A novel thin elongated objects segmentation based on fuzzy connectedness and GMM learning

Qingsong Zhu, Ricang Ye, Ling Shao, Qi Li, Yaoqin Xie

Research output: Contribution to conferencePaper

Abstract

Extraction of thin elongated objects from natural images is an important task in many computer vision applications such as image segmentation, object detection. Extensive approaches attempt to solve this issue with region features or prior knowledge, causing local minimum or short cut path. In this paper, we propose a semi-automatic method for the extraction of thin elongated objects. Given the input image, we manually label some foreground/background pixels as training samples. We use Guassian mixture model (GMM) to model background and extract object. We compute fuzzy affinity based on G-MM and take the framework of fuzzy connectedness (FC) to obtain fuzzy connected component. To obtain better result, we use adaptive components for GMM. Qualitative and quantitative comparisons show that our method outperforms many classical algorithms in terms of accuracy.
Original languageEnglish
DOIs
Publication statusPublished - Sep 2013
EventICIP 2013 - 20th IEEE International Conference on Image Processing - Melbourne, Australia
Duration: 1 Sep 2013 → …

Conference

ConferenceICIP 2013 - 20th IEEE International Conference on Image Processing
Period1/09/13 → …

Fingerprint Dive into the research topics of 'A novel thin elongated objects segmentation based on fuzzy connectedness and GMM learning'. Together they form a unique fingerprint.

Cite this