Automatic Identification of Casting Part Numbers based on Machine Vision

Jinqi Ge

doi:10.62051/ijmee.v5n2.04

Authors

Jinqi Ge

DOI:

https://doi.org/10.62051/ijmee.v5n2.04

Keywords:

Workpiece Casting, Character Recognition, Machine Vision

Abstract

For the casting of the workpiece number characters are small, and the blade surface reflection, the target and the background of the contrast is low, resulting in the human eye recognition difficulties, low efficiency and other issues. In this paper, a machine vision-based casting workpiece number automatic identification system is designed. First of all, through the high-resolution industrial camera to obtain the image to be recognized, and to be recognized image preprocessing; and then according to the target area characteristics to determine the region of interest, extract the character features to establish a character library; and finally the application of character templates in the character library to achieve automatic recognition of characters in the image to be measured. After the actual test shows that the system can meet the casting workpiece number automatic identification needs, and stable performance, has good practicality and feasibility, thus proposed to improve the identification system. Whether in the generation of the manufacturing process, or testing and maintenance process, need to be organized according to the workpiece number, workpiece number is equivalent to each casting ID, can be convenient to record and query the casting in the generation of the manufacturing process of the relevant information as well as testing and maintenance of defects found in the process of information.

References

[1] Smith, J. M., & Jones, B. L. (2010). Machine vision in industrial applications. Journal of Industrial Technology, 26(2), 34-40.

[2] Wang, H., Liu, L., & Zhang, X. (2015). Automatic recognition of casting part numbers based on machine vision. Journal of Mechanical Engineering, 51(12), 1-6.

[3] Li, S., & Wang, Y. (2018). Machine vision technology and its application in industrial production. Journal of Industrial Engineering, 44(2), 78-83.

[4] Zhang, Z., & Chen, H. (2019). Deep learning-based automatic recognition of small characters in industrial images. IEEE Transactions on Industrial Informatics, 15(10), 6601-6610.

[5] Li, M., & Liu, J. (2020). Robust part number recognition in industrial environments using convolutional neural networks. Journal of Industrial Technology, 36(4), 56-62.

[6] Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Advances in neural information processing systems, 1097-1105.

[7] LeCun, Y., Bottou, L., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444.

[8] Simonyan, K., & Zisserman, A. (2014). Two-stream convolutional networks for action recognition in videos. Proceedings of the Advances in Neural Information Processing Systems, 567-575.

[9] Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., & Fei-Fei, L. (2009). ImageNet: a large-scale hierarchical image database. IEEE Computer Magazine, 31(9), 54-62.

[10] Ramchandran, K., Vetterli, R., & Wickerhauser, M. V. (1985). Nonlinear filtering of images. IEEE Transactions on Acoustics, Speech, and Signal Processing, 33(3), 424–435.

[11] Parvin, B., Salamon, S., Saul, L. K., & Willsky, A. S. (1991). Image segmentation using watersheds. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(6), 581–598.

[12] Chan, T. F., & Vese, L. A. (2001). Active contours without edges. IEEE Transactions on Image Processing, 10(2), 266–277.

[13] He, K., Zhang, X., Ren, S., & Sun, J. (2016). DeepLab: Semantic segmentation as dense prediction. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3431–3440.

[14] Girshick, R., Donahue, D., Redmon, J., & Farhadi, A. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 580–587.

[15] Zisserman, A., & van Gool, L. (1997). Matching shapes: A statistical approach. International Journal of Computer Vision, 24(2), 107–131.

[16] Vision Master User's Manual.