Dissertation > Excellent graduate degree dissertation topics show

Research on Content and SVM Based Image Retrieval

Author: ShiHe
Tutor: ZhaoYuQian
School: Central South University
Course: Biomedical Engineering
Keywords: image retrieval support vector machine image classification
CLC: TP391.41
Type: Master's thesis
Year: 2011
Downloads: 51
Quote: 0
Read: Download Dissertation

Abstract


With the rapid development of internet and multimedia technology, how to retrieval target image rapidly and effectively from tons of information is the hotspot of current multimedia technology research. Content Based Image Retrieval (CBIR) becomes the main direction of multimedia information retrieval. CBIR extracts low level image features, calculates the similarity of features and chooses the most similar images as the retrieval results. However, there is a’Semantic Gap’between high-level semantics and low-level image features heavily affects the retrieval performance. How to bridge the gap is the Semantic Based Image Reterival focus on. Support Vector Machine (SVM) is a machine learning technology, has been widely used in classification and pattern recognition.In this thesis, SVM classification algorithm is used, the computer automatically makes a multi-classifier model by training the sample images and then use the classifier model on the testing images, at the last retrieval images on the classification result. This image retrieval method makes a bridge between the low-level image features and high-level semantic features. To improve the accuracy of image retrieval (recall and precision), the classic image color features and texture features are combined to increasing the capacity of the image features’representation. Experimental results show that the accuracy by using integrated features is higher than using a separate features.SVM cannot classify a image which has several objects in it to more than one class, so we proposal a SVM image retrieval algorithm base on the objects. At the fist we sub-block images to several sub-images and pick some of them as the training sample images set, then make multi-classifer by training them. In the forecast step, sub-block the testing images, and extract the features vector of each sub-images, then put all the sub-images of one image features vector together as a input array of the SVM, and finally get a set of testing images of the classification property. In the retrieval step, take the classification property as a new feature vector to a new object-based image retrieval.Experimental results show that object-based SVM image retrieval algorithm can classify a image which has several objects in it to multi-classes, and it do a better job on accuracy of image retrieval than the without sub-block one.

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. 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. Application of Q-Learning in the Content-Based Image Retrieval Technology,TP391.41
  6. Research and Implementation on Content-Based Clothing Image Retrieval,TP391.41
  7. The Discovery of User Concept Region Based on Multiple Instance Learning,TP391.41
  8. Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
  9. Research and Application of Diverse Density Learning Algorithm,TP181
  10. Fault Diagnosis Method Based on Support Vector Machine,TP18
  11. Process Support Vector Machine and Its Application to Satellite Thermal Equilibrium Temperature Prediction,TP183
  12. Research for Infrared Image Target Identification and Tracking Technology,TP391.41
  13. Study on the Road Condition Monitoring Based on Vehicular 3D Acceleration Sensor,TP274
  14. Research of Diagnosing Cucumber Diseases Based on Hyperspectral Imaging,S436.421
  15. Research of Shape Based Image Retrieval in Han Dynasty Stone,TP391.41
  16. The Research on Intrusion Detection System Based on Machine Learning,TP393.08
  17. Research on Improved K Neighbor Support Vector Machine Algorithm Faced Text Classification,TP391.1
  18. Research on Face Recognition Based on AdaBoost Algorithm,TP391.41
  19. Research on Feature Extraction, Selection and Classification Algorithms for Pulmonary CAD,TP391.41
  20. Research on Subimage Selection and Mathching Method for Synthetic Aperture Radar(SAR) Target Recognition,TN957.52
  21. Research of Facial Expression 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