2020
DOI: 10.1007/s12652-020-02528-4
|View full text |Cite
|
Sign up to set email alerts
|

Language identification from multi-lingual scene text images: a CNN based classifier ensemble approach

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 9 publications
(4 citation statements)
references
References 42 publications
0
4
0
Order By: Relevance
“…For MLe2e, a significant performance enhancement is obtained using our technique. Our approach outperforms all the deep learning approaches 7,23,41 . However, the result is competitive with the performance obtained by Chakraborty et al 23 Tables 8 and 9 report the class‐wise accuracy of the test labels of Indic‐FSL2023 and MLe2e using the proposed model based on their best paradigm's performance with the standard CNN models.…”
Section: Experimental Analysismentioning
confidence: 60%
See 3 more Smart Citations
“…For MLe2e, a significant performance enhancement is obtained using our technique. Our approach outperforms all the deep learning approaches 7,23,41 . However, the result is competitive with the performance obtained by Chakraborty et al 23 Tables 8 and 9 report the class‐wise accuracy of the test labels of Indic‐FSL2023 and MLe2e using the proposed model based on their best paradigm's performance with the standard CNN models.…”
Section: Experimental Analysismentioning
confidence: 60%
“…Our approach outperforms all the deep learning approaches. 7,23,41 However, the result is competitive with the performance obtained by Chakraborty et al 23 Tables 8 and 9 report the class-wise accuracy of the test labels of Indic-FSL2023 and MLe2e using the proposed model based on their best paradigm's performance with the standard CNN models. Our model, with fewer samples in some categories gives the best score compared to the traditional CNN.…”
Section: -Way 3-waymentioning
confidence: 77%
See 2 more Smart Citations