Dissertation > Excellent graduate degree dissertation topics show

On Statistical Approaches to Feature Extraction and Recognition for Target above the Water

Author: YeBo
Tutor: LiWanChen
School: Harbin Engineering University
Course: Signal and Information Processing
Keywords: Feature Extraction Target recognition Hadamard transform Gaussian mixture model
CLC: TP391.41
Type: Master's thesis
Year: 2010
Downloads: 78
Quote: 0
Read: Download Dissertation

Abstract


In recent years, with human awareness and further in-depth exploration of marine , increase the control of the marine information in real life becomes increasingly important, which automatically identify surface targets is one of the most important issues . Unpredictable factors more complex waters brought considerable difficulties to the automatic identification of surface targets . Based on the target contour feature extraction and recognition , the two traditional methods ( based on moment invariants based on PCA ( Principal Component Analysis )) for global features for automatic target recognition is estimated under simulated conditions , and because the positioning of the ROI ( region of interest ) algorithm is not accurate enough, these two methods have significant limitations in the identification . In this paper , we first of all the basic image pattern recognition theory , method and application status analysis, combined with surface targets identified requirements for the content of image preprocessing , mainly for impulse noise filtering and image segmentation discussion, and in accordance with the ratio of the experimental results to determine the image filtering and segmentation method . Secondly , through the study and the results of analysis of target recognition method based on the moment invariants and principal component analysis , we put forward by a goal-based local feature -by- block 2D Hadamard transform and Gaussian mixture model classifier . The experiments show that : this method has good robustness in the case of the target outside the field range , the proportional change generated due to the depth of the impact also has certain robustness . Traditional methods during automatic target recognition , invariant moments even in a good environment to identify the effect is very poor , and the more obvious when the target is out of the field of view or obscured . PCA method by the ratio of change in and beyond the field of view of the impact of noise and occlusion have relatively better robustness . Finally, this angle ( caused by the rotation in the plane ) does not match the contour of the training and testing in the target recognition process by using several spatial angle of very far apart to achieve the expansion of the training set , thereby completing the target identification.

Related Dissertations

  1. Research on Automatic Detection Algorithm for Substructure Distress of Highway Pavement Based on SVM,U418.6
  2. ISAR Imaging Simulation of Space Targets and Target Recognition Based on ISAR Images,TN957.52
  3. Research on Feature Extraction and Classification of Pulse Waveform for Cholecystitis and Nephrotic Syndrome Diagnosis,TP391.41
  4. Application of Q-Learning in the Content-Based Image Retrieval Technology,TP391.41
  5. Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
  6. Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
  7. Study on Virtual Detector of Infrared Hyper-Spectral Image,TP391.41
  8. Research on Visual Measurement for Spacecraft Rendezvous and Approach,TP391.41
  9. Research on the Image Real-Time Acquisition, Storage and Image Processing System,TP391.41
  10. Feature Extraction, Selection and Combination in Lipreading,TP391.41
  11. Multi-currency Notes Technology Research and Implementation,TP391.41
  12. The Research on Paper Currency Classification Method Based on Harr-Like Feature and Minimal Ball Including Samples,TP391.41
  13. Pavement Distress Recognition Based on Image,TP391.41
  14. Research on Visual Detection and Tracking of Mobile Robots,TP242.62
  15. Research on Fusion Algorithm of Hyper Spectral and High Spatial Resolution Remote Sensing Image,TP751
  16. An Approach for Identifying a Plant Resistance Gene Based on the Random Forest,Q943
  17. Tobacco Diseases Auto-Recognition Research Based on Image Processing Technology,S435.72
  18. Research on Nondestructive Detection Technology for External Qualities of Papayas Based-on Vision,S667.9
  19. Research on Identification System of Cashmere and Wool Fiber,TS101.921
  20. Research for Infrared Image Target Identification and Tracking Technology,TP391.41
  21. The Compression and Fusion Technique Research of Underwater Target Feature,TN911.7

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