Bill scanning image fast tilt correction method and system

A scanning image and tilt correction technology, which is applied in the field of rapid tilt correction method and system for scanned images of bills, can solve the problems that it is difficult to quickly detect whether there is tilt in the image, the amount of calculation is small, and the accuracy of tilt angle detection is reduced. Bill recognition and counterfeiting errors, small amount of data processing, and the effect of improving detection accuracy

Active Publication Date: 2019-12-03
HUNAN GREATWALL INFORMATION FINANCIAL EQUIP
View PDF12 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The method based on the Hough transform is simple in principle and easy to implement, but the amount of calculation is relatively large, and the Hough transform needs to use the foreground pixels to fit a straight line, and the fitting error is relatively large, resulting in a relatively large error in the detection of the tilt angle.
Moreover, in the financial bill system, the resolution of CIS scanning in the bill acceptance module is 300DPI, and the scanned image obtained is large. If Hough transform is used to realize the tilt correction of the bill image, it is difficult for the system to quickly detect the image due to the large bill scanned image Whether there is a phenomenon of inclination, which seriously affects the efficiency of the bill acceptance module
[0005] Although the projection method is fast and the amount of calculation is small, the scanned bill may have missing corners or damage, causing serious interference and errors, and seriously affecting the accuracy of tilt angle detection

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 scanning image fast tilt correction method and system
  • Bill scanning image fast tilt correction method and system
  • Bill scanning image fast tilt correction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0081] This embodiment provides a method for fast tilt correction of the scanned image of the bill of the bill acceptance module, such as figure 1 As shown, it specifically includes the following steps:

[0082] Step 1. Obtain the color scanned image in the scanned image of the bill, and perform the gray-scale and binarization processing in sequence to obtain the binary image.

[0083] Among them, the bill scan image is scanned by the financial bill system CIS and obtained by the bill acceptance module. The resolution is 300DPI, so the image size is relatively large. The general financial bill system CIS scan light source is white light, infrared, and ultraviolet light sources, so The bill scan image in this embodiment includes multiple images such as a color scan image, an infrared scan image, and an ultraviolet scan image.

[0084] In this step 1, the color scanned image is selected as the object to detect the inclination angle of the bill, that is, the scanned image of the bill i...

Embodiment 2

[0104] Compared with the first embodiment, this embodiment further optimizes the down-sampling process of the binary image obtained in step 1, such as image 3 As shown, including the following steps:

[0105] Step 2.1: Set the number of image pyramid layers n=4 according to the resolution of the color scanned image of the bill, and the j-th layer from bottom to top, j=0,1,2,...,3; take the binary image obtained in step 1 as The binary image of the 0th layer of the image pyramid;

[0106] Step 2.2, initialize j=0;

[0107] Step 2.3, take the binary image of the j-th layer, divide it into cells with a pixel size of 2*2, and count the number of foreground pixels in each cell with a value of 1; there is no overlap between all cells;

[0108] Step 2.4: For each cell in the binary image of the j-th layer, determine whether the number of foreground pixel values ​​of 1 is greater than the preset threshold, if so, fill all the cells with foreground pixel values ​​of 1, otherwise Fill all the...

Embodiment 3

[0113] Compared with the first embodiment, this embodiment further optimizes the tilt angle coarse inspection method and the tilt angle fine inspection method, and the tilt angle fine inspection method specifically adopts the binary search and search algorithm, which can accelerate the detection and processing speed of the tilt angle of the scanned image of the bill.

[0114] Among them, the specific process of rough inspection of tilt angle is:

[0115] Step 3.1, take 0 as the initial rotation angle and preset angle θ step Is the rough inspection step length, in the preset maximum tilt angle range [-θ max , +θ max ] To obtain different rough inspection rotation angles;

[0116] In this embodiment, since the scanned image of the bill scanned by the bill acceptance module generally has an inclination angle of ±2°, the maximum inclination angle θ is set max =2°, and set the coarse inspection step to θ step =1°, in [-θ max ,+θ max ] The value in the interval is taken as the rotation...

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 a bill scanning image fast tilt correction method and system, and the method comprises the steps: step 1, obtaining a color scanning image of a bill, and sequentially carryingout the graying and binarization processing; step 2, performing image pyramid processing on the binary image obtained in the step 1 to obtain a plurality of binary images with different resolutions; step 3, selecting a binary image on the top layer of the image pyramid as a rough detection object to perform inclination angle rough detection to obtain a rough detection inclination angle; step 4, based on the rough detection inclination angle, selecting an image pyramid non-top binary image as a fine detection object to carry out inclination angle fine detection to obtain a fine detection inclination angle; and step 5, carrying out rotation correction processing on the bill scanning image according to the fine detection inclination angle. According to the invention, while the inclination angle detection precision is ensured, the inclination angle detection speed can be accelerated, so that the method has relatively high real-time performance and detection precision.

Description

Technical field [0001] The invention relates to the technical field of image processing and machine vision, in particular to a tilt angle detection method and a tilt correction system for scanned images of financial bills, in particular to a fast tilt correction method and system for scanned images of bills. Background technique [0002] In the financial bill system, the bill acceptance module scans the bill in the early stage, and automatically aligns the scanned bill through devices such as sensors and motors to prevent the scanned image from tilting. However, in the actual scanning process of the bill acceptance module, due to the sensitivity of the alignment device, the obtained scanned image may still have a small angle of inclination, which affects the recognition and forgery of the bill image. [0003] At present, the detection of image tilt angle mainly includes the method based on Hough transform and the projection method. [0004] The method based on Hough transform is sim...

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): G06K9/32G06K9/34G06T5/00G06T7/11G06T7/13G06T7/136G06T7/194
CPCG06T5/006G06T7/11G06T7/13G06T7/136G06T7/194G06T2207/20016G06T2207/30176G06V30/1478G06V10/267
Inventor 李杰王向锋王泽平张旭东
Owner HUNAN GREATWALL INFORMATION FINANCIAL EQUIP
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