Abstract
The overlapped handwritten digit classification is a global challenge and a significant measure to assess the network recognition ability ratio. Most efficient models have been designed based on convolutional neural networks (CNN) for effective image classification and digit identification. Subsequently, multiple CNN models have inadequate accuracy because of high degree parameter dimensions that lead to abnormal digit detection error rates and computation complexity. We propose a Deep Digit Recognition Network (DDRNet) based on Deep ConvNets to minimize the number of parameters and features to keep the model light while maximizing the accuracy with an adaptive voting (AV) scheme for digit recognition. The individual digit is identified by CNN, and uncertain digits or strings are identified by Deep Convolutional Network (DCN) with AV scheme through Voting-Weight Conditional Random Field (VWCRF) strategy. These methods originated with the YOLO algorithm. The simulations show that our DDRNet approach achieves an accuracy of 99.4% without error fluctuations, in a stable state with less than 15 epochs contrast with state-of-art approaches. Additionally, specific convolution techniques (SqueezeNet, batch normalization) and image augmentation techniques (dropout, back-propagation, and an optimum learning rate) were examined to assess the system performance based on MNIST dataset (available at: http://yann.lecun.com/exdb/mnist/).
Similar content being viewed by others
References
Lu, Z.; Chi, Z.; Siu, W.-C.; Shi, P.: A background-thinning-based approach for separating and recognizing connected handwritten digit strings. Pattern Recogn. 32(6), 921–933 (1999)
Guha, A.; Samanta, D.; Banerjee, A.; Agarwal, D.: A deep learning model for information loss prevention from multi-page digital documents. IEEE Access 1 (2021). https://doi.org/10.1109/ACCESS.2021.3084841
Teow, M.Y.W.: A minimal convolutional neural network for handwritten digit recognition 171–176 (2017)
Gomathy, V.; Padhy, N.; Samanta, D.; Sivaram, M.; Jain, V.; Amiri, I.S.: Malicious node detection using heterogeneous cluster based secure routing protocol (HCBS) in wireless adhoc sensor networks, J. Amb. Intell. Human. Comput. 11(11), 4995–5001 (2020). https://doi.org/10.1007/s12652-020-01797-3. http://link.springer.com/10.1007/s12652-020-01797-3
Hossain, M.A.; Samanta, D.; Sanyal, G.; Extraction of panic expression depending on lip detection 137–141 (2012). https://doi.org/10.1109/ICCS.2012.35
Maheswari, M.; Geetha, S.; Kumar, S.S.; Karuppiah, M.; Samanta, D.; Park, Y.: Pevrm: Probabilistic evolution based version recommendation model for mobile applications. IEEE Access 9, 20819–20827 (2021). https://doi.org/10.1109/ACCESS.2021.3053583
Mekala, M.; Park, W.; Dhiman, G.; Srivastava, G.; Park, J.H.; Jung, H.-Y.: Deep learning inspired object consolidation approaches using lidar data for autonomous driving: a review. Arch. Comput. Methods Eng. 1–21 (2021)
MS, R.; Patan, A.H.; Gandomi, J. H.; Park, H.-Y.; Jung A drl based 4-r computation model for object detection on rsu using lidar in ilot. In: IEEE Symposium Series on Computational Intelligence (SSCI), pp. 01–08 . IEEE (2021)
Hochuli, A.G.; Britto, A.S., Jr.; Saji, D.A.; Saavedra, J.M.; Sabourin, R.; Oliveira, L.S.: A comprehensive comparison of end-to-end approaches for handwritten digit string recognition. Expert Syst. Appl. 165, 114196 (2021)
