A method and equipment for improving a user-defined template recognition rate based on image normalization

A normalized and customized technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of not being able to cut out the recognition area, offset the position of the bill content, and inaccurate frames, etc., to improve the recognition effect , Calculation speed is fast, and the effect of ensuring accuracy

Pending Publication Date: 2019-04-02
厦门商集网络科技有限责任公司
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, the angle, height, and camera parameters are different when taking a mobile photo, which will cause the position of the photo to be shifted.
If the position is offset, if the fixed template is used, there will be problems such as inaccurate frame and incomplete frame, and then the correct recognition area will not be cropped.

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 and equipment for improving a user-defined template recognition rate based on image normalization
  • A method and equipment for improving a user-defined template recognition rate based on image normalization
  • A method and equipment for improving a user-defined template recognition rate based on image normalization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] see figure 2 , a method for improving the recognition rate of a custom template based on image normalization, comprising the following steps:

[0047] Obtain the picture to be recognized and create a template picture; the picture to be recognized is a bill image that needs to be automatically recognized, such as Figure 4 As shown in , the template image is the bill image generated by the bill template, such as image 3 shown;

[0048] Extract all the fixed regions in the template map to regenerate a template feature map, such as Figure 5 shown;

[0049] When performing surf feature detection, you can first convert the recognition map and template feature map to grayscale and Gaussian smoothing to reduce noise or distortion on the image;

[0050] Perform surf feature detection on the image to be recognized and the template feature image, identify and record each feature point, including surf feature information and coordinate information of the feature point;

[...

Embodiment 2

[0061] see figure 2 , a device for improving the recognition rate of a custom template based on image normalization, including a memory and a processor, the memory stores instructions, and the instructions are adapted to be loaded by the processor and perform the following steps: obtaining the image to be recognized and Create a template graph such as image 3 with Figure 4 shown;

[0062] Extract all the fixed regions in the template map to regenerate a template feature map, such as Figure 5 shown;

[0063] When performing surf feature detection, you can first convert the recognition map and template feature map to grayscale and Gaussian smoothing to reduce noise or distortion on the image;

[0064] Perform surf feature detection on the image to be recognized and the template feature map, identify and record each feature point, including the surf feature information and coordinate information of the feature point; the extraction of surf feature points is based on the s...

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 relates to a method for improving a user-defined template recognition rate based on image normalization. The method comprises the following steps: obtaining a to-be-recognized image andcreating a template image; regenerating a template feature map by using all the fixed areas in the template map; performing surf feature detection on the to-be-identified image and the template feature image, and identifying and recording each feature point; carrying out feature matching on the feature points of the to-be-identified image and the feature points in the template feature image, and recording coordinates of the successfully matched feature points; selecting at least four feature point groups, and calculating a perspective transformation matrix by utilizing a perspective transformation formula; and calculating a pixel value of each transformed pixel point in the to-be-identified image by using the perspective transformation matrix so as to obtain a perspective transformation image. According to the method, the corresponding feature points on the to-be-identified image and the template image are extracted, the perspective transformation matrix is calculated, the transformedpixel value of each pixel point in the to-be-identified image is calculated by using the perspective transformation matrix, and thus the perspective transformation image is obtained.

Description

technical field [0001] The invention relates to a method and equipment for improving the recognition rate of a self-defined template based on image normalization, and belongs to the field of automatic bill recognition. Background technique [0002] For notes typesetting in a fixed format, the printed paper notes will also have a fixed format, please refer to figure 1 , such as special value-added tax invoices, all have fixed areas such as "buyer", "password area", "seller", and "remarks". Therefore, bills also have overprinting areas that need to be identified, and these overprinting areas also have relatively fixed positions. [0003] Using template automatic recognition is to design a set of reusable templates based on a bill with a fixed format. This template includes the position and width and height of each area that needs to be recognized in a specific mark. According to the position in the template, the electronic version of the bill obtained after scanning or shoot...

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): G06K9/00G06K9/46
CPCG06V30/412G06V30/414G06V10/443
Inventor 吴建杭陈文传杜保发周文贵
Owner 厦门商集网络科技有限责任公司
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