Dissertation > Excellent graduate degree dissertation topics show

Recognition of Humans Inside Video

Author: DaiYi
Tutor: XiaoGuoQiang
School: Southwestern University
Course: Computer System Architecture
Keywords: Face Recognition Gait Recognition 3D face model Face Detection Pose estimation Principal Component Analysis Optical flow field
CLC: TP391.41
Type: Master's thesis
Year: 2010
Downloads: 166
Quote: 0
Read: Download Dissertation

Abstract


In recent years, with the development of the theory of signal processing and computer, people began to ambient image with a video camera and converts it into a digital signal, the computer processing of visual information, which formed the discipline of computer vision. The image information of the image on the retina is the basis of the work of the human visual system, and therefore the development of computer vision the inevitable reference to the ability of the human visual system. One of the basic tasks of the human visual system is identify the space between people, objects and their mutual relations. Computer vision researchers also share a similar goal, that is to study the method to locate and identify targets in the scene. Locate and identify people in the field of research, because of its tremendous value, by the widespread concern. The cutting-edge technology is introduced in this paper, and describe the work of the author of the research in this field. Particular character recognition problem is divided into two parts - face recognition and gait recognition. The initial input of the recognition system for the video sequence (single image is a special case). Due to the different conditions to capture video, image resolution, there will be differences in the recognition performance. The purposes of the current technology, the accuracy of face recognition is often higher than the gait recognition, but the former is higher video resolution requirements, and be limited in the size of the area of ??each frame images of human faces. Gait recognition that the use of low-resolution data to extract motion information in various parts of the body, to achieve robust recognition effect. In other words, it is possible to make a gait recognition to achieve better performance of the video data, and its resolution is often need not meet the requirements of face recognition. Two combine to meet the needs of different environments, to solve this problem of character identification in video sequences highly value. The main research results are as follows: face recognition is a difficult field of face recognition under non-limiting conditions. This paper presents an automatic 3D face reconstruction method face pose change, automatic face annotation, the ASM model combined Candide 3D face model to complete the reconstruction of the face. Light change a bit flat-weighted integration strategy, the face image bit-plane decomposition and weighted fusion. Analysis and experimental results show that the strategy proposed in this paper for multi-angle light face recognition. The face recognition technology in the video is a research focus in recent years, with respect to the timing characteristics of face recognition based on static images, video, face recognition, and therefore more reliable recognition performance. In this paper, the video face recognition algorithm based on HMM, the continuity of the video sequence and statistical analysis of a large number of training samples to improve the robustness of the discriminant analysis method in unconstrained environment. The experiments show that this method can effectively improve the robustness of the recognition algorithm to pose and illumination changes, to improve the recognition rate. The quality of the human silhouette segmentation has a direct impact on the performance of gait recognition. This paper presents a robust gait recognition method using optical flow feature extraction motion information in the video, and the body area according to the characteristics of the human body structure is divided into multiple sub-region, the establishment of the body and then each sub-region ellipse fitting structural model. The recognition phase extraction model parameters as gait characteristics, combined with the dynamic time warping technology to solve the similarity measures and matching problem of dynamic mode. The experiments show that the algorithm can effectively improve the robustness of the recognition algorithm, and has good recognition performance.

Related Dissertations

  1. Research on Algorithms of 2D Face Template Protection,TP391.41
  2. Application of Improved Principal Component Analysis Algorithm in Course Construction,G642.4
  3. Research of Diagnosing Cucumber Diseases Based on Hyperspectral Imaging,S436.421
  4. The Impact of Tourism on Typical Vegetation in Luya Mountain Nature Reserve, Shanxi Province,S759.9
  5. Macaca mulatta palm morphological study of pattern ridge count,Q954
  6. Zhaoguan Lower Coal Group water inrush prediction and control techniques,TD745
  7. Research of Video Face Recognition Based on Weighted Voting and Key-Frame Extraction,TP391.41
  8. Face Recognition Method Based on DE,TP391.41
  9. Research on Cultural Industrial Competitiveness of Chong Qing,F224
  10. Research on Face Detection Based on Skin Color Segmentation and AdaBoost Algorithm,TP391.41
  11. Research on Face Recognition Methods Based on Flexible Neural Tree,TP391.41
  12. The Research of Prairie Road Light Environment Effects on Physiological Indicators of Drivers,U491.254
  13. Research on Face Recognition Based on AdaBoost Algorithm,TP391.41
  14. The Study of Human Face Detection Method Based on OpenCV,TP391.41
  15. Research on the Vision-Based Driver Fatigue Real-Time Detection,TP391.41
  16. Research on Feature Extraction, Selection and Classification Algorithms for Pulmonary CAD,TP391.41
  17. Research Onamethod for Human Face Recognition Based on MMTD,TP391.41
  18. Research and Implementation on Multi-angle Face Detection Technology Based on Continuous Adaboost Algorithm,TP391.41
  19. Competitiveness’ Evaluation and Development Strategy of the Tourism Industry in Huanggang City,F592.7
  20. Research on Rural Information Promoting Urban-rural Integration in Jiangsu Southern Area,F127;F224
  21. The Design of Information System of Power Equipment Current-carrying Faults Diagnosis,TP311.52

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