Dissertation > Excellent graduate degree dissertation topics show

Study on the Character Image Recognition System Based on Virtual Instrumentation

Author: ChengHao
Tutor: QianDongPing
School: Agricultural University of Hebei
Course: Agricultural Mechanization Engineering
Keywords: Virtual instrument Character Recognition Template matching BP neural network IMAQ Vision Image processing
CLC: TP391.41
Type: Master's thesis
Year: 2006
Downloads: 310
Quote: 4
Read: Download Dissertation

Abstract


Countries in the world with the arrival of the information age and the popularity of computer applications, the development of the information industry have given a great deal of attention and concern. But while high-speed development of information technology, a problem also placed in front of us, and that is the contradiction between the computer data processing and network transmission of high-speed and low-speed data input. Text image on paper a lot of information quickly and reliably entered into the computer, how to record and character information into easy computer to identify and deal with, to some extent, become important factors affect the process of social information. People accept the most frequent visual channel. In the day-to-day learning and life, 75% -85% of the information processing of visual information, text information increasingly important position. To achieve the mechanization and automation of these text information processing, a prerequisite is the use of the computer to identify the text message. This study is a character image is recognized by the computer problems. The character is based on the different ways to write into printed characters and handwritten characters. System for each character, characters pretreatment, extraction characteristics of the characters themselves, and then use the specific identification algorithms, automatic identification of the character image. The entire system, including the four parts of the image acquisition, preprocessing, feature extraction and character recognition. Image acquisition hardware including clocked at 2.8GHZ, 512MB of memory Lenovo Kai-day M6200 computer, the the NI company's PCI-1411 image acquisition card and a homemade image acquisition box. Black background design collection box, built-in Panasonic WV-CP240 / G color camera as the input sensor, 40W ring light as lighting equipment to ensure the quality of the image acquisition. The images will be collected by the gradation conversion and the binarization processing, noise removal, image enhancement, characterized in positioning, edge extraction, the pretreatment process of the character segmentation, etc., forming a prominent feature, to facilitate the subsequent processing and the identification of a single character image. Feature location process, design feature location algorithm based on the detection tested coupon two adjacent right-angled edge position to establish relative coordinate system to determine the position of the characters in this coordinate system. According to the needs of the printed and handwritten character recognition, the system takes a different feature extraction strategies. Normalized and refined processing of characters printed characters, using the combined method of the grid characteristics and crosspoint features as a character feature, character standard repository. Handwritten character design combined feature extraction algorithm based on boundary characteristics and holes, stroke characteristics, the character feature extraction. The printed characters using a template matching algorithm to achieve character recognition, the recognition character to be compared to the character standard feature database, the minimum Euclidean distance to be identified as its feature vector of the character recognition feature vectors represent the standard characters. For handwritten characters, the system uses the BP neural network to achieve the recognition of the character. The IMAQ Vision development system software package by NI virtual instrument software the Labview and image processing tools, image acquisition, preprocessing, feature extraction, and character recognition and other functions. The software is simple, friendly interface and high reliability. The experiment showed that the printed character recognition accuracy rate was 95.5%, handwritten character recognition accuracy rate of 90.3%.

Related Dissertations

  1. Research on Temperature Measurement Technique Based on CCD Image Sensor,TH811
  2. Study of Automobile Ignition Coil Testing System Based on Standard LAH032.905,U472.9
  3. Research on Basic Algorithms of Digital Image Processing and Implementation with FPGA,TP391.41
  4. Research of Images Enhancing Algorithms on Fog or Backlighting Conditions and Implementation with Hardwares,TP391.41
  5. Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
  6. Research on the Image Real-Time Acquisition, Storage and Image Processing System,TP391.41
  7. The Research of Moving Object Tracking System Based on Embeded Image Process Unit,TP391.41
  8. Research on Visual Servo System of Mechanical ARM,TP242.6
  9. Application Research of Digital Image Processing on Container Inspection,TP274.4
  10. Municipal tourism land use planning environmental impact assessment,X820.3
  11. Three-Dimensional Numerical Modelling for the Head and the Electric Field Analysis of DBS,R742.5
  12. Application of Semi-Structure in Leisure Dress,TS941.2
  13. Study on Taste Characteristic of Taste Peptide Enzymatic Production from Oyster Base on A Neural Network Method,TS254.4
  14. Research on Nondestructive Detection Technology for External Qualities of Papayas Based-on Vision,S667.9
  15. Research on Detecting Optical Fiber Geometric Parameter Based on Machine Vision,TN253
  16. Research on Identification System of Cashmere and Wool Fiber,TS101.921
  17. Development of Tractor’s Virtual Instrument System Based on CAN Bus,S219.02
  18. Design of Garlic Planting Sorting Machine Based on Image Processing,S223.2
  19. Study on Detection and Grading of ’Jiro’ Persimmon’s External Quality Based on Computer Vision,S665.2
  20. The Research on Evaluation of Living Status Systems of Expressway Relocated People,D523
  21. Flow Behavior Description of Two-Phase Flow Based on Image Processing Techniques,TP391.41

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