Abstract

Automatic handwritten digit recognition provides significant contributions towards many real-time applications starting from the vehicle’s number plate to doctor’s prescription. However, the real challenge in these applications highly depends on the factors such as accuracy rate and time. Considering this significance, a novel handwritten digit recognition method is proposed without the adoption of any pre-processing steps like noise prediction, segmentation, and feature selection/extraction. The purpose of eliminating these preliminary steps is to reduce the computational complexity as the utilization of the Deep Learning (DL) approach helps to reduce the computational complexity of directly performing classification. Here, a novel Layered Convolutional Neural Networks (LCNN) model with an efficient Squirrel Optimizer (LCNN-SO) is modeled to attain better classification and global solution during the handwritten digit recognition. This cascaded model is a simple emerging DL-based one with multiple layers. The proposed LCNN-SO model adds multiple layers over the CNN model to focus on accurate classification and optimizing the layers to achieve better results using squirrel optimizer. The layered stages of CNN with the optimizer are trained and constructed to recognize the various kinds of digit isolation over the input data. Here, Special Database 1 and Special Database 2 are used to analyze and classify the input data for providing non-segregated digits for further processing in real-time applications. The simulation is carried out in MATLAB 2018 environment and metrics like accuracy, elapsed time, precision, recall, and F-measure are evaluated. The outcomes of these metrics are 98.5%, 99%, 99.5%, and 99.50% respectively. The anticipated LCNN-SO model gives better prediction accuracy when compared to existing approaches like Convolutional Neural Networks + Long-Short Term Memory (CNN+LSTM), pre-trained Convolutional Neural Networks + Multi-Layered Perceptron (CNN+MLP), pre-trained CNN+LSTM, pre-trained Convolutional Neural Networks +Support Vector Machine (CNN+SVM), Dense trajectories with Histogram of Gradients (HoG), and Convolutional Neural Networks + Orthogonal Learning Particle Swarm Optimization (OLPSO) respectively.

Keyword

Classification, Global convergence, Layered-CNN, Optimization and Recognition accuracy.

Cite this article

Senthil T, Rajan C, Deepika J

Refference

[1][1]Sampath AK, Gomathi N. Fuzzy-based multi-kernel spherical support vector machine for effective handwritten character recognition. Sādhanā. 2017; 42:1513-25.

[2][2]Bhowmik S, Malakar S, Sarkar R, Basu S, Kundu M, Nasipuri M. Off-line Bangla handwritten word recognition: a holistic approach. Neural Computing and Applications. 2019; 31:5783-98.

[3][3]Tamen Z, Drias H, Boughaci D. An efficient multiple classifier system for Arabic handwritten words recognition. Pattern Recognition Letters. 2017; 93:123-32.

[4][4]Sahoo S, Nandi SK, Barua S, Bhowmik S, Malakar S, Sarkar R. Handwritten bangla word recognition using negative refraction based shape transformation. Journal of Intelligent & Fuzzy Systems. 2018; 35(2):1765-77.

[5][5]Vellasques E, Oliveira LS, Britto AS, Koerich AL, Sabourin R. Filtering segmentation cuts for digit string recognition. Pattern Recognition. 2008; 41(10):3044-53.

[6][6]Ribas FC, Oliveira LS, Britto AS, Sabourin R. Handwritten digit segmentation: a comparative study. International Journal on Document Analysis and Recognition. 2013; 16(2):127-37.

[7][7]Ciresan D. Avoiding segmentation in multi-digit numeral string recognition by combining single and two-digit classifiers trained without negative examples. In international symposium on symbolic and numeric algorithms for scientific computing 2008 (pp. 225-30). IEEE.

[8][8]Hochuli AG, Oliveira LS, Britto AS, Sabourin R. Handwritten digit segmentation: is it still necessary? Pattern Recognition. 2018; 78:1-11.

[9][9]Viola P, Jones MJ. Robust real-time face detection. International Journal of Computer Vision. 2004; 57(2):137-54.

[10][10]Zhang K, Zhang Z, Li Z, Qiao Y. Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Processing Letters. 2016; 23(10):1499-503.

[11] [11]Coates A, Ng AY. Learning feature representations with k-means. In neural networks: tricks of the trade 2012 (pp. 561-80). Springer, Berlin, Heidelberg.

[12][12]Lawrence S, Giles CL, Tsoi AC, Back AD. Face recognition: a convolutional neural-network approach. IEEE Transactions on Neural Networks. 1997; 8(1):98-113.

[13][13]Tan X, Chen S, Zhou ZH, Zhang F. Recognizing partially occluded, expression variant faces from single training image per person with SOM and soft k-NN ensemble. IEEE Transactions on Neural Networks. 2005; 16(4):875-86.

