Dissertation > Excellent graduate degree dissertation topics show

The Rearch of Color Image Retrieval Based on Color Feature of Object

Author: YeXun
Tutor: HuangChaoBing
School: Wuhan University of Technology
Course: Communication and Information System
Keywords: Image Segmentation Main color Otsu Feature Extraction Image Retrieval
CLC: TP391.41
Type: Master's thesis
Year: 2010
Downloads: 69
Quote: 1
Read: Download Dissertation

Abstract


With the advent of the era of multimedia technology , a large number of digital images circulated on the Internet , how to quickly and effectively get the desired image information to become a hot research topic and content-based image retrieval technology came into being . For content-based image retrieval is mostly concentrated in the underlying characteristics based on global based global method is relatively simple , computationally efficient, but some users are not interested in the background containing large amount of information , the target accounted for a small proportion image image retrieve ineffective . Target feature - based image retrieval can reduce the image background information retrieval , the difficulty lies in how to be able to accurately extracted from the images interoperability interested in the target area . In this paper, an object-based image retrieval method , the first image segmentation , split and then split out of the target area for feature extraction and retrieval . First image histogram quantization in the quantization after the peak of the histogram to find a suitable value as the main color in the image , and then each pixel is classified as the main color of the Nearest , the image is converted into a main color chart Otsu method to find the between-class variance maximum threshold , the threshold image is divided into two parts of the object and background , in order to extract the target area of the image . Feature extraction part , the first image segmentation target area color quantization , color- sorted by percentage method to extract the target area of the primary colors , and the percentage of main color and main color as a feature vector for image retrieval , in order to the spatial information is added to the main color feature , before feature extraction , image sub-blocks, the different areas of the extracted feature information attention is set different weights . Finally , using the Euclidean distance normalized similarity measure. Experiments show that the method can better extract the target image feature extraction , excluding the impact of background similarity to improve the effectiveness of retrieval .

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 Facial Feature Extraction and Matching Algorithms for Image Retrieval,TP391.41
  4. The Research and Implemention of Image Retrieval Based on User Interested Feature,TP391.41
  5. Research on Feature Extraction and Classification of Pulse Waveform for Cholecystitis and Nephrotic Syndrome Diagnosis,TP391.41
  6. Application of Q-Learning in the Content-Based Image Retrieval Technology,TP391.41
  7. Research and Implementation on Content-Based Clothing Image Retrieval,TP391.41
  8. The Discovery of User Concept Region Based on Multiple Instance Learning,TP391.41
  9. Research on Image Recognition Algorithm in the Forest Fire Prevention System,TP391.41
  10. Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
  11. Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
  12. Research on Visual Measurement for Spacecraft Rendezvous and Approach,TP391.41
  13. Research on the Image Real-Time Acquisition, Storage and Image Processing System,TP391.41
  14. Feature Extraction, Selection and Combination in Lipreading,TP391.41
  15. Multi-currency Notes Technology Research and Implementation,TP391.41
  16. The Research on Paper Currency Classification Method Based on Harr-Like Feature and Minimal Ball Including Samples,TP391.41
  17. Pavement Distress Recognition Based on Image,TP391.41
  18. Research on Visual Detection and Tracking of Mobile Robots,TP242.62
  19. Research on Fusion Algorithm of Hyper Spectral and High Spatial Resolution Remote Sensing Image,TP751
  20. Research and Application of Diverse Density Learning Algorithm,TP181
  21. Application Research of Digital Image Processing on Container Inspection,TP274.4

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