Abstract

Handwritten character recognition (HCR) has become a growing research, owing to its several applications in processing the images, recognizing the patterns, communication technologies, etc. However, HCR is affected because of different styles of writers, or even if one writer has a different type of writing style according to the situation. Therefore, it is a tedious task to efficiently extract and recognize the digits or characters in the document/image. In that, HCR and classification is the toughest task in the field of pattern recognizing due to the various writing instruments and styles obtained from dissimilar widths, orientations, and sizes. In this work, multi-class support vector machine (MSVM) classifier is utilized for character identification. At first, the handwritten images are developed from real-time and Chars74k datasets, and then, pre-processing is executed for character image enhancement using Binarization. Moreover, the discrete lines are segmented by applying the modified whale optimization algorithm (MWOA)-based Otsu thresholding technique. The proposed MWOA-MSVM gained better evaluation outcomes at 99.2% accuracy, 98.43% precision, 98.99% recall and 97.54% F1-score in HCR when compared to the other techniques that were, hybrid feature-based long short-term memory (LSTM) and stacked sparse auto encoder.

Keyword

Handwritten character, Binarization, Adaptive threshold, Fitness function, MWO-OTSU, Steerable pyramid transform, Classifier.

Cite this article

Ganeshaiah KP, Hegde V

Refference

[1][1]Tong G, Dong M, Sun X, Song Y. Natural scene text detection and recognition based on saturation-incorporated multi-channel MSER. Knowledge-Based Systems. 2022; 250:109040.

[2][2]Moudgil A, Singh S, Gautam V, Rani S, Shah SH. Handwritten Devanagari manuscript characters recognition using capsnet. International Journal of Cognitive Computing in Engineering. 2023; 4:47-54.

[3][3]Alwaqfi YM, Mohamad M, Al-taani AT. Generative adversarial network for an improved Arabic handwritten characters recognition. International Journal of Advances in Soft Computing & Its Applications. 2022; 14(1):1776-95.

[4][4]Anggraeny FT, Via YV, Mumpuni R. Image preprocessing analysis in handwritten Javanese character recognition. Bulletin of Electrical Engineering and Informatics. 2023; 12(2):860-7.

[5][5]Chen X, Jin G. Preschool education interactive system based on smart sensor image recognition. Wireless Communications and Mobile Computing. 2022; 2022:1-11.

[6][6]Ahsan S, Shah TN, Sarwar TB, Miah MS, Bhowmik A. A machine learning approach for Bengali handwritten vowel character recognition. IAES International Journal of Artificial Intelligence. 2022; 11(3):1143-52.

[7][7]Naiemi F, Ghods V, Khalesi H. Scene text detection and recognition: a survey. Multimedia Tools and Applications. 2022; 81(14):20255-90.

[8][8]Rahman MM, Akhand MA, Islam S, Shill PC, Rahman MH. Bangla handwritten character recognition using convolutional neural network. International Journal of Image, Graphics and Signal Processing. 2015; 7(8):42-9.

[9][9]Das M, Panda M, Dash S. Enhancing the power of CNN using data augmentation techniques for Odia handwritten character recognition. Advances in Multimedia. 2022; 2022:1-13.

[10][10]Guo Z, Zhou Z, Liu B, Li L, Jiao Q, Huang C, et al. An improved neural network model based on inception-v3 for oracle bone inscription character recognition. Scientific Programming. 2022; 2022:1-8.

[11][11]Dan Y, Zhu Z, Jin W, Li Z. PF-ViT: parallel and fast vision transformer for offline handwritten Chinese character recognition. Computational Intelligence and Neuroscience. 2022; 2022:1-11.

[12][12]Motamedisedeh O, Zagia F, Alaei A. A new optimization approach to improve an ensemble learning model: application to Persian/Arabic handwritten character recognition. In international conference on document analysis and recognition 2023 (pp. 180-94). Cham: Springer Nature Switzerland.

[13][13]Saqib N, Haque KF, Yanambaka VP, Abdelgawad A. Convolutional-neural-network-based handwritten character recognition: an approach with massive multisource data. Algorithms. 2022; 15(4):1-25.

[14][14]Sahay R, Coustaty M. An enhanced prototypical network architecture for few-shot handwritten Urdu character recognition. IEEE Access. 2023; 11:33682-96.

