Optical Character Recognition (OCR) Applications

Character recognition overview

OCR (Optical Character Recognition) refers to optical character recognition, which uses optical technology and computer technology to convert characters printed on the surface of objects into information that can be recognized by computers. In the metallurgical field, OCR technology can be applied to automobile license plate recognition, hot metal tank number recognition, train carriage number recognition, as well as hook number, steel bar bundle number, billet number, etc.

OCR technology is also widely used in food and drug packaging, 3C electronics, auto parts production, tobacco and other industries to realize automatic identification of production date, batch number, product number and other information.

System composition

The Optical Character Recognition system includes image segmentation and neuron deep learning technology, which can accurately identify stamped characters. The character recognition system uses a high-definition industrial camera to obtain character images. After image preprocessing, character positioning and segmentation, the characters are recognized, and the results are analyzed to achieve the purpose of use.

The character recognition system includes signal acquisition sub-module, video acquisition sub-module, character recognition sub-module, recognition result output and display sub-module.

Deep learning OCR completes the information encoding of character images to be recognized by designing a convolutional neural network with dozens of layers and then uses a heuristic attention model to achieve decoding from features to characters. Among them, the heuristic mechanism specially designed for character recognition simulates the thinking mode of the human brain to evaluate the rationality of the features extracted by the attention model, making the attention model highly adaptable in complex scenes and achieving an extreme accuracy of greater than 99.5%. High character recognition rate.

Advantages of Optical Character Recognition

1. Achieve standardization and avoid manual recording or unrecognized manual operators.

2. Labor costs are high and efficiency is limited;

3. Various sites are complex, and there are certain risks in personnel scanning codes, and the labor intensity is high and the efficiency is low.

Optical Character Recognition application scenarios

Hook number identification

High Speed Wire Rod PF Line Hook Number Recognition System


Train compartment number identification

Train compartment number identification, OCR


Steel plate character recognition

rebar online welding tag system


Square (plate) billet number identification

Automatic Coding Robot

Metallurgical Intelligence
Change the way of manufacturing

Save labor, improve working environment, improve efficiency, reduce error rate and save cost!

Металлургический интеллект
Изменить способ производства

Сэкономьте труд, улучшите рабочую среду, повысьте эффективность, уменьшите количество ошибок и снизьте затраты!