Abstract
Detection of wood plate surface defects using image processing is a complicated problem in the forest industry as the image of the wood surface contains different kinds of defects. In order to obtain complete defect images, we used convex optimization (CO) with different weights as a pretreatment method for smoothing and the Otsu segmentation method to obtain the target defect area images. Structural similarity (SSIM) results between original image and defect image were calculated to evaluate the performance of segmentation with different convex optimization weights. The geometric and intensity features of defects were extracted before constructing a classification and regression tree (CART) classifier. The average accuracy of the classifier is 94.1% with four types of defects on Xylosma congestum wood plate surface: pinhole, crack, live knot and dead knot. Experimental results showed that CO can save the edge of target defects maximally, SSIM can select the appropriate weight for CO, and the CART classifier appears to have the advantages of good adaptability and high classification accuracy.
Similar content being viewed by others
References
Baják S, Páles Z (2009) A separation theorem for nonlinear inverse images of convex sets. Acta Math Hung 124(1):125–144
Barszcz A, Michalec K, Wasik R (2014) A comparative analysis of pine and beech wood classification according to polish and eunorms. Drewno 57(193):135–145
Bhateja V, Srivastava A, Kalsi A (2014) Fast SSIM index for color images employing reduced-reference evaluation. Adv Intell Syst Comput 247:451–458
Bouhamidi A, Enkhbat R, Jbilou K (2014) Conditional gradient Tikhonov method for a convex optimization problem in image restoration. J Comput Appl Math 255:580–592
Castellani M, Rowlands H (2009) Evolutionary artificial neural network design and training for wood veneer classification. Eng Appl Artif Intell 22:732–741
Dirami A, Hammouche K, Diaf M, Siarry P (2013) Fast multilevel thresholding for image segmentation through a multiphase level set method. Sig Process 7:342–355
Han YH, Wang YM, Sun Q, Zhao Y (2016) Crop row detection based on wavelet transformation and Otsu segmentation algorithm. J Electron Inf Technol 1:63–70
Hu CS, Min X, Yun H, Wang T, Zhang SK (2011) Automatic detection of sound knots and loose knots on sugi using gray level co-occurrence matrix parameters. Ann For Sci 68(6):1077–1083
Santiago AJS, Yuste AJ, Expósito JEM, Galán SG, Prado RP, Maqueira JM, Bruque S (2012) Real-time image texture analysis in quality management using grid computing: an application to the MDF manufacturing industry. Int J Adv Manuf Technol 58(9):1217–1225
Wang DQ, Liu ZW, Cong FY (2015) Wood surface quality detection and classification using gray level and texture features. Lect Notes Comput Sci V9377:248–257
Yuan WQ, Li SL, Li DJ (2016) Wood surface defect recognition based on sub-region zoom Gaussian fitting. Chin J Sci Instrum 4:879–886
Zhang YZ, Liu SJ, Cao J, Li C, Yu HL (2014) A rapid, automated flaw segmentation method using morphological reconstruction to grade wood flooring. J For Res 25(4):959–964
Zhang YZ, Liu SJ, Cao J, Li C, Yu HL (2016) Wood board image processing based on dual-tree complex wavelet feature selection and compressed sensing. Wood Sci Technol 50(2):297–311
Author information
Authors and Affiliations
Corresponding authors
Additional information
Project funding: The work was supported by the Fund of Forestry 948 project (2015-4-52), the Fundamental Research Funds for the Central Universities (2572017DB05), and the Natural Science Foundation of Heilongjiang Province (C2017005).
The online version is available at http://www.springerlink.com
Corresponding editor: Tao Xu.
Rights and permissions
About this article
Cite this article
Chang, Z., Cao, J. & Zhang, Y. A novel image segmentation approach for wood plate surface defect classification through convex optimization. J. For. Res. 29, 1789–1795 (2018). https://doi.org/10.1007/s11676-017-0572-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11676-017-0572-7