[15][15]Tan YF, Connie T, Goh MK, Teoh AB. A pipeline approach to context-aware handwritten text recognition. Applied Sciences. 2022; 12(4):1-17.

[16][16]Hu M, Qu X, Huang J, Wu X. An end-to-end classifier based on CNN for in-air handwritten-Chinese-character recognition. Applied Sciences. 2022; 12(14):1-12.

[17][17]Albattah W, Albahli S. Intelligent Arabic handwriting recognition using different standalone and hybrid CNN architectures. Applied Sciences. 2022; 12(19):1-23.

[18][18]Zhang Y, Li Z, Yang Z, Yuan B, Liu X. Air-GR: an over-the-air handwritten character recognition system based on coordinate correction YOLOv5 algorithm and LGR-CNN. Sensors. 2023; 23(3):1-23.

[19][19]Geng S, Zhu Z, Wang Z, Dan Y, Li H. LW-ViT: the lightweight vision transformer model applied in offline handwritten Chinese character recognition. Electronics. 2023; 12(7):1-10.

[20][20]Li Y, Yang Q, Chen Q, Hu B, Wang X, Ding Y, et al. Fast and robust online handwritten Chinese character recognition with deep spatial & contextual information fusion network. IEEE Transactions on Multimedia. 2022: 2140-52.

[21][21]Chandure S, Inamdar V. Handwritten MODI character recognition using transfer learning with discriminant feature analysis. IETE Journal of Research. 2023; 69(5):2584-94.

[22][22]Rasheed A, Ali N, Zafar B, Shabbir A, Sajid M, Mahmood MT. Handwritten Urdu characters and digits recognition using transfer learning and augmentation with AlexNet. IEEE Access. 2022; 10:102629-45.

[23][23]Islam MS, Rahman MM, Rahman MH, Rivolta MW, Aktaruzzaman M. RATNet: a deep learning model for Bengali handwritten characters recognition. Multimedia Tools and Applications. 2022; 81(8):10631-51.

[24][24]Ahmed G, Alyas T, Iqbal MW, Ashraf MU, Alghamdi AM, Bahaddad AA, et al. Recognition of Urdu handwritten alphabet using convolutional neural network (CNN). Computers, Materials & Continua. 2022; 73(2):2967-84.

[25][25]Rani NS, BR P. Robust recognition technique for handwritten Kannada character recognition using capsule networks. International Journal of Electrical & Computer Engineering (2088-8708). 2022; 12(1):383-91.

[26][26]Ramteke SP, Gurjar AA, Deshmukh DS. A novel weighted SVM classifier based on SCA for handwritten Marathi character recognition. IETE Journal of Research. 2022; 68(2):845-57.

[27][27]Pughazendi N, Harikrishnan M, Khilar R, Sharmila L. Optical handwritten character recognition for Tamil language using CNN-VGG-16 model with RF classifier. Optical and Quantum Electronics. 2023; 55(11):976.

[28][28]Prashanth DS, Mehta RV, Ramana K, Bhaskar V. Handwritten Devanagari character recognition using modified Lenet and Alexnet convolution neural networks. Wireless Personal Communications. 2022; 122(1):349-78.

[29][29]Elkhayati M, Elkettani Y. UnCNN: a new directed CNN model for isolated Arabic handwritten characters recognition. Arabian Journal for Science and Engineering. 2022; 47(8):10667-88.

[30][30]Kathigi A, Honnamachanahalli KK. Handwritten character recognition using skewed line segmentation method and long short term memory network. International Journal of System Assurance Engineering and Management. 2022; 13(4):1733-45.

[31][31]Dey R, Balabantaray RC, Mohanty S. Sliding window based off-line handwritten text recognition using edit distance. Multimedia Tools and Applications. 2022; 81(16):22761-88.

[32][32]Arun M, Arivazhagan S. A unified feature descriptor for generic character recognition based on zoning and histogram of gradients. Neural Computing and Applications. 2022; 34(14):12223-34.

[33][33]Ganeshaiah KP, Hegde V. Handwritten character recognition using morlet stacked sparse auto encoder based feature dimension reduction. International Journal of Intelligent Engineering & Systems. 2023; 16(2):454-63.

