Bill feature region extraction method, apparatus and device and storage medium

A feature area and extraction method technology, applied in the field of image processing, can solve the problems of high time consumption and low efficiency, and achieve the effect of avoiding the steps of correction, improving the determination speed, and reducing the amount of data processing

Inactive Publication Date: 2018-09-14
SHENZHEN YIHUA COMP +2
View PDF2 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the image of the ticket obtained by the ticket inspection machine and other equipment is usually a distorted image. In the prior art, the following method can be used to extract the feature area: firstly, the distorted image is corrected, and then the straight line is detected by Hough transform. To extract the feature area, and finally identify the information in the feature area, but the above method in the prior art consumes a lot of time and has low efficiency

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
  • Bill feature region extraction method, apparatus and device and storage medium
  • Bill feature region extraction method, apparatus and device and storage medium
  • Bill feature region extraction method, apparatus and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] Figure 1a It is a flow chart of a method for extracting feature regions of bills provided in Embodiment 1 of the present invention. The method is executed by a device for extracting feature regions of bills. The device can be executed by software and / or hardware, and the device can be configured In equipment such as ticket checking machines.

[0028] The feature region extraction method provided by the embodiment of the present invention can be applied in the scene where the acquired bill image is a distorted image, such as Figure 1a As shown, the technical solutions provided by the embodiments of the present invention are as follows:

[0029] S110: Acquire the image of the bill.

[0030] In this step, the bill can be an invoice, a receipt, etc., and the image of the bill can be a grayscale image.

[0031] S120: When the image is identified as a distorted image, determine boundary points of the bill in the image.

[0032] In one embodiment of the present invention, ...

Embodiment 2

[0045] Figure 2a It is a flow chart of a bill feature area extraction method provided in Embodiment 2 of the present invention. In this embodiment, the "line fitting according to the boundary points" is refined, as shown in Figure 2a As shown, the technical solutions provided by the embodiments of the present invention include:

[0046] S210: Acquire the image of the bill.

[0047] S220: When the image is identified as a distorted image, determine boundary points of the bill in the image.

[0048] S230: Segment the boundary points.

[0049] Among them, the specific segmentation can be determined according to the actual situation. For example, for the upper boundary, the lower boundary or the boundary in the similar direction, the segmentation can be carried out according to the X coordinate value; for the left boundary, the right boundary or the boundary in the similar direction, it can be divided according to the Y Coordinate values ​​are segmented. Wherein, the X coord...

Embodiment 3

[0073] image 3 It is a structural block diagram of a bill feature area extraction device provided by an embodiment of the present invention, as shown in image 3 As shown, the device includes an image acquisition module 310 , a boundary point determination module 320 , a boundary line determination module 330 and a feature area determination module 340 .

[0074] Wherein, the image acquisition module 310 is used to acquire the image of the bill;

[0075] A boundary point determining module 320, configured to determine the boundary point of the bill in the image when the image is identified as a distorted image;

[0076] A boundary line determining module 330, configured to perform straight line fitting according to the boundary points to determine the boundary line of the note;

[0077] A feature area determining module 340, configured to determine the feature area of ​​the note according to the boundary line of the note.

[0078] Further, the linear fitting of the boundar...

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 embodiment of the invention discloses a bill feature region extraction method, apparatus and device and a storage medium. The method comprises the steps of: obtaining images of a bill; when the images are identified to distortion images, determining boundary points of the bill in the images; performing linear fitting of the boundary points according to the least square method, and determiningthe boundary lines of the bill; and determining the feature regions of the bill according to the boundary lines of the bill. The bill feature region extraction method, apparatus and device and the storage medium can improve the determination speed of the feature regions and can achieve rapid and accurate identification of character information in the distortion images.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of image processing, and in particular, to a method, device, device, and storage medium for extracting feature regions of bills. Background technique [0002] With the rapid development of artificial intelligence, the intelligence of the financial field is becoming more and more important. For example, the rapid classification processing and classification processing of checks and invoices are important aspects of financial intelligence. The feature area extraction of bills is a method of classifying and processing checks according to the information in the bills. [0003] At present, the image of the ticket obtained by the ticket inspection machine and other equipment is usually a distorted image. In the prior art, the following method can be used to extract the feature area: firstly, the distorted image is corrected, and then the straight line is detected by Hough transform. To extra...

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): G06K9/46
CPCG06V10/462
Inventor 石鸥傅博扬
Owner SHENZHEN YIHUA COMP
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