Sketch based flower detection and tracking

Guru, D. S. and Sharath Kumar, Y. H. and Krishnaveni, M. T. (2013) Sketch based flower detection and tracking. In: Multimedia Processing, Communication and Computing Applications.

Full text not available from this repository. (Request a copy)
Official URL:


In this paper, we present a system for detecting and tracking of a flower in a flower video based on a query sketch of the flower. The proposed system has two stages detection and tracking. In first stage a sketch of a flower of interest is given as an input. The edge orientation information of the given sketch is matched against that of an individual frame in search of a location of the flower of interest using fast directional chamfer matching. In second stage the detection coordinates have been used for tracking the sketch part in flower videos. For tracking we used joint color texture histogram to represent a target and then apply it to the mean shift framework. For experimentation we created our own dataset of 10 videos of different flowers and their sketches. To study the efficiency of the proposed method we have compared the obtained results provided by five human experts.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Communication, Textures, Graphic methods, Mean shift, Chamfer matching, Color-texture histograms, Detection and tracking, Edge orientations, Flower detections, Human expert, Target tracking
Subjects: D Physical Science > Computer Science
Divisions: Department of > Computer Science
Depositing User: Arshiya Kousar Library Assistant
Date Deposited: 20 Sep 2019 05:36
Last Modified: 20 Sep 2019 05:36

Actions (login required)

View Item View Item