Unlock instant, AI-driven research and patent intelligence for your innovation.

Tire text detection and recognition method

A recognition method and text detection technology, applied in character and pattern recognition, character recognition, instruments, etc., can solve the problems of high cost, low detection efficiency, high false detection rate, etc., and achieve the effect of improving accuracy

Active Publication Date: 2021-06-01
ZHEJIANG HAOTENG ELECTRONICS POLYTRON TECH INC
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It uses the circular curve fitting algorithm as the basis, uses the TPS interpolation algorithm to correct the image, and uses the text recognition model in the corrected image to identify the text part, which is used to solve the low detection efficiency and false detection in the existing technology. High rate, high cost and other issues

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Tire text detection and recognition method
  • Tire text detection and recognition method
  • Tire text detection and recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be described in detail below in conjunction with the examples and pictures.

[0040] A tire text detection and recognition method, the specific steps are as follows:

[0041] Step 1: Detect the text on the side of the tire through the deep neural network, and record the result as R={r k |k=1,2,…,K}, define a group of characters whose distribution is adjacent as a combined character cluster, in R, r k Indicates the minimum circumscribed rectangular bounding box of the kth combined character cluster detected, and K represents the number of detected combined character clusters; figure 1 In (a), the same combined character cluster is represented by a dotted rectangular box;

[0042] Step 2: Define the set C={p k =(x k ,y k )|k=1,2,…,K}, among them, p k for r k center point of figure 1 In (a), each point in the set C is represented by a solid point; the coordinates in the set C are substituted into the formula (1), and the circular curve e...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an annular tire text detection and recognition method, which uses a circular curve fitting algorithm as a basis, uses a TPS interpolation algorithm to correct an image, uses a character recognition model in the corrected image to recognize a character part in the corrected image, and is used for solving the problems of low detection efficiency, high false detection rate, high cost and the like in the prior art.

Description

technical field [0001] The invention relates to the fields of image processing and scene text detection and recognition, in particular to a tire text detection and recognition method based on circular curve fitting and image correction. Background technique [0002] The text engraved on the side of the tire contains information such as the tire brand, manufacturer, production time, service life, and maximum load capacity. For vehicle users, especially vehicle operators and traffic regulators, this information is crucial. In road traffic, there are often violations such as tires equipped with vehicles exceeding the service life, vehicle load exceeding the maximum load capacity of tires, and vehicles using unqualified tires. These violations have brought great hidden dangers to traffic safety. Therefore, it is of great significance to design a method that can automatically detect and identify texts containing unique information on tires. [0003] For the detection and recogn...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/32G06K9/34G06N3/04
CPCG06V20/62G06V30/153G06V30/10G06N3/045
Inventor 刘远超吴宗林黄俊俊姜世强陈钦鸿
Owner ZHEJIANG HAOTENG ELECTRONICS POLYTRON TECH INC