2017 International Conference on Frontiers of Information Technology (FIT) 2017
DOI: 10.1109/fit.2017.00024
|View full text |Cite
|
Sign up to set email alerts
|

Classification of Urdu Ligatures Using Convolutional Neural Networks - A Novel Approach

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
7
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
7
3

Relationship

1
9

Authors

Journals

citations
Cited by 18 publications
(7 citation statements)
references
References 19 publications
0
7
0
Order By: Relevance
“…They reported good results on both CLE and UPTI. A similar kind of study on 38K ligatures images for 98 classes scanned from the book, was done by Javed et al [61], they used fixedsize ligatures of 55 × 55 pixels and reported an accuracy of 95%. Also, Rafeeq et al [21] showed that a deep neural network and clustering of ligatures significantly enhances the classification accuracy on the custom generated a dataset of 17010 Urdu ligatures from CLE [22] in 2018.…”
Section: Hybrid/end-to-end Approachesmentioning
confidence: 80%
“…They reported good results on both CLE and UPTI. A similar kind of study on 38K ligatures images for 98 classes scanned from the book, was done by Javed et al [61], they used fixedsize ligatures of 55 × 55 pixels and reported an accuracy of 95%. Also, Rafeeq et al [21] showed that a deep neural network and clustering of ligatures significantly enhances the classification accuracy on the custom generated a dataset of 17010 Urdu ligatures from CLE [22] in 2018.…”
Section: Hybrid/end-to-end Approachesmentioning
confidence: 80%
“…They developed four separate recognizers to accommodate varied text sizes for this objective. Reference [10] suggested CNN recognize Nastaleeq font style ligatures. The technique analyzed 18,000 ligatures over 98 classes and achieved a recognition rate of 95%.…”
Section: Holistic Approachmentioning
confidence: 99%
“…Among different identification techniques, Sabbour and Shafait in [11] use object descriptors to recognize ligatures in the UPTI database, resulting in an 89% recognition rate. On the UPTI database [12][13][14], many implicit partition-based techniques have also been calculated. In such methods, the learning limitations are determined after the ground truth transcription, and the pictures of text lines are provided to the learning algorithm.…”
Section: Literature Reviewmentioning
confidence: 99%