Texture classification using scale invariant feature transform and Bag-of-Words

Author

Budak, Umit ; Sengur, Abdulkadir

Author_Institution

Muhendislik Fak., Elektrik - Elektron. Muhendisligi Bolumu, Bitlis Eren Univ., Bitlis, Turkey

fYear

2015

fDate

16-19 May 2015

Firstpage

152

Lastpage

155

Abstract

Texture images can be characterized with key features extracted from images. In this way, they can be qualified with distinctive features. In this paper, a featurebased approach is presented for texture classification using Scale Invariant Feature Transform (SIFT) and Bag of Words (BoW) methods. The SIFT method is preferred because the features obtained by this method are invariant against such cases of rotation, angle of camera, ambient light intensity. UIUCTex and KTH-TIPS2-a data sets are selected which are widely used for classification. A success rate of 91.2% was obtained for the data set UIUCTex. This rate was determined as 72.1% for the data set KTH-TIPS2-a.

Keywords

cameras; feature extraction; image classification; image texture; transforms; BoW method; KTH-TIPS2-a; SIFT method; UIUCTex; ambient light intensity; angle-of-camera; bag-of-word method; feature extraction; image texture classification; scale invariant feature transform method; Expert systems; Feature extraction; Histograms; Kernel; Pattern recognition; Support vector machines; Transforms; Bag of Words (BoW); K-means; Scale Invariant Feature Transfrom (SIFT); Support Vector Machine (SVM); Texture Classification;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing and Communications Applications Conference (SIU), 2015 23th

Conference_Location

Malatya

Type

conf

DOI

10.1109/SIU.2015.7130323

Filename

7130323