The research of defect detection technology of magnetic sheet surface has important significance for improvement of production efficiency and product quality in enterprise. A single threshold method is used for binary segmentation of magnetic sheet image in this paper, then the template localization algorithm is used for template position of magnetic sheet image after binary segmentation, the magnetic sheet image with different position should be transformed into a unified coordinate system for detecting, then least square method is used for fitting straight line and fillet edge, then the calculated values are compared with standard value to determine whether are knock edges. Further, the appropriate grayscale threshold is set by the pitting and scratches characteristics of magnetic sheet image, the magnetic sheet image should be segmented according to the determined threshold value, if the defect exists, the defect area or length will be calculated, then the result is compared with standard values to determine whether is pitting or scratches. The final tests of technology in this paper show that the detection rate of knock edge and the detection rate of pitting or scratches are both acceptable. Keyword: Magnetic sheet, Machine vision, Surface defect detection, Least squares, Curve fitting, Gray threshold

Research on the Surface Defect Detection of Magnetic Sheet for Industrial Manufacture

Image segmentation method combined with Markov random field (MRF) model and regional growth image in this paper is proposed to achieve the accuracy of sonar image segmentation. First of all, the characteristics of field and the label field of sonar image is established through the MRF model; secondly, the further image segmentation is processed by region growing based on the initial image segmentation by ICM algorithm, and this reduced segmentation plaques caused by the MRF method on image segmentation. Finally, experimental results show that the method in this paper can obtain the image segmentation effectively.

A Method for Sonar Image Segmentation Based on Combination of MRF and Region Growing

Failure of asynchronous motor will cause motor short circuit accident, personal electric shock and other hazards, so it is very important to detect its abnormalities during its operation. In order to solve the problems of low detection accuracy and inaccurate detection results in asynchronous motor detection, a fault detection method of asynchronous motor based on ant lion optimizer optimizes three kernel support vector data description (ALO-TKSVDD) is proposed in this paper. Firstly, for the current signal of asynchronous motor, stochastic resonance is used to improve the signal-to-noise ratio; Secondly, ant lion optimizer (ALO) is used to optimize the three kernel support vector data description (TKSVDD) to detect abnormal data of the target signal; Finally, the accuracy and feasibility of ALO-TKSVDD are verified. Comparative experiments show that the asynchronous motor anomaly detection method proposed in this paper has the highest accuracy and the lowest false detection rate.

Fault Detection of Induction Motor Based on ALO Optimized TKSVDD

JiaGuWen image segmentation is a challenge because of their illegible writing, serious noises and broken strokes. We propose a new segmentation method based on MRF and fuzzy clustering because of their good performance in image segmentation. The segmentation is based on a new random function considering both ambiguity and spatial relationship of image pieds simultaneously. The New adaptive balance coefficient is computed according to the gray level of the considering pixel and the mean, standard deviation of the neighbor. The final value of the new random function is searching by iteration. The experiments show that the new method has good performance for JiaGuWen image segmentation.

New method for jiaguwen image segmentation based on MRF and fuzzy clustering

In respect of the classification of current image retrieval technology and the existing issues, the paper put forward a method designed for image semantic feature extraction based on artificial intelligence. The new method has solved the tough problem of image semantic feature extraction, by fusing fuzzy logic, genetic algorithm and artificial neural network altogether, which greatly improved the efficiency and accuracy of image retrieval. Keywords-Artificial Intelligence; Image Semantics Retrieval; Image Segmentation; Image Annotation

http://ipedr.com/vol49/018-A0092RE0418.pdf

The Intervention of Artificial Intelligence in Image Semantics Retrieval

This paper presented and discussed all the typical approaches based on MRF.First it provided a general framework of MRF in image segmentation and new progress for MRF modeling in recent years,and then emphatically presented the major image segmentation algorithms based on MRF,including graph cut algorithm,normalized cut algorithm,belief propagation algorithm,etc.Finally,it pointed out the future work for these segmentation algorithms.

Liu Guang-hui

Papers

Survey of image segmentation methods based on Markov random fields