Dissertation > Excellent graduate degree dissertation topics show
Numeral recognition technology based on image processing
Author: DiJun
Tutor: LeiJinHui
School: Kunming University of Science and Technology
Course: Computer Software and Theory
Keywords: Character recognition License Plate Recognition Template matching BP neural network
CLC: TP391.41
Type: Master's thesis
Year: 2010
Downloads: 187
Quote: 0
Read: Download Dissertation
Abstract
|
Nearly twenty years, with the rapid development of computer vision technology , intelligent character recognition technology has been applied to more and more areas . Such as the license plate number recognition , billing identification entry , house number identification , books and scanning recognition . In the face of large amounts of data need to identify input manually is inefficient , and the error rate is high . Although the market there have been many character recognition systems , but many are only for single image information is relatively simple and standardized character recognition . But the reality is often more complex , the characters of different sizes , the presence of background noise character , the character of the tilt angle tends to affect the identification efficiency and recognition accuracy rate . This thesis focuses on this case study to design a feasible , be able to solve the license plate number recognition system in the complex case . The system through repeated experiments compare and contrast the neural network algorithm and template matching algorithm , in the case of both identify the efficiency and accuracy rate selected a practical template matching algorithm, and in the process one by one to achieve . The system includes : image preprocessing, license plate location, character recognition , the three most content . By comparing several algorithms in the feature extraction stage , the papers with a high efficiency and high recognition rate , pixel by pixel scan feature extraction method , which makes the BP network training after fast convergence . Requirements for real-time high accuracy requirements higher as well as the complexity of the environment of the network training ; seem less efficient . Therefore , when a series of practical problems encountered license plate number recognition template matching will get better recognition effect . In this thesis, the system proved by experiments for the identification of the license plate number , whether it is in Chinese characters, letters and numbers on the correct rate of more than 90% recognition speed in about 2 seconds : and complex environment has a higher adaptation can do has some practical significance .
|
Related Dissertations
- Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
- Research on Visual Servo System of Mechanical ARM,TP242.6
- Municipal tourism land use planning environmental impact assessment,X820.3
- Study on Taste Characteristic of Taste Peptide Enzymatic Production from Oyster Base on A Neural Network Method,TS254.4
- The Research on Evaluation of Living Status Systems of Expressway Relocated People,D523
- Mine Risk Information Integration and Intelligent Early Warning,X936
- Research of Orange Quality Classification Technology Based on Computer Vision,TP391.41
- Research of License Plate Recognition Based on Rough Sets and Fuzzy SVM,TP391.41
- Optimization Study on Gating System and Molding Process Parameters of Injection Mold Based on Simulation,TQ320.662
- Vehicle License Plate Recognition Algorithm Based on the PowerPC Architecture,TP391.41
- Study on Luohe Technical Supervision Bureau of Food Safety Early Warrning System Based on Neural Network,F203
- Research of Adaptive Active Noise Control Based on Neural Network,TP183
- Research and Design on License Plate Location in Complex Background,TP391.41
- Drivers' eyes open or closed state of the computer image recognition technology development,TP391.41
- Design and implementation of intelligent transportation system based on license plate recognition technology,TP391.41
- Research on Automatic Reading System for Digital Meters,TP391.41
- Research on Feature Extraction, Selection and Classification Algorithms for Pulmonary CAD,TP391.41
- The Research of Evaluation Method in Connect6 Based on BP-TD Learning,TP18
- Research on State Diagnosis on Fan Based on Factor Analysis and BP Neural Network,F426.61
- The Research and Design of Converter Steelmaking Endpoint Guiding System,TF345
- Analysis on Water Ecological Carrying Capacity of Jiangxi Province,TV213.4
CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Pattern Recognition and devices > Image recognition device
© 2012 www.DissertationTopic.Net Mobile
|