Image Crack Detection with Fully Convolutional Network Based on Deep Learning

被引：0

作者：

Wang S. ^{[1
]}

Wu X. ^{[1
]}

Zhang Y. ^{[1
]}

Chen Q. ^{[1
]}

机构：

[1] Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming

来源：

Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics | 2018年 / 30卷 / 05期

关键词：

Crack detection; Deep learning; Fully convolutional network; Network model;

D O I：

10.3724/SP.J.1089.2018.16573

中图分类号：

学科分类号：

摘要：

In order to effectively detect crack and reduce the error mark under complex background, a FCN fully convolutional network is introduced into the image crack detection in this paper. A crack FCN model based on FCN model is proposed to address the problems that lose local information and the capacity of partial refinement, which are frequently encountered in FCN model in the crack detection experiment. Firstly, with increasing resolution, the Dropout method of the full connection layer is cancelled, such that the increased selection of the crack information is fulfilled. Secondly, the whole network is carried out in a progressive manner by deepening the network depth of the FCN network. Finally, deconvolution layer in higher scale is added to extend the local fine detail based on the constructed network. According to the comparison experiment results, FCN-8s model and other detect methods in the 2 156 self-made crack image datasets illustrate that the accuracy of detection can be improved, whilst the error label can be reduced by using the Crack FCN network model. © 2018, Beijing China Science Journal Publishing Co. Ltd. All right reserved.

引用

页码：859 / 867

页数：8

共 28 条

[1]

Kim H., Ahn E., Cho S., Et al., Comparative analysis of image binarization methods for crack identification in concrete structures, Cement and Concrete Research, 99, pp. 53-61, (2017)

[2]

Priyadumkol J., Kittichaikarn C., Thainimit S., Crack detection on unwashed eggs using image processing, Journal of Food Engineering, 209, pp. 76-82, (2017)

[3]

Omid M., Soltani M., Dehrouyeh M.H., Et al., An expert egg grading system based on machine vision and artificial intelligence techniques, Journal of Food Engineering, 118, 1, pp. 70-77, (2013)

[4]

Yao L., Xiao J., Pantograph slide cracks detection method based on fuzzy entropy and hough rransform, Journal of the China Railway Society, 36, 5, pp. 58-63, (2014)

[5]

Withayachumnankul W., Kunakornvong P., Asavathongkul C., Et al., Rapid detection of hairline cracks on the surface of piezoelectric ceramics, International Journal of Advanced Manufacturing Technology, 64, 9-12, pp. 1275-1283, (2013)

[6]

Wang Y., Qu G., Liu X., Et al., Image subtraction detection algorithm for surface defect of steel ball, Journal of Computer-Aided Design & Computer Graphics, 28, 10, pp. 1699-1704, (2016)

[7]

Cai Z., Xiao J., Wen L., Et al., Algorithm of defect segmentation for AFP based on prepregs, Journal of Aeronautical Materials, 37, 2, pp. 21-27, (2017)

[8]

Zhang Y., Xu L., Ding L., Et al., Defects segmentation for wood floor based on image fusion method, Electric Machines and Control, 18, 7, pp. 113-118, (2014)

[9]

Luo Q.W., He Y.G., A cost-effective and automatic surface defect inspection system for hot-rolled flat steel, Robotics and Computer-Integrated Manufacturing, 38, pp. 16-30, (2016)

[10]

Zhao J., Jia M., Detection and recognition method of small defects in workpiece surface, Journal of Southeast University: Natural Science Edition, 44, 4, pp. 735-739, (2014)

← 1 2 3 →