An Improved Component Tree Based Approach to User-Intention Guided Text Extraction from Natural Scene Images

2013 ◽  
Author(s):  
Lei Sun ◽  
Qiang Huo
Keyword(s):  
Natural Scene ◽  
User Intention ◽  
Text Extraction ◽  
Natural Scene Images ◽  
Component Tree

scholarly journals Text extraction from natural scene images using Renyi entropy

2019 ◽  
Vol 2019 (8) ◽  
pp. 5397-5406
Author(s):  
Angia Venkatesan Karpagam ◽  
Mohan Manikandan
Keyword(s):  
Renyi Entropy ◽  
Rényi Entropy ◽  
Natural Scene ◽  
Text Extraction ◽  
Natural Scene Images

Text detection in natural scene images with user-intention

2013 ◽  
Author(s):  
Liuan Wang ◽  
Yutaka Katsuyama ◽  
Wei Fan ◽  
Yuan He ◽  
Jun Sun ◽  
...  
Keyword(s):  
Text Detection ◽  
Natural Scene ◽  
User Intention ◽  
Natural Scene Images

scholarly journals Urdu text in natural scene images: a new dataset and preliminary text detection

2021 ◽  
Vol 7 ◽  
pp. e717
Author(s):  
Hazrat Ali ◽  
Khalid Iqbal ◽  
Ghulam Mujtaba ◽  
Ahmad Fayyaz ◽  
Mohammad Farhad Bulbul ◽  
...  
Keyword(s):  
Text Detection ◽  
Support Vector ◽  
Research Use ◽  
Natural Scene ◽  
Text Extraction ◽  
Second Stage ◽  
Maximally Stable Extremal Region ◽  
Interesting Task ◽  
Candidate Regions ◽  
Natural Scene Images

Text detection in natural scene images for content analysis is an interesting task. The research community has seen some great developments for English/Mandarin text detection. However, Urdu text extraction in natural scene images is a task not well addressed. In this work, firstly, a new dataset is introduced for Urdu text in natural scene images. The dataset comprises of 500 standalone images acquired from real scenes. Secondly, the channel enhanced Maximally Stable Extremal Region (MSER) method is applied to extract Urdu text regions as candidates in an image. Two-stage filtering mechanism is applied to eliminate non-candidate regions. In the first stage, text and noise are classified based on their geometric properties. In the second stage, a support vector machine classifier is trained to discard non-text candidate regions. After this, text candidate regions are linked using centroid-based vertical and horizontal distances. Text lines are further analyzed by a different classifier based on HOG features to remove non-text regions. Extensive experimentation is performed on the locally developed dataset to evaluate the performance. The experimental results show good performance on test set images. The dataset will be made available for research use. To the best of our knowledge, the work is the first of its kind for the Urdu language and would provide a good dataset for free research use and serve as a baseline performance on the task of Urdu text extraction.

scholarly journals Text Extraction from Natural Scene Images using OpenCV and CNN

2019 ◽  
Vol 11 (9) ◽  
pp. 48-54
Author(s):  
Vaibhav Goel ◽  
◽  
Vaibhav Kumar ◽  
Amandeep Singh Jaggi ◽  
Preeti Nagrath
Keyword(s):  
Natural Scene ◽  
Text Extraction ◽  
Natural Scene Images
Sign in / Sign up

Export Citation Format

Share Document