Detection and identification method for tire embossed characters

Abstract

The invention discloses a detection and identification method for tire embossed characters, and the method comprises the steps: extracting a concentric annular region-of-interest of a tire in a tire image, and unfolding the extracted concentric annular region-of-interest into a rectangular region-of-interest; inputting the rectangular region of interest into an improved Faster R-CNN model, outputting a detected imprinting character string in the tire, and finding out a DOT identifier in the detected imprinting character string; segmenting the detected and positioned DOT identifier by adopting a projection method to obtain a single embossed character; and carrying out character recognition on the segmented impressed characters one by one by adopting a convolutional neural network. Rectangular reconstruction is adopted, the inclination angle of the embossed character does not need to be calculated, and the calculation complexity is reduced; and a bilinear interpolation method and a threshold method are adopted in the Faster R-CNN model, so that the accuracy and reliability of image edge information and the accuracy of imprinting character detection are improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a detection and recognition method for tire embossed characters. Background technique [0002] With the rapid development of computers and related technologies, the application of machine vision technology in industrial automation production and other fields is becoming more and more extensive. The use of this technology in industry and other fields has greatly improved the efficiency and quality of the production process of industrial products, and brought huge economic and social benefits to the society. [0003] like figure 1 As shown, the characters on the tire are all three-dimensional characters produced by direct embossing of the mold. Compared with common optical characters such as printed characters, handwritten characters, and license plate characters, there is no color difference between the characters themselves and the background, resulting in t...

AI Technical Summary

Problems solved by technology

[0003] like figure 1 As shown, the characters on the tire are all three-dimensional characters produced by direct embossing of the mold. Compared with common optical characters such as printed characters, handwritten characters, and license plate characters, there is no color difference between the characters themselves and the background, resulting in the difference between the front and rear backgrounds. The contrast is low, so that the embossed characters will be affected by factors such as light intensity, preprocessing, detection and recognition technology, and there is a possibility that the target characters in the tire image cannot be correctly recognized

Due to the limitations of traditional machine learning algorithms, when in a complex environment, these algorithms have low positioning accuracy for the target area

Images