Color and gradient features for text segmentation from video frames

Shivakumara, P. and Guru, D. S. and Basavaraju, H. T. (2013) Color and gradient features for text segmentation from video frames. In: Multimedia Processing, Communication and Computing Applications. Springer, New Delhi, pp. 267-278. ISBN 978-81-322-1143-3

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


Text segmentation in a video is drawing attention of researchers in the field of image processing, pattern recognition and document image analysis because it helps in annotating and labeling video events accurately. We propose a novel idea of generating an enhanced frame from the R, G, and B channels of an input frame by grouping high and low values using Min-Max clustering criteria. We also perform sliding window on enhanced frame to group high and low values from the neighboring pixel values to further enhance the frame. Subsequently, we use k-means with k = 2 clustering algorithm to separate text and non-text regions. The fully connected components will be identified in the skeleton of the frame obtained by k-means clustering. Concept of connected component analysis based on gradient feature has been adapted for the purpose of symmetry verification. The components which satisfy symmetric verification are selected to be the representatives of text regions and they are permitted to grow to cover their respective region fully containing text. The method is tested on variety of video frames to evaluate the performance of the method in terms of recall, precision and f-measure. The results show that method is promising and encouraging.

Item Type: Book Section
Uncontrolled Keywords: Image processing, Pattern recognition, Communication, Connected component analysis, Clustering algorithms, Text detection, Sliding Window, K-means, Min-max
Subjects: D Physical Science > Computer Science
Divisions: Department of > Computer Science
Depositing User: Arshiya Kousar Library Assistant
Date Deposited: 18 Nov 2019 07:11
Last Modified: 18 Nov 2019 07:11

Actions (login required)

View Item View Item