2019
DOI: 10.1109/access.2019.2936363
|View full text |Cite
|
Sign up to set email alerts
|

A Scale and Rotation Invariant Urdu Nastalique Ligature Recognition Using Cascade Forward Backpropagation Neural Network

Abstract: In the emerging age of technologies, machines are becoming more and more skilled and capable just like humans. Despite the fact that machines do not have their own intelligence, but still due to advancement in Artificial Intelligence (AI), machines are rapidly advancing. The area of Pattern Recognition (PR) deals with bringing enhancements to identify obscure patterns corresponding to specific classes. Optical Character Recognition (OCR) is a subfield of PR which deals with the recognition of characters. A gre… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0
2

Year Published

2020
2020
2022
2022

Publication Types

Select...
6
1

Relationship

1
6

Authors

Journals

citations
Cited by 11 publications
(6 citation statements)
references
References 53 publications
(37 reference statements)
0
4
0
2
Order By: Relevance
“…Table III shows the performance comparison of the method [18] from the literature with the proposed method using publicly available benchmark data sets. We have implemented the method proposed in [18] to test its performance with a few of the benchmark data sets [7]. Even though we have implemented the method proposed in [18], the implementation may not meet the optimizations as per the expectations of the original author [16].…”
Section: Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…Table III shows the performance comparison of the method [18] from the literature with the proposed method using publicly available benchmark data sets. We have implemented the method proposed in [18] to test its performance with a few of the benchmark data sets [7]. Even though we have implemented the method proposed in [18], the implementation may not meet the optimizations as per the expectations of the original author [16].…”
Section: Resultsmentioning
confidence: 99%
“…This paper reported an average recognition accuracy of 98.89% using four image data sets from the Brodatz database. K. U. Rehman et al in the paper [7] proposed a feature extraction technique for character recognition using existing moment based features such as raw moments, central moments, hu moments, and Zernike moments and reported a success rate of 96.922% using Urdu proprietary data set. L. A. Torres-Méndez et al, in the paper [8] presented a translation, rotation, and scale invariant method for object recognition by extracting topological object characteristics with the help of novel coding of the normalized moment of inertia.…”
Section: Related Workmentioning
confidence: 99%
“…Henceforth, for furnishing the feature vector, only those mathematical and computational models are most apt which are sensitive to the relative positioning of component nucleotide bases within genomic sequences. It is a critical factor in formulating yielding and assiduous feature sets 18 26 . Since Hahn moments require two-dimensional data, therefore, the genomic sequences are converted into a two-dimensional notation S’ of size k*k which stores the same information as S but in a two-dimensional form such that and …”
Section: Methodsmentioning
confidence: 99%
“…Beberapa metode yang dapat digunakan untuk proses pengkalsifikasian tulisan dan fitur ekstraksi dalam machine learning yaitu seperti Support Vector Machine (SVM) dan Artificial Neural Network (ANN) [13]. Penelitian terkait Urdu Nastalique Ligature Recognition menggunakan Backpropagation Neural Network (BPP) [14], penelitian selanjutnya terkait Signature Recognition menggunakan metode ANN sebagai classifier [15], pengenalan karakter urdu script menggunakan metode BPP menghasilkan akurasi 92% [5] dan penelitian [16] terkait recognition of offline Tulu Handwritten Scripts juga menggunakan metode machine learning. Selain menggunakan metode machine learning, beberapa penelitian menggunakan pemrosesan yang lebih kompleks sehingga membutuhkan metode yang lebih advance yaitu deep learning.…”
Section: Pendahuluanunclassified