Bill image field positioning method and system based on location template and semantic template

A positioning system and ticket technology, applied in the field of image recognition and video analysis, can solve the problem of small ticket range

Active Publication Date: 2018-01-23
JIANGSU HONGXIN SYST INTEGRATION
View PDF9 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Patent CN201310082322 "Invoice Information Area Automatic Identification and Extraction Method and Equipment" focuses on using cascaded classifiers to c

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 image field positioning method and system based on location template and semantic template

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0049] Example one.

[0050] A method for locating bill image fields based on location templates and semantic templates, which includes the following steps:

[0051] Step 1: The field positioning system analyzes the four types of position attributes of the field in the bill image;

[0052] Step 2: The field positioning system formulates different template configuration xml files for different ticket types according to the format rules of different ticket types;

[0053] Step 3: The bill classification system analyzes the bill type of the bill image and sends the bill type to the field positioning system, and the field positioning system loads the template configuration xml file with the same bill type as the bill image;

[0054] Step 4: Obtain all field position coordinates in the bill image;

[0055] Step 5: The field positioning system configures the xml file through the template and performs positioning calculation according to the four types of position attributes to obtain the speci...

Example Embodiment

[0075] Example two.

[0076] A bill image field positioning system based on a location template and a semantic template. The system includes a field positioning system, a bill classification system and a text recognition system. The field positioning system is respectively connected to the bill classification system and the text recognition system;

[0077] The field positioning system includes:

[0078] Analysis module, used to analyze the four types of position attributes of the field in the bill image;

[0079] The production module is used to formulate different template configuration xml files for different ticket types according to the format rules of different ticket types;

[0080] The receiving module is used to receive the bill type of the bill image sent by the bill classification system;

[0081] The loading module is used to load the template configuration xml file with the same ticket type as the ticket image;

[0082] The obtaining module is used to obtain the specific posi...

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 provides a bill image field positioning method and system based on a location template and a semantic template. The method comprises the following steps: analyzing four types of locationattributes of the fields in the bill image; respectively formulating different template configuration xml files for different bill types; analyzing the bill type of the bill image through a bill sorting system, and loading the template configuration xml file with the same bill type as the bill image; positioning all field location coordinates in the bill image; performing positioning computationthrough the template configuration xml file and according to four types of location attributes, thereby acquiring the location coordinate of the field needing to recognize in the bill image, and acquiring the field local image, wherein the character recognition system recognizes the field local image as the character string by using the OCR technology. Through the method and system provided by theinvention, the specific location coordinate of the field in the bill image can be effectively acquired, a large number of data about the invoice type characteristic rule is effectively saved, and more data support is provided for the invoice character positioning and character recognition.

Description

technical field [0001] The invention belongs to the fields of image recognition and video analysis, and in particular relates to a bill image field positioning method and system based on a position template and a semantic template. Background technique [0002] Various commercial activities in modern society widely use various bills. Although electronic payments and electronic bills are increasing, traditional paper bills are still widely used, such as various paper invoices and financial bills. At present, the financial department has a large number of invoice images every day on average, and employees in multiple positions need to repeatedly audit the same invoice, which not only consumes manpower, but also reduces the efficiency of reimbursement. Realize the extraction of bill information through image OCR technology, compare the extracted face information with the reimbursement information, and realize automatic audit; the bill information extracted by OCR is stored in t...

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): G06K9/00G06K9/32
Inventor 车少帅于志文胡笳
Owner JIANGSU HONGXIN SYST INTEGRATION
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