A metal plate strip product label information identification method based on computer vision

Abstract

The invention discloses a metal plate strip product label information identification method based on computer vision. the position of a product label area is obtained through segmentation of a lightweight network; the coordinate information of the product label is obtained through an image processing means; correction to enabline see-through transformer is realized, the VGG16 is used for identifying the rotating text; character rotation small-angle registration is carried out by using a variance method; the text position detection precision and the text recognition precision are effectively improved; YOLOv3 and ENet are adopted, so that text correction and position acquisition are faster and more accurate; the loss of the computer and the requirement on the performance of the computer areeffectively reduced; the detection of the text with the uncertain length is realized by utilizing the characteristics of the LSTM in the CRNN; The detection performance is effectively improved, the good recognition performance is achieved in natural scenes such as non-uniform illumination, complex backgrounds, multi-language mixing, text complex formats, product label picture rotation, affine distortion and perspective distortion, and convenience is provided for inputting of label information of metal plate strips.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a text information recognition method for metal strip product labels which integrates "traditional image processing, target segmentation, target detection and text recognition". Background technique [0002] Entering the relevant ordering information of the ordered products into the enterprise system is an important part of the warehouse-in operation in iron and steel enterprises, and manually entering information is very time-consuming and labor-intensive. When there are a large number of warehouse-in products, it is difficult to complete in a short time, seriously Therefore, it is an urgent problem to use the existing image processing technology to help enterprises improve the input efficiency of product label information. The traditional text recognition method firstly locates the text, then corrects the oblique text, and then separates the individual characters, and ...

AI Technical Summary

Problems solved by technology

[0002] Entering the relevant ordering information of the ordered products into the enterprise system is an important part of the warehouse-in operation in iron and steel enterprises, and manually entering information is very time-consuming and labor-intensive. When there are a large number of warehouse-in products, it is difficult to complete in a short time, seriously It affects the production efficiency. Therefore, it is an urgent problem to use the existing image processing technology to help enterprises improve the input efficiency of product label information.

The traditional text recognition method firstly locates the text, then corrects the oblique text, and then separates the individual characters, and recognizes the individual characters, and finally performs semantic error correction based on statistical models (such as hidden Markov chains, HMM). When the product label pictures taken in the scene have complex backgrounds, artistic fonts, low resolution, non-uniform lighting, image degradation, character deformation, multi-language mixing, and complex text layouts, etc., the text recognition ability is lost.

The existing advanced text recognition methods based on deep learning have shown great advantages in text recognition in natural scenes, but they are also ineffective in the case of serious distortions such as affine deformation, perspective deformation, and rotation transformation in product label images. Can accurately identify text information, and the text recall rate is low

The existing text recognition technology has not been popularized and effectively applied in the iron and steel industry, and there is no effective identification technology for the product label information of iron and steel enterprises

Images