A flexible ic substrate character recognition and information analysis method

Abstract

The invention discloses a method for character recognition and information analysis of a flexible IC substrate, which comprises the following steps: collecting a color image of an IC substrate, performing rough positioning of a text area; cutting the image of a text area from the original image, and performing connected domain analysis; performing upper and lower boundaries and Fine positioning of the left and right boundaries; use convolutional network for feature extraction; segment the image into sequences; input the cyclic neural network to obtain the character prediction results; decode the result sequence to obtain the final recognition results; divide the final character recognition results according to the design rules and compare them with the standard library Comparison; obtain the final recognition result and the analysis result of key component information. The invention solves the problem that the traditional character recognition algorithm is easily affected by environmental factors and leads to poor generalization performance, and is suitable for the detection of variable-length character strings, greatly improves the accuracy of detection, and can effectively analyze the circuits contained in character strings Component key information.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a flexible IC substrate character recognition and information analysis method. Background technique [0002] Due to the precision requirements of electronic products, each process is closely linked in the production process of the product, so the quality of each process must be guaranteed. The characters on the flexible IC substrate identify important information such as the type, capacity, and package type of circuit components such as capacitors, inductors, and chips. Therefore, it is very important to detect them. However, traditional character recognition algorithms are vulnerable to various Influenced by these factors, the generalization performance is poor. Contents of the invention [0003] The main purpose of the present invention is to overcome the shortcomings and deficiencies of the prior art, and provide a flexible IC substrate character recognition and information a...

AI Technical Summary

Problems solved by technology

The characters on the flexible IC substrate identify important information such as the type, capacity, and package type of circuit components such as capacitors, inductors, and chips. Therefore, it is very important to detect them. However, traditional character recognition algorithms are vulnerable to various Influenced by various factors, the generalization performance is poor

Images