Character recognition method of sparse coding license plate based on shape contour feature
A technology of sparse coding and contour features, which is applied in the field of sparse coding license plate character recognition, can solve the problem of low character recognition accuracy, achieve high-efficiency classification characteristics, improve recognition effect, and enhance the effect of discrimination
Inactive Publication Date: 2016-04-06
XIAN UNIV OF TECH
View PDF5 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] The purpose of the present invention is to provide a sparsely coded license plate character recognition method based on shape contour features, which solves the problem of low character recognition accuracy in the prior art
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
[0048] The specific embodiments of the present invention will be further described in detail below in conjunction with the accompanying drawings. Sparse coded license plate character recognition method based on shape contour features, such as figure 1 As shown, it consists of the learning process of the sparse dictionary (above the dotted line) and the recognition process of the sparse dictionary (below the dotted line).
[0049] 1. The learning process of the sparse dictionary specifically includes the following steps:
[0050] (1) Preprocessing the license plate image of the training sample to obtain the training character image set;
[0051] In order to consider the differences caused by factors such as license plate clarity, cleanliness, new and old background colors, and lighting background, ensure that enough training sample license plate pictures are collected, so that the number of each character in the training process is at least 100. License plate image preprocess...
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 present invention provides a sparsely coded license plate character recognition method based on shape and contour features, which is composed of a sparse dictionary learning process and a character recognition process using the dictionary, and mainly includes the following steps: 1. Preprocessing the standard license plate image to form a training image 2. Extract features from the training image set to form a training feature set; 3. Introduce the sample area features and chain code histogram features of the training feature set into the objective function, and conduct sparse dictionary learning on the license plate character samples offline to obtain each character The corresponding dictionaries form a dictionary set; 4. Extract features from the test sample data; 5. Sparsely represent the test sample features on each dictionary, and use the reconstruction error to perform license plate character recognition. The invention considers both the region feature and the boundary feature of the character image, and is a fast and robust license plate character recognition method.
Description
technical field [0001] The invention belongs to the technical field of image processing and intelligent transportation, and in particular relates to a sparsely coded license plate character recognition method based on shape and contour features. Background technique [0002] License plate recognition is an important link in the intelligent transportation system (Intelligent Transportation System, ITS), which can be widely used in intersection monitoring, parking lot monitoring and management, highway toll collection and other occasions. License plate recognition consists of license plate location, license plate tilt correction, character segmentation and character recognition. License plate character recognition is an important factor affecting the system recognition rate based on the completion of the previous parts. [0003] Due to the low resolution of the character dot matrix in the license plate, the low resolution will lead to the loss of character feature information...
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): G06K9/62
Inventor 赵凡廖开阳曲方莹张二虎
Owner XIAN UNIV OF TECH