Automatic image labelling using similarity measures

Author

Uher, Vaclav ; Burget, Radim ; Karasek, Jan ; Masek, Jaroslav ; Dutta, Malay Kishore ; Singh, Ashutosh

Author_Institution

Dept. of Telecommun., Brno Univ. of Technol., Brno, Czech Republic

fYear

2014

fDate

7-8 Nov. 2014

Firstpage

101

Lastpage

104

Abstract

Scene classification based on global features. It can be used, for example, for annotating large databases of photos. The whole process has several steps. The first step is features extraction, and then the distance between a new image and reference images is calculated. A model is trained to classify new images based on this distance. The model was created using the Naïve Bayes classifier. To improve accuracy the forward selection was used, which optimizes the selection of a group of attributes. The overall performance on the testing dataset was 69.76%.

Keywords

Bayes methods; feature extraction; feature selection; image classification; automatic image labelling; feature extraction; forward selection; image classification; naive Bayes classifier; scene classification; Feature extraction; Histograms; Image color analysis; Image edge detection; Layout; Sections; Transform coding; Scene classification; image labelling; image processing; machine learning;

fLanguage

English

Publisher

ieee

Conference_Titel

Medical Imaging, m-Health and Emerging Communication Systems (MedCom), 2014 International Conference on

Conference_Location

Greater Noida

Print_ISBN

978-1-4799-5096-6

Type

conf

DOI

10.1109/MedCom.2014.7005984

Filename

7005984