A method for detect and correcting bill direction and an automatic ticket checking system

A technology of direction detection and bills, applied in the direction of instruments, character and pattern recognition, computer parts, etc., to achieve the effect of high recognition accuracy, accurate results, and extended angle range

Active Publication Date: 2019-03-08
BEIFANG UNIV OF NATITIES
View PDF6 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the adverse effects of the inconsistency of the direction of the photographed bill images on the efficiency and accuracy of ticket checking in the existing bill face automatic recognition system, and to provide a bill direction detection based on the characteristic area clustering algorithm and Radon transform Correction method to ensure the consistency of the direction of the bill image in the bill face automatic recognition system

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
  • A method for detect and correcting bill direction and an automatic ticket checking system
  • A method for detect and correcting bill direction and an automatic ticket checking system
  • A method for detect and correcting bill direction and an automatic ticket checking system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] see figure 1 In this embodiment, a bill direction detection and correction method is provided, which mainly involves a feature area clustering algorithm and a Radon transformation algorithm, and the specific steps are as follows:

[0047] Step 1: Perform grayscale processing on the collected bill image to obtain a grayscale image.

[0048] Usually, the relationship between white and black is divided into several levels according to the logarithmic relationship, which is called gray scale. It is called a grayscale image, which means that each pixel has only one sampled color on the image. Grayscale processing of any image is a very mature existing technology, so I won’t go into details here.

[0049] Step 2: Segment the grayscale image by using a feature region clustering algorithm, and highlight information regions on the bill by setting a grayscale threshold.

[0050] The information area is the face of the bill. For the highlighting and extraction of the information...

Embodiment 2

[0093] This embodiment 2 adopts the bill direction detection and correction method in embodiment 1, and carries out direction detection and correction to the train ticket image collected after tilting 120 degrees, in order to verify the feasibility and effect of the method described in embodiment 1, The specific process is as follows:

[0094] (1) Perform grayscale processing on the collected bill image to obtain a grayscale image, such as Figure 4 as shown in (A);

[0095] (2) Using the 3-means clustering algorithm to perform image segmentation on the grayscale image, that is, in the first step of the K-means clustering algorithm, 3 pixels are set as the initial center points of the clustering, so that the K-means clustering algorithm can be used Carry out 3-mean clustering on the train ticket image, so that all pixels on the train ticket image can be clustered into three gray levels, that is, in the collected train ticket image, the background of the ticket (that is, the b...

Embodiment 3

[0101] Present embodiment 3 adopts the method of embodiment 1 or embodiment 2, in plane Cartesian coordinate system, the train ticket image of 60 °, 120 °, 210 ° and 330 ° in four quadrants is carried out inclination angle test, and the result presented, respectively, as Figure 5 , Figure 6 , Figure 7 ,as well as Figure 8 As shown, it can be seen that the actual inclination angle of the train ticket image is highly consistent with the inclination angle of the monitored train ticket image. It can be seen that the bill direction detection and correction method provided by the present invention can be accurately for all angles (in the range of 0 to 360 degrees), Orientation detection for train ticket images in any orientation.

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

A method for detect and correcting bill direction and an automatic ticket checking system are provided, wherein the method for detect and correcting bill direction adopts a feature region clustering algorithm and a Radon transform to detect and correct the bill direction, realizes the efficient detection process and the accurate result, and can not only detect and rectify the direction of all-angle (0-3600) bill images, but also eliminate the interference of the complex background of the image itself and the pixel points in the neighborhood of the direction characteristic region to the direction detection, which is beneficial to the positioning and cutting of the information region in the ticket surface automatic recognition system, and has strong practicability and wide applicability.

Description

technical field [0001] The invention relates to the technical field of automatic ticket checking, in particular to a bill direction detection and correction method and an automatic ticket checking system. Background technique [0002] The automatic detection system of paper bills is widely used in railway stations, high-speed rail stations, movie theaters and other related fields; however, during automatic ticket checking, there is usually a certain deviation in the direction of the bill, which is not conducive to the recognition efficiency and accuracy of the automatic ticket checking system; For example, for a railway station with a relatively large flow of people, an automatic ticket checking system (that is, an automatic ticket recognition system) is usually installed. The direction of the train ticket image captured by the system is inconsistent. This inconsistent image will have a negative impact on the recognition efficiency and accuracy of the train ticket, which gre...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/32G06K9/34G06K9/46G06K9/62
CPCG06V10/242G06V10/25G06V10/267G06V10/462G06F18/23213
Inventor 韦海成许亚杰李云琴肖明霞
Owner BEIFANG UNIV OF NATITIES
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap