Cattle´s fur detection in complex background based on Graph Cuts

Author

Fahmi, Hisyam ; Noviyanto, Ary ; Arymurthy, Aniati Murni

Author_Institution

Image Process. & Pattern Recognition Lab., Univ. Indonesia, Depok, Indonesia

fYear

2013

fDate

28-29 Sept. 2013

Firstpage

267

Lastpage

271

Abstract

Segmentation becomes a difficult task if the objects are not homogeneous and have overlapping characteristics. The Graph Cuts methods combined with Gaussian Mixture Model (GMM) for initialization label has been adopted to detect cattle object in an image with complex background. The RGB colors and Gray Level Co-occurrence Matrix (GLCM) textures are used as the features set. This method can robustly segment the cattle beef image from its background. This segmentation method produces the average of accuracy value up to 90%.

Keywords

Gaussian processes; feature extraction; graph theory; image colour analysis; image segmentation; image texture; matrix algebra; mixture models; GLCM texture; Gaussian mixture model; RGB colors; cattle beef image segmentation method; cattle fur detection; cattle object detection; complex background; feature set; graph cut method; gray level co-occurrence matrix texture; initialization label; overlapping characteristics; Accuracy; Cows; Equations; Gaussian mixture model; Image color analysis; Image segmentation; Mathematical model;

fLanguage

English

Publisher

ieee

Conference_Titel

Advanced Computer Science and Information Systems (ICACSIS), 2013 International Conference on

Conference_Location

Bali

Type

conf

DOI

10.1109/ICACSIS.2013.6761587

Filename

6761587