因此提出一種改進級聯(lián)R-CNN的布匹疵點檢測方法。針對小目標問題,在R-CNN部分采用在線難例挖掘,加強對小目標的訓練;針對布匹疵點極端的長寬比,在特征提取網絡中采用了可變形卷積v2來代替?zhèn)鹘y(tǒng)的正方形卷積,并結合布匹特征重新設計邊界框比例。最后采用完全交并比損失作為邊界框回歸損失,獲取更精確的目標邊界框。結果表明:對比改進前的模型,改進后的模型預測邊界框更加精確,對小目標的疵點檢測效果更好,在準確率上提升了3.57%,平均精確度均值提升了6.45%,可以更好地滿足面料疵點的檢測需求。
關鍵詞 級聯(lián)R-CNN;面料疵點;檢測;可變形卷積v2;在線難例挖掘;完全交并比損失
改進Cascade R-CNN的面料疵點檢測方法


圖1 Cascade R-CNN網絡結構
Fig.1 Architecture of the Cascade R-CNN network
1.1 在線難例挖掘采樣

圖2 在線難例挖掘結構
Fig.2 Architecture of online hard example mining
1.2 可變形卷積v2
R={(-1,-1),(-1,0)...,(0,1),(1,1)}
(1)

(2)

(3)

(4)

圖3 Resnet骨干網絡結構
Fig.3 Architecture of Resnet backbone network

圖4 可變形卷積示意
Fig.4 Diagram of deformable convolution
1.3 完全交并比損失函數(shù)

(5)
IoU Loss=-ln(IoU)
(6)

(7)

(8)

(9)

(10)

(11)
實驗結果與對比分析

2.1 實驗數(shù)據(jù)集
表1 布匹瑕疵的分類與數(shù)量
Tab.1 Classification and quantity of fabric defects


圖5 不同類別目標數(shù)統(tǒng)計
Fig.5 Statistics of target number of different categories

圖6 目標寬高比統(tǒng)計
Fig.6 Statistics of target aspect ratio

圖7 典型疵點
Fig.7 Typical defects

圖8 目標面積統(tǒng)計
Fig.8 Statistics of target area
2.2 實驗環(huán)境及配置
2.3 實驗結果對比

圖9 模型改進前后的檢測效果對比
Fig.9 The Comparison of detection effect before and after model improvement
表2 模型改進前后的評價參數(shù)
Tab.2 Evaluation parameter before and after model improvement %

表3 不同光照強度下測試集的對比
Tab.3 The comparison of the proposed algorithm under different light intensities on test sets

表4 引入OHEM前后的對比
Tab.4 The comparison before and after the introduction of OHEM

表5 算法在不同特征提取網絡上的對比
Tab.5 The comparison of algorithms on different feature extraction networks

