Dissertation > Excellent graduate degree dissertation topics show

Image Device Source Identification Based on Pattern Recognition

Author: ZhouChangHui
Tutor: HuYongJian
School: South China University of Technology
Course: Pattern Recognition and Intelligent Systems
Keywords: digital image forensics source identification of imaging equipment pattern recognition support vector machine robustness Feature selection
CLC: TP391.41
Type: Master's thesis
Year: 2011
Downloads: 37
Quote: 1
Read: Download Dissertation

Abstract


Digital image can be easily generated and forgery, in this case, the reliability problems of digital image source suffered a serious question. In order to solve this problem, the digital image forensics that an objective, fair and to clarify the truth verification technology is proposed. It has an important significance to ensure the reliability of the digital image source.This paper is based on pattern classification approach to research the source of digital image from digital camera and a color scanner. Discuss the performance and robustness problem of source identification algorithm in the ideal mode and actual application mode. The ideal mode that test images are not processed, and the actual application pattern means that the test images are tampered. The contributions of this thesis are described as follows.1. An improved source camera identification algorithm based on image features is proposed. More ideal classification effect can be got by using the method. Then, we analyze the robustness of the current source identification and point out the problem in the design processing of the existing camera source identification algorithms. Finally, we give the direction to solve this problem.2. A robust source scanner identification algorithm is proposed. The proposed algorithm aims at solving the robust problem of the existing source scanner identification. It improves the accuracy of classification, but it also reduces the amount of calculation.3. Using the sequential forward floating search algorithm for choosing features. Using image feature subsets, we analyze the performance and robustness of source camera/scanner identification, and then, discussed the impact of using these subsets on the robustness of these algorithms. We also give the direction to solve the robustness problem of feature selection.

Related Dissertations

  1. Research on Automatic Detection Algorithm for Substructure Distress of Highway Pavement Based on SVM,U418.6
  2. Research on Autamatic Music Structrue Analysis,TN912.3
  3. Feature Extraction, Selection and Combination in Lipreading,TP391.41
  4. Study on the Road Condition Monitoring Based on Vehicular 3D Acceleration Sensor,TP274
  5. Identification and Robustness Analysis of Nonlinear Hybrid Dynamical System Concerning Glycerol Transport Mechanism,TQ223.162
  6. The Research on Feature Selection for Data Stream,TP311.13
  7. Study on Applications of Soft Sensor in Chloromethane Recovery,TQ222.214
  8. Driverless smart car moving target detection and tracking,TP391.41
  9. Solder paste printing quality based on image processing techniques to detect,TP391.41
  10. Smartphone dimensional code recognition system design and implementation,TN929.53
  11. Based on LabVIEW typical communication signal modulation , parameter identification and simulation experiment,TP274
  12. Based on Information Fusion Fault Diagnosis of Analog Circuits,TN710
  13. Based on DCE-MRI of computer-aided diagnosis of benign and malignant breast lesions studied,TP391.7
  14. Dynamic Voltage Restorer Robust Control Measurement,TM76
  15. Seamless integration of automatic detection of ultrasonic vortex systems research and development,TH878.2
  16. Customer value assessment based on comprehensive foreign trade enterprise channels of customer classification,F752;F224
  17. Based on SVM-RFE potential biomarker selection algorithm,TP311.13
  18. Random Forests Feature Selection,TP311.13
  19. Rural road environment obstacle detection,TP391.41
  20. Based on sparse representation Face Image Recognition Method,TP391.41
  21. Machine learning based on sparse coding and image content recognition algorithm,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