Skip to content
Research Article Open access CC BY 4.0

A Hybridized Feature Extraction Model for Offline Yorùbá Document Recognition

Jumoke F. Ajao, Rafiu M. Isiaka, Ronke S. Babatunde, Ajao, Jumoke F.

Asian Journal of Research in Computer Science · pp. 42–59 · Published 16 May 2023

10.9734/ajrcos/2023/v15i4329

Abstract

Document recognition is required to convert handwritten and text documents into digital equivalents, making them more easily accessible and convenient to store. This study combined feature extraction techniques for recognizing Yorùbá documents in an effort to preserve the cultural values and heritages of the Yorùbá people. Ten Yorùbá documents were acquired from Kwara State University’s Library, and ten indigenous literate writers wrote the handwritten version of the documents. These were digitized using HP Scanjet300 and pre-processed. The pre-processed image served as input to the Local Binary Pattern, Speeded-Up-Robust-Features and Histogram of Gradient. The combined extracted feature vectors were input into the Genetic Algorithm. The reduced feature vector was fed into Support Vector Machine. A 10-folds cross-validation was used to train the model: LBP-GA, SURF-GA, HOG-GA, LBP-SURF-GA, HOG-SURF-GA, LBP-HOG-GA and LBP-HOG-SURF-GA. LBP-HOG-SURF-GA for Yorùbá printed text gave 90.0% precision, 90.3% accuracy and 15.5% FPR. LBP-HOG-SURF-GA for Handwritten Yorùbá document showed 80.9% precision, 82.6% accuracy and 20.4% (FPR) LBP-HOG-SURF-GA for CEDAR gave 98.0% precision, 98.4% accuracy and 2.6% FPR. LBP-HOG-SURF-GA for MNIST gave 99% precision, 99.5% accuracy, 99.0% and 1.1% FPR. The results of the hybridized feature extractions (LBP-HOG-SURF) demonstrated that the proposed work improves significantly on the various classification metrics.

Yorùbá feature extraction document recognition feature selection language processing machine learning

References (30)

  1. 1 Histograms of Oriented Gradients for Human Detection [DOI]
  2. 2 Speeded-Up Robust Features (SURF) [DOI]
  3. 3 Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond [DOI]
  4. 4 2D object recognition: a comparative analysis of SIFT, SURF and ORB feature descriptors [DOI]
  5. 5 Hybrid CNN-SVM Classifier for Handwritten Digit Recognition [DOI]
  6. 6 Arabic handwriting recognition system using convolutional neural network [DOI]
  7. 7 A GA based hierarchical feature selection approach for handwritten word recognition [DOI]
  8. 8 A genetic Algorithm-Based feature selection
  9. 9 Challenges in Arabic Natural Language Processing [DOI]
  10. 10 Novel Deep Convolutional Neural Network-Based Contextual Recognition of Arabic Handwritten Scripts [DOI]
  11. 11 GA-SURF: A new Speeded-Up robust feature extraction algorithm for multispectral images based on geometric algebra [DOI]
  12. 12 Vehicle make and model recognition using sparse representation and symmetrical SURFs [DOI]
  13. 13 Classification of Handwritten Devanagari Number – An analysis of Pattern Recognition Tool using Neural Network and CNN [DOI]
  14. 14 Gradient histogram: Thresholding in a region of interest for edge detection [DOI]
  15. 15 Performance evaluation of feature extraction techniques in MR-Brain image classification system [DOI]
  16. 16 Islanding detection method based on image classification technique using histogram of oriented gradient features [DOI]
  17. 17 Handwriting Analysis based on Histogram of Oriented Gradient for Predicting Personality traits using SVM [DOI]
  18. 18 Face recognition attendance system using Local Binary Pattern (LBP) [DOI]
  19. 19 Hybridizing Evolutionary Computation and Deep Neural Networks: An Approach to Handwriting Recognition Using Committees and Transfer Learning [DOI]
  20. 20 Support Vector Machine [DOI]
  21. 21 On developing handwritten character image database for Malayalam language script [DOI]
  22. 22 Learning to Spell in Arabic: The Impact of Script-Specific Visual-Orthographic Features [DOI]
  23. 23 Computational Linguistics, Speech and Image Processing for Arabic Language [DOI]
  24. 24 Vehicle make and model recognition using sparse representation and symmetrical SURFs [DOI]
  25. 25 The hybrid feature extraction method for classification of adolescence idiopathic scoliosis using Evolving Spiking Neural Network [DOI]
  26. 26 DEVELOPMENT OF AN IMPROVED DATABASE FOR YORUBA HANDWRITTEN CHARACTER [DOI]
  27. 27 TRANSFER LEARNING BASED OFFLINE YORÙBÁ HANDWRITTEN CHARACTER RECOGNITION SYSTEM [DOI]
  28. 28 Database corpus for Yoruba handwriting [DOI]
  29. 29 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'2001)
  30. 30 Computer Vision and Image Understanding [DOI]

Cited by 0

No indexed citations yet.

Related research

Article metrics

Real usage data collected on this platform.

13

Page views

0

PDF downloads

1

Outbound clicks

0

Citations

Views over time

Views by country

Approximate, from request IP at view time — not citizenship or institution. Countries with fewer than 5 views are grouped as "Other".

Traffic sources

Referring site, by host.

Views and downloads exclude known bots/crawlers. Citations combines this platform's own DOI-resolved index with each external source's own reported total — see Cited by above for individually listed citing works. Last refreshed 0 seconds ago.