A barcode tilt correction method based on multi-task target detection

Abstract

The invention discloses a barcode tilt correction method based on multi-task target detection, comprising: constructing a single-stage target detector, the single-stage target detector includes a sequentially connected feature extraction basic network and a detection head network; Inputting the feature extraction basic network to extract a feature map; inputting the feature map into the detection head network, performing classification and position regression on the feature map, and obtaining a correction result. The present invention firstly classifies the degree of inclination of the barcode, and then performs angle regression, which effectively reduces the difficulty of barcode correction, and forms a multi-task target detection model by merging with a single-stage target detector, thereby improving the efficiency of detection and correction in parallel, and improving the translation efficiency. Code accuracy and speed play a better role in promoting.

Description

technical field [0001] The invention relates to the technical fields of deep learning and image processing, in particular to a bar code tilt correction method based on multi-task target detection. Background technique [0002] The current mainstream barcode recognition methods are mainly divided into traditional digital image processing and deep learning algorithms. [0003] The traditional image processing method mainly designs the features and rules manually, marks the barcode area, calculates the rotation angle, and then obtains the barcode correction result. In general, traditional image algorithms have higher requirements for experiments and application environments. In the logistics package sorting scenario, the barcode image quality is degraded and the features are not obvious due to uneven lighting, background interference, package distortion, blur, and contamination, which greatly reduces the performance of the algorithm. [0004] In recent years, with the rapid d...

AI Technical Summary

Problems solved by technology

Among some existing methods, some are cascaded barcode detection algorithms based on convolutional neural networks. First, the Faster-Rcnn target detection algorithm is used to obtain the barcode area, and then the Maximally Stable Extremal Regions (MSERs) algorithm is used to eliminate the background. noise and detect the direction of the barcode, and finally process the fuzzy barcode area through the adaptive manifold (Adaptive Manifold, AM) filter, the whole algorithm flow is slow due to the multi-stage processing

Others use the YOLO target detection algorithm to locate the barcode area, and then cut and scale the barcode area to a square and send it to an angle correction convolutional neural network to predict the inclination angle of the barcode. However, the features extracted by these two parts of the network have redundancy and are directly regressed. Predicted inclination angle error is too large

Images