Dissertation > Excellent graduate degree dissertation topics show

Handwritten numeral recognition and classification based on artificial neural network

Author: YangLiLi
Tutor: BaiYanPing
School: University of North
Course: Applied Mathematics
Keywords: Pattern recognition Classifier Handwritten numerals Neural Network Principal Component Analysis
CLC: TP183
Type: Master's thesis
Year: 2012
Downloads: 125
Quote: 0
Read: Download Dissertation

Abstract


With the rapid development of science and technology, the processing speed of computeris more and more quickly, using a computer to solve real-life problems is a hot spot ofresearch direction.The handwritten number recognition technology have important theoreticalsignificance and broad prospect of application both in scientific research or in daily life, is themore important research direction of pattern recognition and classification. The handwrittennumber recognition technology involved in many classic problems of the pattern recognitionand classification,such as the feature extraction, classifier design and the choice of samples,and so on, how to improve the accuracy and efficiency is also the scientific research goal ofthe scholars.With the capabilities of parallel computing,fault tolerance,self-learning and classificationand identification, Artificial Neural Network is paid full attention and used in the field ofpattern recognition.In the article, Classifier design adopts the artificial neural networkalgorithm, identification system is established. The learning samples are firstly preprocessedincluding Noise removing, binarization, thinning,and the normalized and so on. Secondly itspixel features are extracted,and the principal component analysis method was adopted toreduce the number of dimensions for saving the time of the training sample.Finally throughthe classifier deal with numerical attributes of the extracted characteristics of sample andclassify to recognise what it is.In the article, Neural network classification and recognitionsystem is established by means of the artificial neural network algorithm,.such as the BPneural network, RBF neural network, probabilistic neural network and so on and eachclassifier’s recognition effect was maked a detailed comparison and analysis.Finally,the paper concluded were related,and proposes future research priorities anddirections.

Related Dissertations

  1. Development of the Platform for Compressor Optimization Design and Aerodynamic Optimization Design in the Transonic Compressor,TH45
  2. The Classification of High Dimsnsion Flew Field Based on Manifold Learning,V231.3
  3. ISAR Imaging Simulation of Space Targets and Target Recognition Based on ISAR Images,TN957.52
  4. Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
  5. Study on Virtual Detector of Infrared Hyper-Spectral Image,TP391.41
  6. Research on Text Classification Based on Biomimetic Pattern Recongnition,TP391.1
  7. The Application of Fuzzy Control and Neural Network in Planar Double Inverted Pendulum,TP273.4
  8. Research of Visual Servoing in 4-DOF Robotic Manipulator,TP242.6
  9. Research on Visual Servo System of Mechanical ARM,TP242.6
  10. Design of Weapon Detection Device Control System,TP183
  11. Municipal tourism land use planning environmental impact assessment,X820.3
  12. Research on the Inteligent System of High Performance Concrete Mix Design in Zhujiang Triangle Area,TU528
  13. Application of Improved Principal Component Analysis Algorithm in Course Construction,G642.4
  14. Study on Taste Characteristic of Taste Peptide Enzymatic Production from Oyster Base on A Neural Network Method,TS254.4
  15. Smart Control Research in Paddy Drying Based on BP Neural Network,S226.6
  16. BP network optimization based on genetic algorithm optimization of the biodiesel process,TE667
  17. Research on Identification System of Cashmere and Wool Fiber,TS101.921
  18. Fire Fighting System Research for the Offshore Platform,U698.4
  19. Intrusion detection based on the ultrasonic echo envelope in the military security patrols,E919
  20. The Research on Evaluation of Living Status Systems of Expressway Relocated People,D523
  21. Research on Inspection Technology of Dehydrated Garlic Slice Based on Computer Vision,TP391.41

CLC: > Industrial Technology > Automation technology,computer technology > Automated basic theory > Artificial intelligence theory > Artificial Neural Networks and Computing
© 2012 www.DissertationTopic.Net  Mobile