Dissertation > Excellent graduate degree dissertation topics show

Relevant Algorithms for General Object Recognition Based on Feature Combination

Author: TianYuanDong
Tutor: ZhangLiQing
School: Shanghai Jiaotong University
Course: Computer Software and Theory
Keywords: Feature Combination Object Recognition HMAX model Machine Vi-sion Vision Model
CLC: TP391.4
Type: Master's thesis
Year: 2007
Downloads: 391
Quote: 4
Read: Download Dissertation

Abstract


General Object Recognition (GOR) is a basic but hard problem in Vision. Althoughthere exist a number of working algorithms and systems for specific purpose recognition task(e.g., Face Detection & Recognition), to develop a general-purpose recognition algorithmand system with human-level performance, is still challenging.Vision Research is interdisciplinary, covering a variety of fields from Computer Visionto Neurobiology. This paper firstly makes a survey on recent achievements of GOR, with anemphasis on modeling techniques and computational approaches in the regime of ComputerVision. In addition, one primary approach for GOR, the patch-based method, is furtherstudied.Then the famous biologically plausible HMAX model is elaborated and analyzed inthis thesis. The hierarchical structures of HMAX is fully decomposed and its functionalcounterpart in Computer Vision is clearly revealed. Based on the insights, two novel localimprovement strategies are developed and the experiment results show that both are indeedpractical.The main contributions of this thesis are as follows:1) This paper provides an elaborate description on computational feasible HMAX model.Four-layered structures (S1,C1,S2,C2) of HMAX model are under close scrutiny. Asa result, its functional relation to the counterparts in Computer Vision is revealed:“blocky histogram”(S1+C1) by“histogram”(S2+C2). Due to this analysis, HMAXmodel can be called a supervised“one layer and a half”model in term of featurecombination, if we take one stage of“blocky histogram”extraction as one layer. 2) Some tentative improvement strategies are developed in local operations of HMAXmodel. Different from regular strategies that focus purely on machine learning, in thispaper two novel vision-based approaches are proposed: a) A Non-uniform partition onblocky histogram in contrast with fixed 8×8 partitions in HMAX, and b) A globalscheme to find common parts of multiple images, in contrast with local and random-ized patch-picking in HMAX.3) Practical modeling and solutions of both proposed strategies are given. For a), its 1-Dand 2-D case are analyzed respectively. For 1-D case(’signal case’), it can be solvedexactly and efficiently via Dynamic Programming, while for 2-D case (“image case”),no exact solution is available. Instead, coordinate descent is adopted to get a quitereasonable approximation. For b), a generative model is proposed and standard EMiterations are used to get locally best solutions of the problem. For both strategies,experiments are conducted. The experiment results prove that both ideas lead to betterperformance and thus are applicable.4) This paper constructs a patch-based interactive platform for GOR. It is designed tofacilitate algorithm debugging in Computer Vision. On this platform, users can see theresult of feature extraction and the running process of algorithms. They can dynami-cally adjust parameters as well. Besides, this platform also has some novel character-istics on software architectures.

Related Dissertations

  1. Research on Intelligent Learning-Based Multi-Sensor Target Recognition and Tracking System,TP391.41
  2. Camera Calibration and Position and Pose Detecting on Vision Measurement System of PCB,TP391.41
  3. Aerial Target Anti-interference Recognition and Tracking System,TN215
  4. Research on Detecting Optical Fiber Geometric Parameter Based on Machine Vision,TN253
  5. Research on Vision Detection Algorithm for Tracing Printing System,TP391.41
  6. Research on Image Denoising Algorithm in Machine Vision System,TP391.41
  7. Orchidaceae based on embedded intelligent control system for plant tissue culture,TP273.5
  8. Fabric appearance based on machine vision digital analysis method and system design,TP391.41
  9. Mold sections based on machine vision sorting system design,TP274
  10. The Rapid Detection of Soil Moisture Based on Near-Infrared Spectroscopy and Machine Vision,S152.7
  11. Research on Water Level Monitoring System Based on Machine Vision,TP277
  12. FPGA/DSP Image Co-processor Technology and Ethernet Data Transmission,TP391.41
  13. Study of 3-D Measuring Method Based on Machine Vision,TP274
  14. Inspecting and Controlling System of Checking Bottle Machine for Beer Product Line,TP277
  15. Korean inherent color of semantic analysis,H55
  16. Waveguide array fiber alignment technology based on machine vision,TP391.41
  17. Research on Molding Production Oriented Technology and Application of Visual Defects Recognition,TP391.41
  18. Distinguishing the Dated Marker Lines of Highway Based on Image Processing,TP391.41
  19. Study of Flow Characteristics Extraction Technology in Microcirculation Based on Image Processing,TP391.41
  20. Study on the Recognition Algorithm of AGV Dynamic Path Based on Machine Vision,TP391.41
  21. Design and Implementation of enlarging its online detection system based on machine vision,TP391.41

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Pattern Recognition and devices
© 2012 www.DissertationTopic.Net  Mobile