[34][34]Elaraby N, Barakat S, Rezk A. A novel Siamese network for few/zero-shot handwritten character recognition tasks. Computers, Materials & Continua. 2023; 74(1):1837-54.

[35][35]Siddanna SR, Kumar A, Dubey A, Govind B, Dixit D. Kannada handwritten character recognition using hybrid RNN. International Journal of Progressive Research in Engineering Management and Science. 2022; 2(7):5-9.

[36][36]Lee SH, Yu WF, Yang CS. ILBPSDNet: based on improved local binary pattern shallow deep convolutional neural network for character recognition. IET Image Processing. 2022; 16(3):669-80.

[37][37]Zanwar SR, Bhosale YH, Bhuyar DL, Ahmed Z, Shinde UB, Narote SP. English handwritten character recognition based on ensembled machine learning. Journal of the Institution of Engineers (India): Series B. 2023:1-5.

[38][38]Ali AA, Mallaiah S. Intelligent handwritten recognition using hybrid CNN architectures based-SVM classifier with dropout. Journal of King Saud University-Computer and Information Sciences. 2022; 34(6):3294-300.

[39][39]Kavitha BR, Srimathi CB. Benchmarking on offline handwritten Tamil character recognition using convolutional neural networks. Journal of King Saud University-Computer and Information Sciences. 2022; 34(4):1183-90.

[40][40]Khan MM, Uddin MS, Parvez MZ, Nahar L. A squeeze and excitation ResNeXt-based deep learning model for Bangla handwritten compound character recognition. Journal of King Saud University-Computer and Information Sciences. 2022; 34(6):3356-64.

[41][41]Sonthi VK, N K. An intelligent Telugu handwritten character recognition using multi-objective mayfly optimization with deep learning–based DenseNet model. ACM Transactions on Asian and Low-Resource Language Information Processing. 2023; 22(3):1-16.

[42][42]Abdalla PA, Qadir AM, Shakor MY, Saeed AM, Jabar AT, Salam AA, et al. A vast dataset for Kurdish handwritten digits and isolated characters recognition. Data in Brief. 2023; 47:1-13.

[43][43]Dan Y, Li Z. Particle swarm optimization-based convolutional neural network for handwritten Chinese character recognition. Journal of Advanced Computational Intelligence and Intelligent Informatics. 2023; 27(2):165-72.

[44][44]Omayio EO, Indu S, Panda J. Word spotting and character recognition of handwritten Hindi scripts by integral histogram of oriented displacement (IHOD) descriptor. Multimedia Tools and Applications. 2023:1-28.

[45][45]Maray M, Al-onazi BB, Alzahrani JS, Alshahrani SM, Alotaibi N, Alazwari S, et al. Sailfish optimizer with deep transfer learning-enabled arabic handwriting character recognition. Computers, Materials & Continua. 2023; 74(3):5467-82.

[46][46]Alheraki M, Al-matham R, Al-khalifa H. Handwritten Arabic character recognition for children writing using convolutional neural network and stroke identification. Human-Centric Intelligent Systems. 2023:1-13.

[47][47]https://www.kaggle.com/datasets/supreethrao/chars74kdigitalenglishfont?select=EnglishFnt.tgz . Accessed 20 October 2023.

[48][48]Jadhav S, Inamdar V. Convolutional neural network and histogram of oriented gradient based invariant handwritten MODI character recognition. Pattern Recognition and Image Analysis. 2022; 32(2):402-18.

[49][49]Alemayoh TT, Shintani M, Lee JH, Okamoto S. Deep-learning-based character recognition from handwriting motion data captured using IMU and force sensors. Sensors. 2022; 22(20):1-15.

[50][50]Alwagdani MS, Jaha ES. Deep learning-based child handwritten Arabic character recognition and handwriting discrimination. Sensors. 2023; 23(15):1-21.

[51][51]Gader TB, Echi AK. Attention-based deep learning model for Arabic handwritten text recognition. Machine Graphics and Vision. 2022; 31(1/4):49-73.

[52][52]Niharmine L, Outtaj B, Azouaoui A. Tifinagh handwritten character recognition using optimized convolutional neural network. International Journal of Electrical & Computer Engineering (2088-8708). 2022; 12(4):4164-71.