Fuzzy‐Based Segmentation for Variable Font‐Sized Text Extraction from Images/Videos

Abstract

Textual information embedded in multimedia can provide a vital tool for indexing and retrieval. A lot of work is done in the field of text localization and detection because of its very fundamental importance. One of the biggest challenges of text detection is to deal with variation in font sizes and image resolution. This problem gets elevated due to the undersegmentation or oversegmentation of the regions in an image. The paper addresses this problem by proposing a solution using novel fuzzy-based method. This paper advocates postprocessing segmentation method that can solve the problem of variation in text sizes and image resolution. The methodology is tested on ICDAR 2011 Robust Reading Challenge dataset which amply proves the strength of the recommended method.

Fuzzy Logic-Based Evaluation Model of Handwritten Font Sizes Readability on Extra Small Devices

“…Also, Agusta et al [2] proposed a model of effort estimation for web-based mobile application developed using object-oriented approach based on fuzzy logic in order to compare and evaluate two metrics. Tehsin et al [22] made one step forward and used fuzzy logic for segmentation and extraction text elements from images and videos.…”

A novel Iterative algorithm to text segmentation for web born-digital images

“…Recently, reading text from web born-digital images has been organized as a competition in 2011 and 2013 International Conference for Document Analysis and Recognition (ICDAR) [2,3]. As text localization and segmentation play a fundamental role for text recognition, several methods [4,5,6] had published its performance on the competition datasets. In "Textorter" [2], edge detectors are employed to extract components, then features such as aspect ratio and binary transitions are used to detect text components; for text segmentation a threshold is applied to the text regions to obtain a binary image.…”