本文以焦化廠爐號自動識別為研究背景，基于MATLAB 軟件并運用圖像處理的方法對從工業現場采集到的數字字符圖像進行處理，然后采用神經網絡的方法對圖像中的字符進行識別仿真，從而達到對工業現場中的字符識別要求。該方法與傳統的方法相比較，具有較高的識別效率，且通用性較強。
關鍵詞：MATLAB；字符識別；神經網絡；圖像處理

A Research of Numerical Character Recognition Based on MATLAB Neural Networks in Industry Field Zhang Liang Fang Kangling Gong Jian Yan Xia （College of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan, China, 430081） Abstract: This paper’s research background is the auto-recognition of cook oven number in the cokeoven plant. It is based on the software MATLAB, and uses the image processing methods to deal with the pictures which are sampled in the industry field, and then the neural network algorithm is applied to stimulant the recognition of the numerical characters in the picture, so that it can fit for producing need. Compared with the traditional methods, this algorithm has good recognition efficiency and versatility.
Keywords: MATLAB; Character Recognition; Neural Networks; Image procession