Dissertation > Excellent graduate degree dissertation topics show

Study of Image Content Annotation Based on Emotion Semantic

Author: HuLingZi
Tutor: YuXueLi
School: Taiyuan University of Technology
Course: Computer Software and Theory
Keywords: Image annotation Image emotional semantic Feature Extraction Support Vector Machine SVM
CLC: TP391.41
Type: Master's thesis
Year: 2010
Downloads: 113
Quote: 0
Read: Download Dissertation

Abstract


Many images in the application not only carry the appearance, but also carry a lot of emotional information, however, the image annotation retrieval technology, but most of them ignore the emotional factors. How effective and to describe the emotion of the image, and give quantified, and thus make the retrieval process to reflect the user's subjective tendencies, meet the emotional needs of the user to retrieve an important and challenging issues of image annotation and retrieval . Occupies a very important position in the image contains all kinds of semantic rich emotional semantics as an important high-level semantic content, marked in semantic image retrieval. The emotional semantic description, feature extraction, emotion recognition is the core problem of emotional semantic annotation retrieval. Semantic annotation for image emotional problems game scene image library of the Institute of Psychology, Chinese Academy of Sciences for the data source, and do in-depth research on some of the key techniques and methods in the the emotional semantic annotation retrieval. First simple classification image database, extract the emotional characteristic attributes of the image, the image emotional semantic classification label Secondly, based on support vector machine (SVM) and different SVM parameters based precision analysis, different feature or combination of emotional semantic classification labels. Final the semantic classifier training for each emotion to generate specific semantic rules and the emotional semantic concept by certain emotional semantic rules to determine. The experimental results show that, by selecting the appropriate emotional characteristics of properties and SVM parameters, SVM classifier can effectively image databases emotional semantic classification label. Statistical learning theory and support vector machines SVM in many ways shows a good effect for sample study, can reduce the burden on the user, more suitable for the emotional image annotation retrieval. Support vector machine (SVM) based on statistical learning theory, exhibit many unique advantages in solving small sample, nonlinear and high dimensional pattern recognition problem, is becoming a new hotspot in the field of machine learning. Chapter This article mainly extracted image characteristic attributes of the degree of happiness, and positive and negative emotional activation degree as emotion recognition, support vector machine image emotional semantic annotation recognition. When the training samples to determine the model of SVM, SVM can be carried out emotion recognition test collection. 178 In this study, the test image, the underlying characteristics of the image input SVM can get their class. By contrast with the pre-defined category, according to the formula of emotion recognition correct rate, you can get the appropriate classification label prediction accuracy rate. Can be drawn through the experimental results: select the appropriate sample normalization parameters can effectively improve the classification label prediction accuracy rate, while the optimal parameters and sample normalized combination can get better experimental results. Overall, the article mainly from the following aspects of emotional semantic image annotation retrieval taken further research, select appropriate emotional adjectives describe the image emotional semantic selected two highly correlated image emotional emotional attribute characteristics, then this based on support vector machine SVM algorithm as emotional recognition algorithm, and the proposed method and parameters selected for a large number of experiments, the experimental results show that the proposed method and parameters effectively achieved within a certain range image emotion classification marked.

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 Autamatic Music Structrue Analysis,TN912.3
  4. Research on Feature Extraction and Classification of Pulse Waveform for Cholecystitis and Nephrotic Syndrome Diagnosis,TP391.41
  5. Application of Q-Learning in the Content-Based Image Retrieval Technology,TP391.41
  6. Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
  7. Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,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