Dissertation > Excellent graduate degree dissertation topics show

Research on Scene Classification Technologies with the Local Context Feature and Spatial Pyramid Model

Author: TuZuoLei
Tutor: HuZhengPing
School: Yanshan University
Course: Communication and Information System
Keywords: scene image classification context feature complementary feature category-specific visual words sparse coding spatial pyramid matching
CLC: TP391.41
Type: Master's thesis
Year: 2012
Downloads: 177
Quote: 0
Read: Download Dissertation

Abstract


The process of scene image classification is that how to make computer systems toclassify the image sets automatically which contain semantic information, according to thevisual perception mechanism of human. Scene classification has become an activeresearch topic in the computer vision area, which provides important environmental cluesfor object recognition and other computer vision tasks. Be similar to the words in text data,modeling scene images with visual vocabulary could form a middle representation, whichdescribes the semantic information of scene images effectively. Based on the bag-of-wordsmodel of scene images, we focus on the feature extraction, visual words formation andvisual words representation to do the following research:First of all, the traditional visual words are formed by local features independently,and consider nothing about the relations among of features. To overcome this defect, wepropose a kind of local visual features that include multi-direction context information,and use the category-specific strategy to form the visual vocabulary, after that the spatialpyramid model is combined to accomplish the scene classification. According to differentscene categories, this method combines the feature similarity and contextual relationtogether. The experiments show that this method performs better than the existed methods.Secondly, since the context relations play an important role in the featurerepresentation of images, we do some further research about the effectiveness of contextinformation. Utilizing the flatness information of image regions, a new feature extractionmethod is proposed to form adaptive context features in an unsupervised manner, and thevisual words are formed by the specific categories of images. After that the integrateddistribution vectors of visual words are computed by applying the spatial pyramid modelwhich based on sparse coding, and the scene classification is accomplished by thosedistribution vectors. This method chooses the effective context features and theexperiment results show that it could achieve a higher accuracy obviously.Finally, in order to extract the further visual property of scene images in differentaspects, we introduce a local self-similarity descriptor to describe scene images on the basis of adaptive context features. Then an image representation method is proposed bycombining the two complementary features, and the visual words model is obtained byusing the category-specific strategy and sparse coding, after that a discriminative spatialpyramid representation is exploited by applying partial least squares theory to accomplishthe scene classification. This method could make the bag-of words model more flexibleand discriminative. The experiment results show that this method could achieve a higheraccuracy, especially perform well in complicated indoor images.

Related Dissertations

  1. Research on Sparse Image Representation and Coding Model,TP391.41
  2. Spatio-temporal Feature Learning and Human Activity Analysis in Complex Scenes,TP391.41
  3. Research on Biological Visual Features Extraction in Images Combining Sparse Coding,TP391.41
  4. Research on Face Recognition and Tracking Technology in Instant Message,TP242
  5. Supervised Learning Based Image Local Interest Points Detector,TP391.41
  6. Based on sparse representation of high spatial resolution remote sensing image texture description Method,TP751
  7. Non-negative Local Coordinate Factorization for Image Representation,TP391.41
  8. Non-negative matrix factorization based on sparse image retrieval,TP391.41
  9. Graph-based color image segmentation algorithm targets,TP391.41
  10. Machine learning based on sparse coding and image content recognition algorithm,TP391.41
  11. Training and weighted online dictionary sparse representation of difference,TP391.41
  12. Research on Scene Classification Technologies with the Local Region Description Feature and Probabilistic Latent Semantic Analysis Model,TP391.41
  13. Research on Designing and Application of Topical Spider,TP391.3
  14. Mechanisms Underlying the Robust Synchronization in Excitatory-inhibitory Network and Its Application,TP393.02
  15. Russian conflict Speech Genre Study,H35
  16. Research on Deformed Target Locate Algorithm Based on Extended Contour Description,TP274
  17. Polarimetric SAR image speckle reduction research,TN957.52
  18. Synchronization of Neural Activities with Binding Problem in Memory,B842.3
  19. Noisy aliasing speech signals separation method,TN912.3
  20. On Content Representation and Catigorization of Scene Images,TP391.41
  21. A Study on Offensive Addressing Terms,H03

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