Printing Digital Recognition Method Based on the Cascade Classification

Abstract:

Milk yield automatic measurement in dairy farms plays a very important role in modern production management. Then, the measurement bottle scale and the reading recognition are key steps. So, this paper presents a new effective recognition algorithm on a printed numeric character of milk measurement bottle. The algorithm uses character image Euler number, the structural shape of printed numeric character, and vertical threading of character to accomplish the cascade classification. The method for character image does not need to be complex refining process, and has come up with a new algorithm of feature extraction from image sunken area. It reduces the complexity of the algorithm, the error recognition and rejection caused by thinning deformation. It greatly improves production efficiency and economic benefits. The experiment proves that the method is effective.

• Periodical: Advanced Materials Research (Volumes 546-547)
• Pages: 599-603
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.546-547.599
• Online since: July 2012
• Authors: Hui Pu, Wen Xing Bao, Xiao Wu Zhang
• Keywords: Automatic Measurement, Cascade Classification, Euler Number, Structural Shap, Vertical Threading

References

[1] Oivind Due Trier, Anil K. Jain, Torfinn Taxt. Feature Extraction Methods for Character Recognition-A Survey. Pattern Recognition, Vol. 29, No. 4, pp.641-662, 1996, Elsevier Science Ltd.

DOI: 10.1016/0031-3203(95)00118-2

[2] Fukushima K, Wake N. ．Handwritten alphanumeric character recognition by the recognition．IEEE transactions on neural networks, Vol. 2, No. 3, May 1991.

DOI: 10.1109/72.97912

[3] Pope, Arthur R. and David G. Lowe．Learning probabilistic appearance models for object recognition．in Early Visual Learning, eds．Shree Nayar and Tomaso Poggio (Oxford University Press, 1996), p.67–97.

[4] Quanbing Yuan，Fu Huang． Digital character recognition algorithm research [D]. China's outstanding master's degree dissertation full-text database.

[5] David G. Lowe．Distinctive Image Features from Scale-Invariant Keypoints．Accepted for publication in the International Journal of Computer Vision, 2004.

[6] Guibo Ni，Xiaozhun Niang, Printing digital recognition method based on shape [D]．China's outstanding master's degree dissertation full-text database.

[7] Yueping Kong，Ping Zeng，Zhijie Li , Haihong Zheng， Peipei Xu．Efficient recognition algorithm based on combination features [D]．China's outstanding master's degree dissertation full-text database.

[8] Guoen Xia, Weidong Jin, Gexiang Zhang．Handwritten digital recognition method based on combination features [D]．China's outstanding master's degree dissertation full-text database.