結 論

(點擊閱讀原文,閱讀電子期刊)
參考文獻
[1] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: Common objects in context [C]// European Conference on Computer Vision, Cham: Pringer International Pubcishing, 2014:740-755.
[2] HU X, XU X, XIAO Y, et al. SINet: A scale-insensitive convolutional neural network for fast vehicle detection[J]. IEEE Transactions on Intelligent Transportation Systems,2019,20(3): 1010-1019.
[3] LI J, LIANG X, WEI Y, et al. Perceptual generative adversarial networks for small object detection [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA. IEEE, 2017: 1222-1230.
[4] 陳康,朱威,任振峰,等.基于深度殘差網絡的布匹疵點檢測方法[J]. 小型微型計算機系統(tǒng),2020,41(4):800-806.
CHEN Kang, ZHU Wei, REN Zhenfeng, et al. Fabric defect detection method based on deep residual network[J]. Journal of Chinese Mini-Micro Computer Systems. 2020, 41(4): 800-806.
[5] 孟志青,邱健數(shù).基于級聯(lián)卷積神經網絡的復雜花色布匹瑕疵檢測算法[J]. 模式識別與人工智能,2020,33(12): 1135-1144.
MENG Zhiqing, QIU Jianshu. Defect detection algorithm of complex pattern fabric based on cascaded convolution neural network[J]. Pattern Recognition and Artificial Intelligence, 2020, 33(12): 1135-1144.
[6] CHAWLA N V, BOWYER K W, HALL L O, et al. Synthetic minority over-sampling technique[J]. Journal of artificial intelligence research,2002,16: 321-357.
[7] YANG Y Z, XU Z. Rethinking the value of labels for improving class-imbalanced learning[EB/OL]. 2020: arXiv: 2006.07529[cs.LG]. https://arxiv.org/abs/2006.07529.
[8] CAI Z W, VASCONCELOS N. Cascade R-CNN: Delving into high quality object detection[C]//Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA. IEEE, 2018: 6154-6162.
[9] ZHU X Z, HU H, LIN S, et al. Deformable ConvNets V2: More deformable, better results[C]//Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA. IEEE, 2019: 9300-9308.
[10] SHRIVASTAVA A, GUPTA A, GIRSHICK R. Training region-based object detectors with online hard example mining[C]// Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA. IEEE, 2016: 761-769.
[11] ZHENG Z H, WANG P, LIU W, et al. Distance-IoU loss: Faster and better learning for bounding box regression[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(7): 12993-13000.
[12] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
[13] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]// Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA. IEEE, 2016: 770-778.
[14] LIN T Y, DOLLwidth=9,height=12,dpi=110R P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]// Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA. IEEE, 2017: 936-944.
[15] DAI J F, QI H Z, XIONG Y W, et al. Deformable convolutional networks[C]//International Conference on Computer Vision. Venice, Italy. IEEE, 2017: 764-773.
[16] YU J H, JIANG Y N, WANG Z Y, et al. UnitBox: An advanced object detection network[C]//Proceedings of the 24th ACM International Conference on Multimedia. Amsterdam The Netherlands. New York, NY, USA: ACM, 2016: 516-520.
[17] REZATOFIGHI H, TSOI N, GWAK J, et al. Generalized intersection over union: A metric and a loss for bounding box regression[C]// Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA. IEEE, 2019: 658-666.
[18] BODLA N, SINGH B, CHELLAPPA R, et al. Soft-NMS: Improving object detection with one line of code[C]// International Conference on Computer Vision. Venice, Italy. IEEE, 2017: 5562-5570.
[19] NEUBECK A, VAN GOOL L. Efficient non-maximum suppression[C]// 18th International Conference on Pattern Recognition. Hong Kong, China. IEEE,2006: 850-855.
[20] 安萌,鄭飂默,王詩宇,等.一種改進Faster R-CNN的面料疵點檢測方法[J]. 小型微型計算機系統(tǒng),2021,42(5):1029-1033.
AN Meng, ZHENG Liaomo, WANG Shiyu, et al. A fabric defect detection method based on improved faster R-CNN[J]. Journal of Chinese Computer Systems, 2021,42(5):1029-1033.
[21] 張澤苗,霍歡,趙逢禹. 深層卷積神經網絡的目標檢測算法綜述[J]. 小型微型計算機系統(tǒng),2019,40(9):1825-1831.
ZHANG Zemiao, HUO Huan, ZHAO Fengyu. Survey of object detection algorithm based on deep convolutional neural networks[J]. Journal of Chinese Computer Systems, 2019, 40(9): 1825-1831.
[22] PADILLA R, PASSOS W L, DIAS T L B, et al. A comparative analysis of object detection metrics with a companion open-source toolkit[J]. Electronics,2021,10(3): 279.
[23] 陳科圻,朱志亮,鄧小明,等.多尺度目標檢測的深度學習研究綜述[J]. 軟件學報,2021,32(4):1201-1227.
CHEN Keqi, ZHU Zhiliang, DENG Xiaoming, et al. Deep learning for multi-scale object detection: asurvey[J]. Journal of Software. 2021,32(4):1201-1227.
發(fā)布 | 浙江理工大學雜志社 新媒體中心
編輯 | 徐 航
本文僅做學術分享,如有侵權,請聯(lián)系刪文。
