Detection and Recognition of Characters on the Surface of Metal Workpieces with Complex Background

The industrial code contains a lot of information, and is widely used in all walks of life. It is an important carrier for enterprises to carry out production management, quality control, product tracking and automated production. The detection and recognition of characters on the surface of metal workpieces has an important role and significance in complex industrial environments. Aiming at complex industrial environment, this paper proposes a method for detecting and recognizing characters on the surface of metal workpieces. First of all, improve the process of image acquisition. Secondly, the image is pre-processed, such as image enhancement, filtering and denoising, character localization and extraction. And then, the vertical projection method is used for character segmentation. Finally, Tesseract-OCR is used for character recognition. Experimental results show that the method has a recognition rate of 98.6%, and has the characteristics of high efficiency and realtime performance.