Plate number character recognition method based on multi-feature fusion
A multi-feature fusion and character recognition technology, applied in the field of license plate character recognition, can solve problems such as poor real-time performance, complex calculation, and insufficient theoretical basis, and achieve the effect of reducing empirical components, improving effects, and sufficient feature extraction theory.
Active Publication Date: 2015-01-21
TONGJI UNIV
View PDF4 Cites 18 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The template matching method has the disadvantages of complex calculation and relatively poor real-time performance.
In the pattern recognition method, the feature extraction includes half-projection, coarse grid and other pixel ratio features, including invariant moments, texture features such as gray level co-occurrence matrix, including edge information features such as HOG, SIFT, EOH, etc. The selection process of these features They are all artificially designed, with a lot of empirical elements, and the theoretical basis is not very sufficient
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
[0037] Below in conjunction with accompanying drawing, technical solution of the present invention will be further described:
[0038] Principle: The present invention extracts a method based on multi-feature fusion to effectively recognize license plate characters in real-time video. The high-order feature descriptors of the underlying pixels of the license plate character image mined through the deep belief network are added to the traditional artificially designed features, and the license plate character classifier is constructed by using the support vector machine to train the fusion features.
[0039] The license plate character recognition method based on multi-feature fusion in the present invention: the extracted license plate character feature is based on the traditional features by adding high-order features excavated from the bottom layer pixels of the license plate character picture, and the globality of traditional features is preserved through feature fusion , a...
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 relates to a plate number character recognition method based on multi-feature fusion. The method comprises the steps that (1), vehicles in a video are detected, and plate numbers in the vehicles are located and segmented; (2), projection analysis is carried out on the segmented plate numbers, and seven effective characters in each plate number are segmented and extracted; (3), morphological processing is carried out on segmented character pictures, and three features of the plate number characters are extracted and effectively fused; (4), a support vector machine is utilized for training the fusion features to generate a plate number character classifier, and therefore the plate number characters in the real-time video can be effectively recognized. Compared with the prior art, the experience components of the extracted plate number character features can be reduced, the basis of the feature extraction theory can be more sufficient, and therefore the effect of recognizing the plate numbers can be improved.
Description
technical field [0001] The invention relates to a license plate character recognition method, in particular to a license plate character recognition method based on multi-feature fusion. Background technique [0002] Nowadays, cars have become an indispensable means of transportation in people's work and life. Due to the increase in the number of cars, the current traffic situation in the city is not optimistic. From this point of view, the application of Intelligent Transportation System (ITS: Intelligent Transportation System) is imminent. The license plate is the unique information of a car, therefore, the recognition technology of the vehicle license plate can be used as the most effective method to identify a car. Fundamentally, license plate recognition applies advanced image processing, pattern recognition, and artificial intelligence techniques to acquire, process, interpret, and record photographed images. At present, license plate recognition technology has been...
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 Applications(China)
IPC IPC(8): G06K9/66G06K9/46G06T7/00
CPCG06V20/62G06V30/153G06V10/50G06V20/625
Inventor 蒋昌俊陈闳中闫春钢张亚英刘春梅钱华
Owner TONGJI UNIV