Shaukat, Z.; Ali, S.; Xiao, C.; Sahiba, S.; Ditta, A.; et al.: Cloud-based efficient scheme for handwritten digit recognition. Multim. Tools Appl. 79(39), 29537–29549 (2020)
Zhenwei, S.: Datefinder: detecting date regions on handwritten document images based on positional expectancy, Ph.D. thesis, Faculty of Science and Engineering (2016)
Saabni, R.: Recognizing handwritten single digits and digit strings using deep architecture of neural networks. In: Third International Conference on Artificial Intelligence and Pattern Recognition (AIPR), pp. 1–6. IEEE (2016)
Kusetogullari, H.; Yavariabdi, A.; Hall, J.; Lavesson, N.: Digitnet: a deep handwritten digit detection and recognition method using a new historical handwritten digit dataset. Big Data Res. 23, 100182 (2021)
Hochuli, A.G.; Oliveira, L.S.; Britto, A., Jr.; Sabourin, R.: Handwritten digit segmentation: is it still necessary? Pattern Recogn. 78, 1–11 (2018)
Granell, E.; Chammas, E.; Likforman-Sulem, L.; Martínez-Hinarejos, C.-D.; Mokbel, C.; Cîrstea, B.-I.: Transcription of spanish historical handwritten documents with deep neural networks. J. Imaging 4(1), 15 (2018)
Aly, S.; Almotairi, S.: Deep convolutional self-organizing map network for robust handwritten digit recognition. IEEE Access 8, 107035–107045 (2020)
Jebril, N.A.; Al-Zoubi, H.R.; Al-Haija, Q.A.: Recognition of handwritten arabic characters using histograms of oriented gradient (hog). Pattern Recogn. Image Anal. 28(2), 321–345 (2018)
Ahlawat, S.; Choudhary, A.: Hybrid cnn-svm classifier for handwritten digit recognition. Proc. Comput. Sci. 167, 2554–2560 (2020)
Krishnan, P.; Jawahar, C.: Hwnet v2: an efficient word image representation for handwritten documents. Int. J. Doc. Anal. Recogn. 22(4), 387–405 (2019)
Dhiman, MS, G.; Patan, R.; Kallam, S.; Ramana, K.; Yadav, K.; Alharbi, A.O.: Deep learning-influenced joint vehicle-to-infrastructure and vehicle-to-vehicle communication approach for internet of vehicles. Exp. Syst. e12815 (2021)
Khaja, M.; Kumar, S.; Jain, A.K.; Ahmed, S.; Analysis and simulation of handwritten recognition system. Mater. Today Proc. (2021)
Sharma, R.; Kaushik, B.: Offline recognition of handwritten indic scripts: A state-of-the-art survey and future perspectives. Comput. Sci. Rev. 38, 100302 (2020)
Abdulrazzaq, M.B.; Saeed, J.N.: A comparison of three classification algorithms for handwritten digit recognition, in: 2019 International Conference on Advanced Science and Engineering (ICOASE), pp. 58–63. IEEE (2019)
Qiao, J.; Wang, G.; Li, W.; Chen, M.: An adaptive deep q-learning strategy for handwritten digit recognition. Neural Netw. 107, 61–71 (2018)
Aras, G.; Makaroğlu, D.; Demir, S.; Cakir, A.: An evaluation of recent neural sequence tagging models in turkish named entity recognition. Expert Syst. Appl. 182, 115049 (2021)
Liu, X.; Zhou, Y.; Wang, Z.: Deep neural network-based recognition of entities in chinese online medical inquiry texts. Futur. Gener. Comput. Syst. 114, 581–604 (2021)
Mekala, M.; Rizwan, P.; Khan, M. S.: Computational intelligent sensor-rank consolidation approach for industrial internet of things (iiot). IEEE Int. Things J. (2021)
Inkeaw, P.; Charoenkwan, P.; Huang, H.-L.; Marukatat, S.; Ho, S.-Y.; Chaijaruwanich, J.: Recognition of handwritten lanna dhamma characters using a set of optimally designed moment features. Int. J. Doc. Anal. Recogn. 20(4), 259–274 (2017)
Iandola, F.N.; Han, S.; Moskewicz, M.W.; Ashraf, K.; Dally, W.J.; Keutzer, K.: Squeezenet: Alexnet-level accuracy with 50x fewer parameters and<0.5mb model size. arXiv:1602.07360
