Dissertation > Excellent graduate degree dissertation topics show

Research on Image Annotation Based Active Learning

Author: XuYan
Tutor: SunFuMing
School: Liaoning University of Technology
Course: Communication and Information System
Keywords: active learning sampling strategy density-entropy SVM regularization
CLC: TP181
Type: Master's thesis
Year: 2014
Downloads: 20
Quote: 0
Read: Download Dissertation

Abstract


In recent years, with rapid development of multimedia technologies and networks, digitalimages are increasing in an explosive way. The majority of digital image are unknown data,and annotating the unlabeled samples requires a high workload and is time-consuming.Therefore, much more attention has been paid to find a good method that significantlyminimums labeling efforts. As a promising approach, active learning is often adopted toreduce the labeling efforts in classification problems. The active learner has the ability toautomatically select the most informative samples for human labeling, and then the labeledsamples are added to training datasets for building up the learner. In such iterative process, theaccuracy of the learning algorithm is improved significantly with less training samples,avoiding acceptance of the redundant informance.This paper does some research on sampling strategy and model selection. The mainworks are as follows:In uncertainty sampling, it is easy to select outliers, especially samples distributedunevenly. To tackle this issue, this paper takes into account the prior distribution of samples,and proposes an active learning algorithm based density-entropy, namely the combination ofthe uncertainty and representativeness. Neighbor entropy and neighbor density are adopted tomeasure the sample’s uncertainty and representativeness, respectively. The experimentalresults from UCI benchmark demonstrate that the proposed sampling algorithm performsbetter than random sampling in most case.In active learning support vector machine, it is a common practice to use default valuesfor model parameter, leading to unsatisfying learning performance. This paper proposes anactive learning SVM algorithm with regularization path that can fit the entire solution path ofSVM for every value of model parameters. This algorithm traces the entire solution path ofthe current classifier and find a series of candidate model parameters, then uses unlabeledsamples to select the best model parameter. The experimental results from UCI andNUS-WIDE data sets show that the algorithm proposed in this paper outperforms the defaultparameter method.

Related Dissertations

  1. Soft Sensor of Naphtha Dry Point on Support Vector Machines Regression,TE622.1
  2. The Research of the Fault Diagnoses Algorithm for the Liquid Rocket Engine Testing Bed Based on PCA-SVM,V433.9
  3. ISAR Imaging Simulation of Space Targets and Target Recognition Based on ISAR Images,TN957.52
  4. Research on Autamatic Music Structrue Analysis,TN912.3
  5. Research on Feature Extraction and Classification of Pulse Waveform for Cholecystitis and Nephrotic Syndrome Diagnosis,TP391.41
  6. Research on Classification Method of Tongue Substance Color and Tongue Coating Color Based on SVM,TP391.41
  7. The Research on Paper Currency Classification Method Based on Harr-Like Feature and Minimal Ball Including Samples,TP391.41
  8. Research on Focused Crawler Based on SVM Classification Algorithm,TP391.3
  9. Research on Predicting Intrinsic Disorder Protein Structure Based on Supervision Manifold Learning Algorithm,Q51
  10. Study on the Road Condition Monitoring Based on Vehicular 3D Acceleration Sensor,TP274
  11. Research and Application of Gas Emission Prediction Based on LS-SVM,TD712.5
  12. Research of Support Vector Machine Based Fault Diagnosis System,TH165.3
  13. Computer-aided Hepatopathy Detection Based on MRI Perfusion Images,R445.2
  14. Research of Chinese Ellipsis Identification,TP391.1
  15. Research of Orange Quality Classification Technology Based on Computer Vision,TP391.41
  16. Superfluid-Mott Insulator Phase Transition at Finite Temperature,O512
  17. Research on Supplier-Selection Based on Strategic Sourcing,F426.31
  18. Analysis on Synoptic Climatology Characteristics and Forecast Methods of Fog in Hainan,P457
  19. Research of License Plate Recognition Based on Rough Sets and Fuzzy SVM,TP391.41
  20. Study on Visual Target Detection Based on SVM,TP391.41
  21. Vision-based Human Movement Analysis,TP391.41

CLC: > Industrial Technology > Automation technology,computer technology > Automated basic theory > Artificial intelligence theory > Automated reasoning,machine learning
© 2012 www.DissertationTopic.Net  Mobile