Interactive Segmentation of User Concepts in Images

Anjali Ananthan; R Jayadevan; Mahesh K.R

CALL FOR PAPERS : Mar-2023

Submission Last Date

25-Mar-23

Submit Manuscript Online

FOR AUTHORS

FOR REVIEWERS

ARCHIEVES

DOWNLOADS

Open Access

Interactive Segmentation of User Concepts in Images

Author(s):

Anjali Ananthan , THEJUS ENGINEERING COLLEGE; R Jayadevan, Government Engineering College,Thrissur; Mahesh K.R, Thejus Engineering College,

Keywords:

Mean Shift Clustering, Merging, Neighbourhood Classification, Pruning, User Interactive Segmentation

Abstract:

This paper is mainly focusing on the area user interactive image segmentation. For this purpose a user interactive image segmentation algorithm is applied to the input image. After performing segmentation of the input image only the desired portion of the image i.e., the foreground is extracted. The segmentation method used in this project is semi-automated in nature. This algorithm begins with an initial over segmentation that is performed using mean shift clustering mechanism. Then the selected foreground and background regions are distinguished as white and black regions. Merging the unmarked regions as either foreground or background is done. Then a local neighbourhood classification is performed followed by the pruning step. The final result of this paper will isolate the foreground region as desired by the user from the background region. Foreground will be represented by white region and background by black region.