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM
Guha, A.; Samanta, D.: Hybrid approach to document anomaly detection: an application to facilitate RPA in title insurance, Int. J. Autom. Comput. 18(1), 55–72 (2021). https://doi.org/10.1007/s11633-020-1247-y. http://link.springer.com/10.1007/s11633-020-1247-y
De Sousa Neto, A.F.; Bezerra, B.L.D.; Lima, E.B.; Toselli, A.H.: Hdsr-flor: a robust end-to-end system to solve the handwritten digit string recognition problem in real complex scenarios. IEEE Access 8, 208543–208553 (2020). https://doi.org/10.1109/ACCESS.2020.3039003
Siebra Lopes, G.; Clifte da Silva, D.; Oliveira Rodrigues, A.W.; Reboucas Filho, P.P.: Recognition of handwritten digits using the signature features and optimum-path forest classifier. IEEE Latin Am. Trans. 14(5), 2455–2460 (2016). https://doi.org/10.1109/TLA.2016.7530445
Aly, S.; Mohamed, A.: Unknown-length handwritten numeral string recognition using cascade of pca-svmnet classifiers. IEEE Access 7, 52024–52034 (2019). https://doi.org/10.1109/ACCESS.2019.2911851
Gurunath, R., Agarwal, M., Nandi, A., Samanta, D.: An Overview: Security Issue in Iot Network, pp. 104–107 (2018). https://doi.org/10.1109/I-SMAC.2018.8653728
Mekala, D.; Mallah, G.A.; Chaudhry, S.A.: Dawm: Cost-aware asset claim analysis approach on big data analytic computation model for cloud data centre, Sec. Commun. Netw. (2021)
Cecotti, H.; Vajda, S.; Belaïd, A.: High performance classifiers combination for handwritten digit recognition 619–626 (2005)
Mohemmed, A.; Lu, G.; Kasabov, N.: Evaluating span incremental learning for handwritten digit recognition 670–677 (2012)
Jolfaei, MS, A.; Srivastava, G.; Zheng, X.; Anvari-Moghaddam, A.; Viswanathan, P.: Resource offload consolidation based on deep-reinforcement learning approach in cyber-physical systems, IEEE Trans. Emerg. Topics Comput. Intell. (2020)
Kaensar, C.: A comparative study on handwriting digit recognition classifier using neural network, support vector machine and k-nearest neighbor 155–163 (2013)
Le Cun, Y.; Jackel, L.D.; Boser, B.; Denker, J.S.; Graf, H.P.; Guyon, I.; Henderson, D.; Howard, R.E.; Hubbard, W.: Handwritten digit recognition: Applications of neural net chips and automatic learning 303–318 (1990)
Liu, C.-L.; Nakashima, K.; Sako, H.; Fujisawa, H.: Handwritten digit recognition: investigation of normalization and feature extraction techniques. Pattern Recogn. 37(2), 265–279 (2004). https://doi.org/10.1016/S0031-3203(03)00224-3.
Xi, E.; Bing, S.; Jin, Y.: Capsule network performance on complex data, arXiv preprint arXiv:1712.03480 (2017)
Merabti, H.; Farou, B.; Seridi, H.: A segmentation-recognition approach with a fuzzy-artificial immune system for unconstrained handwritten connected digits. Informatica 42(1), 95–106 (2018)
Redmon, J.; Farhadi, A.: Yolov3: An incremental improvement, arXiv preprint arXiv:1804.02767 (2018)
Acknowledgements
This work was supported in part by Basic Science Research Programs of the Ministry of Education (Grant NRF-2018R1A2B 6005105) and in part by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2019R1A5A8080290).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Singh, D., Bano, S., Samanta, D. et al. Deep Learning Inspired Nonlinear Classification Methodology for Handwritten Digits Recognition Using DSR Encoder. Arab J Sci Eng 48, 1385–1397 (2023). https://doi.org/10.1007/s13369-022-06865-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13369-022-06865-8