Dissertation > Excellent graduate degree dissertation topics show

A Study for Conventional Imaging to Computational Imaging Recognition

Author: KangJian
Tutor: WeiSui
School: Anhui University
Course: Signal and Information Processing
Keywords: Conventional recognition Computational imaging Face recognition Facial expression recognition Gender recognition Contour monitoring identificationsystem
CLC: TP391.41
Type: Master's thesis
Year: 2014
Downloads: 1
Quote: 0
Read: Download Dissertation

Abstract


Pattern recognition, which enables the computer to find the law embedded in a variety of images, data or way of thinking automatically, and take advantage of this law to model to achieve the identification and classification of the same object. It is significant to study it, because pattern recognition occupies a pivotal role in various fields, for example, biology, medicine, defense and so on.A pattern recognition system aims at classifying the input pattern into a specific class. Conventional recognition proceeds into two successive tasks:(1)the analysis(or description) that extracts the characteristics from the pattern being studied and (2)the classification(or recognition)that enables us to recognize an object(or a pattern)by using some characteristics derived from the first task. The analysis is the core of the conventional recognition. Therefore, in the first part of this paper, extracting effectively the feature of the original object space is focused. The various popular algorithms are investigated and experiments on expressional database for analyzing are conducted and their recognition rates are compared.However, it is easy to find that the above algorithm separate the imaging and pattern recognition, which measures the intermediate "object-like" representation and then conducts the post processing algorithms, and it inevitably brings a waste of resources. In the second half of this paper, the recognition based on the computational imaging paradigm is studied. The so-called "computing", which is the joint design allows us to incorporate the knowledge about the task within the imaging hardware design, and using this idea to design a new imaging system-"computational imaging". The purpose of this imaging paradigm is no longer to meet the people’s vision but to provide the robust and intelligent functions to meet the intelligent applications, which leap "from3D to information".The main work and innovation of this paper is shown as follow:1. The paper studies the popular algorithms of feature extraction and feature reduction of conventional recognition, and combine the advantage of the algorithm to compose a better recognition algorithm for expressional recognition: Gabor wavelet+local feature extraction+Kernal Discrimination Common Vector+Support Vector Machine.2. In the funding and technical support of the laboratory, in collaboration with members of the laboratory, completing a face recognition system, and participating in the contest sponsored by the Taiwanese company for three consecytive years and getting good resluts.3. The simulation experiments on face recognition, facial expression recognition and gender recognition, which is based on computational imaging. The experimental results demonstrate the effectiveness of the studied methods.4. Giving a contour monitoring identification system which is based on the idea of computational imaging.This system extracts the contour information of the target by active infrared laser and classifies based on the contour information, which reduces the waste of resource effectively,and the system has received software patent.

Related Dissertations

  1. Research on Algorithms of 2D Face Template Protection,TP391.41
  2. Research of Video Face Recognition Based on Weighted Voting and Key-Frame Extraction,TP391.41
  3. Face Recognition Method Based on DE,TP391.41
  4. Research on Face Recognition Based on Classifer Fusion,TP391.41
  5. Based on Sub-pattern Locality Preserving Projection Approaches Research for Race Recognition,TP391.41
  6. Research of Sparse Represention Based Face Recognition Algorithm,TP391.41
  7. A Novel Approach for Projection by Optimize Local Area in Face Recognition Applications,TP391.41
  8. Research on Deep Structure Learning Algorithms Based on Dynamic Fuzzy Relation,TP181
  9. The Study of 3d Face Recognition System,TP391.41
  10. 3D Face Recognition Based on Biomimetic Pattern Recognition,TP391.41
  11. Research on Robust Manifold Learning Algorithms,TP391.41
  12. The Research for Fractal Feature Extraction and Face Recognition Algorithm,TP391.41
  13. Face Recognition Research Based on Manifold Learning,TP391.41
  14. The Research for Face Recognition Based on Pseudo-Zernike Moment and BP Network,TP391.41
  15. Research on the Key Technique in Face Recognition,TP391.41
  16. Research on Face Recognition Methods Based on Flexible Neural Tree,TP391.41
  17. Pose Adjustment in Face Recognition Based on Range Image,TP391.41
  18. Face recognition based on manifold learning techniques,TP391.41
  19. Research on Face Recognition Based on AdaBoost Algorithm,TP391.41
  20. An Illumination Independence Face Recognition Algorithm Based on Gabor and SVM,TP391.41
  21. Research Onamethod for Human Face Recognition Based on MMTD,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