Banknote detection and recognition method in complex environment based on rgb-d camera
A technology of complex environment and identification method, which is applied in the field of judging whether there are banknotes in the complex environment and the denomination of the output banknotes when they exist, to achieve the effects of convenient use, high speed and improved speed
Active Publication Date: 2018-05-22
ZHEJIANG UNIV
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] In order to solve the urgent banknote recognition problem for visually impaired people, the present invention provides a banknote detection and recognition method based on an RGB-D camera in a complex environment
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0038] like figure 1 As shown, the present invention is based on the RGB-D camera-based banknote detection and identification method in a complex environment, comprising the following steps:
[0039] 1. Before the image to be tested is processed, the data of the seven banknotes is obtained. This step is realized through the following sub-steps:
[0040] 1.1. Put the front of the 1-yuan banknote into the field of view of the RGB-D camera, and move the banknote from near to far according to the shortest distance of the normal hand-held banknote until the arm is straight, at this time the longest distance (the distance here The distance is relative to the plane of the RGB-D camera on the frame); then put the reverse side of the 1-yuan banknote into the field of view of the RGB-D camera, and move the banknote from near to far until it reaches the farthest distance. Ensure that the front and back of the banknote are within the shortest distance and the farthest distance. A total o...
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
Login to View More Abstract
The invention discloses a method for detecting and recognizing a bill under complex environments based on an RGB-D camera. In the method, an RGB-D camera is used for segmenting a bill, an RGB color space of a bill region is converted into an HIS color space after image pre-processing, chrominance components are used for initial determination, then an SURF algorithm is used for extracting feature points and matching with a reference region template, and a result is outputted by comparison with a threshold according to the matched feature points. The method is dedicated for the blind to detect and recognize the bill under complex environments, and has the functions of detecting no bill in the field of view in the absence of a bill and outputting the value of the bill in the presence of the bill. The method can be implemented with no special requirements for the blind, is operated as normal people do, meanwhile fully considers interference factors that may be encountered in a variety of actual environments, and has the advantages of high speed, high accuracy, good robustness and so forth.
Description
technical field [0001] The invention relates to the technical fields of scene acquisition, object recognition, and assistance for visually impaired people, in particular to a method for collecting video images by using an RGB-D camera, judging whether there are banknotes in a complex environment and outputting the face value of the banknotes when they exist. Background technique [0002] Vision is the sense that humans rely on most. Through vision, humans obtain at least 80% of the external information, and obtain various information that is of great significance to the survival of the organism. However, there are about 450,000 people with new visual impairment and 1.35 million people with low vision in China every year, that is, about 1 total blind patient and 3 low vision patients every minute. According to the latest statistics in 2013, there are about 13.5 million disabled people with visual impairment in China, while the World Health Organization estimates that there a...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G07D7/20
CPCG07D7/2016
Inventor 汪凯巍张豫杨恺伦
Owner ZHEJIANG UNIV