[14][14]Zhao Z, Zhang X, Fang Y. Stacked multilayer self-organizing map for background modeling. IEEE Transactions on Image Processing. 2015; 24(9):2841-50.

[15][15]Dasgupta J, Bhattacharya K, Chanda B. A holistic approach for off-line handwritten cursive word recognition using directional feature based on arnold transform. Pattern Recognition Letters. 2016; 79:73-9.

[16][16]Jino PJ, Balakrishnan K, Bhattacharya U. Offline handwritten Malayalam word recognition using a deep architecture. In soft computing for problem solving 2019 (pp. 913-25). Springer, Singapore.

[17][17]Barua S, Malakar S, Bhowmik S, Sarkar R, Nasipuri M. Bangla handwritten city name recognition using gradient-based feature. In proceedings of the 5th international conference on frontiers in intelligent computing: theory and applications 2017 (pp. 343-52). Springer, Singapore.

[18][18]Sueiras J, Ruiz V, Sanchez A, Velez JF. Offline continuous handwriting recognition using sequence to sequence neural networks. Neurocomputing. 2018; 289:119-28.

[19][19]Bhowmik TK, Parui SK, Roy U. Discriminative HMM training with GA for handwritten word recognition. In international conference on pattern recognition 2008 (pp. 1-4). IEEE.

[20][20]Saha C, Faisal RH, Rahman MM. Bangla handwritten digit recognition using an improved deep convolutional neural network architecture. In international conference on electrical, computer and communication engineering 2019 (pp. 1-6). IEEE.

[21][21]http://yann.lecun.com/exdb/publis/index.html#lecun-98. Accessed 10 March 2021.

[22][22]LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proceedings of the IEEE. 1998; 86(11):2278-324.

[23][23]Lu Y, Yi S, Zeng N, Liu Y, Zhang Y. Identification of rice diseases using deep convolutional neural networks. Neurocomputing. 2017; 267:378-84.

[24][24]Guo Y, Liu Y, Oerlemans A, Lao S, Wu S, Lew MS. Deep learning for visual understanding: a review. Neurocomputing. 2016; 187:27-48.

[25][25]Vernes K. Gliding performance of the northern flying squirrel (Glaucomys sabrinus) in mature mixed forest of eastern Canada. Journal of Mammalogy. 2001; 82(4):1026-33.

[26][26]Bag S, Harit G. A survey on optical character recognition for Bangla and Devanagari scripts. Sadhana. 2013; 38(1):133-68.

[27][27]Elleuch M, Maalej R, Kherallah M. A new design based-SVM of the CNN classifier architecture with dropout for offline Arabic handwritten recognition. Procedia Computer Science. 2016; 80:1712-23.

[28][28]Jauhiainen T, Lui M, Zampieri M, Baldwin T, Lindén K. Automatic language identification in texts: a survey. Journal of Artificial Intelligence Research. 2019; 65:675-782.

[29][29]Kumar M, Jindal MK, Sharma RK, Jindal SR. Character and numeral recognition for non-Indic and Indic scripts: a survey. Artificial Intelligence Review. 2019; 52(4):2235-61.

[30][30]Al-Thubaity A, Alkhalifa A, Almuhareb A, Alsanie W. Arabic diacritization using bidirectional long short-term memory neural networks with conditional random fields. IEEE Access. 2020; 8:154984-96.

[31][31]Mahmood Z, Safder I, Nawab RM, Bukhari F, Nawaz R, Alfakeeh AS, et al. Deep sentiments in Roman Urdu text using recurrent convolutional neural network model. Information Processing & Management. 2020; 57(4).

[32][32]Husnain M, Saad MMM, Mumtaz S, Jhanidr MZ, Coustaty M, Muzzamil LM, et al. Recognition of Urdu handwritten characters using convolutional neural network. Applied Sciences. 2019; 9(13):1-21.

[33][33]Parija B, Pattanayak R, Tripathy SK. Faults classification in a microgrid using decision tree technique and support vector machine. In second international conference on green computing and internet of things 2018 (pp. 145-8). IEEE.

[34][34]Bahrani A, Majidi B, Eshghi M. Coral reef management in persian gulf using deep convolutional neural networks. In international conference on pattern recognition and image analysis 2019 (pp. 200-4). IEEE.

[35][35]Bossaghzadeh A. Improving persian digit recognition by combining deep neural networks and SVM and Using PCA. In international conference on machine vision and image processing 2020 (pp. 1-5). IEEE.

[36][36]Wu S, Wei W, Zhang L. Comparison of machine learning algorithms for handwritten digit recognition. In international symposium on intelligence computation and applications 2017 (pp. 532-42). Springer, Singapore.