Automated visual inspection of surface defects based on compound moment invariants and support vector machine

The traditional inspection methods are mostly based on manual inspection which is very likely to make erroneous judgments due to personal subjectivity or eye fatigue, and can＇t satisfy the accuracy. To overcome these difficulties, we develop a machine vision inspection system. We first compare several kinds of methods for feature extraction and classification, and then present a real-time automated visual inspection system for copper strips surface （CSS） defects based on compound moment invariants and support vector machine （SVM）. The proposed method first processes images collected by hardware system, and then extracts feature characteristics based on grayscale characteristics and morphologic characteristics （Hu and Zernike compound moment invariants）. Finally, we use SVM to classify the CSS defects. Furthermore, performance comparisons among SVM, back propagation （BP） and radial basis function （RBF） neural networks have been involved. Experimental results show that the proposed approach achieves an accuracy of 95.8% in detecting CSS defects.

Complications and outcomes of descemet stripping automated endothelial keratoplasty with artisan aphakia intraocular lens implantation

AIM： To evaluate the complications and outcomes of descemet stripping automated endothelial keratoplasty（DSAEK） combined with artisan aphakia intraocular lens（IOL） implantation in severely damaged eyes without capsular support.METHODS： DSAEK combined with artisan iris claw IOL implantation was performed on 29 eyes. All eyes were of abnormal structure due to complications from prior intraocular surgeries and ocular trauma. Ocular complications observed included graft dislocations, high intraocular pressure（IOP）, IOL dislocations, macular edema and hyphema. Best corrected visual acuity（BCVA）, IOP and mean central endothelial cell density（ECD） were recorded.RESULTS： Thirteen eyes had a history of ocular trauma, 10 eyes had an anterior chamber IOL, 16 eyes had prior vitrectomy. The iris was abnormal in 22 cases. Graft dislocation occurred in 5（17.2%） of 29 eyes. IOL dislocation occurred in 2 eyes（6.9%）. High IOP was found in 9 eyes and was controlled with treatment. The preoperative mean BCVA was 20/286. The 6 mo postoperative mean BCVA was 20/42. The average center ECD was 1965.3 cells/mm^2 at 6 mo, and the rate of the donor cell loss was 34.7%.CONCLUSION： DSAEK combined with artisan aphakia IOL implantation is an alternative option for resolving endothelial and lens disorders in aphakic eyes without capsular support. However, it should be performed cautiously for eyes with severe iris defects.

Multi-class classification method for strip steel surface defects based on support vector machine with adjustable hyper-sphere

Focusing on strip steel surface defects classification, a novel support vector machine with adjustable hyper-sphere （AHSVM） is formulated. Meanwhile, a new multi-class classification method is proposed. Originated from support vector data description, AHSVM adopts hyper-sphere to solve classification problem. AHSVM can obey two principles： the margin maximization and inner-class dispersion minimization. Moreover, the hyper-sphere of AHSVM is adjustable, which makes the final classification hyper-sphere optimal for training dataset. On the other hand, AHSVM is combined with binary tree to solve multi-class classification for steel surface defects. A scheme of samples pruning in mapped feature space is provided, which can reduce the number of training samples under the premise of classification accuracy, resulting in the improvements of classification speed. Finally, some testing experiments are done for eight types of strip steel surface defects. Experimental results show that multi-class AHSVM classifier exhibits satisfactory results in classification accuracy and efficiency.

Influence of Residual Stress on Shape of Heavy-gauge,High-strength Steel Caused by Cooling Process after Hot Rolling

The cooling process following hot rolling has a significant effect on the shape quality of a hot-rolled strip.The temperature and stress fields in the cooling process for a 14 mm thick strip with yield strength of 500 MPa grade were analyzed by the finite element method and actual test data,and the relationship between residual stress and shape defects was described.Subsequently,the small-crown rolling process and the coil slow cooling process were investigated.The results indicate that these processes improved the shape quality of the final product significantly.