Indoor Scene Classification by Object Detection

Please enable javascript in your browser.

Mazinani, Mohammad Reza | 2013

429 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 44853 (19)
University: Sharif University of Technology
Department: Computer Engineering
Advisor(s): Manzuri, Mohammad Taghi
Abstract:
Image classification is one of the most challenging issues in computer vision. One sort of such classifications is Scene Classification. To perform automatic classification reserchers used many aproches.The general approach used features directly extracted from the image, such as color and texture or features extracted by the SIFT algorithmetc. Another method is based on recognizing object of the Scene (espessially indoor scene). This method is based on finding of a limited number of prespecified objects. In the proposed method, first a window surrounding each objects, (regardless of the type of object) founded. Then the SIFT feature is extracted from that window. All features (corresponding to objects) are clustered using clustering K-means algorithm and the dictionary is build. All features are coded using locally constraint linear coding approach. In this study it is shown that this new feature would be useful inindoor scene, because indoor scenes are known with objects in it
Keywords:
Scene Classification ; Indoor Scene ; Object Detection ; Object Window

No TOC