Detection of Irregularities on Automotive Semiproducts
Erik Dovgan, Klemen Gantar, Valentin Koblar, Bogdan Filipic Department of Intelligent Systems, Jozef Stefan Institute, Jamova cesta 39, SI-1000 Ljubljana, Slovenia
Abstract: he use of applications for automated inspection of semiproducts is increasing in various industries, including the automotive industry. This paper presents the development of an application for automated visual detection of irregularities on commutators that are parts of vehicle’s fuel pumps. Each type of irregularity is detected on a partition of the commutator image. The initial results show that such an automated inspection is able to reliably detect irregularities on commutators. In addition, the results confirm that the set of attributes used to build the classifiers for detecting individual types of irregularities and the priority of these classifiers significantly influence the classification accuracy.
Keywords: Bioreceptor Elements, Sensors, Water Purifiers Detection of Irregularities on Automotive Semiproducts
References: [1] Koblar, V., Dovgan, E., Filipic. B. (2014). Tuning of a machinevision- based quality-control procedure for semiproducts in automotive industry. 2014. Submitted for publication.
[2] OpenCL module within OpenCV library. http: //docs.opencv.org/modules/ocl/doc/ introduction.html.
[3] OpenCL: The open standard for parallel programming. http: //www.khronos.org/opencl/.
[4] OpenCV: Open source computer vision. http://opencv. org/.
[5] Playne, D. P., Hawick, K. A., and Leist. A. (2010). Parallel graph component labelling with GPUs and CUDA. Parallel Computing, 36(12): 655–678, 2010.
[6] Quinlan, J. R. (1993). C4.5: Programs for Machine Learning. Morgan Kaufmann Publishers, 1993.
[7] Weka Machine Learning Project. http://www.cs. waikato.ac.nz/ml/weka/index.html.