Handwriting recognition using Deep Learning in Keras

Arora, Shefali; Bhatia, M. P. S.

doi:10.1109/icacccn.2018.8748540

Cited by 28 publications

(13 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study differs from other existed work because it reveals the effectiveness of CNN in terms of high accuracy and low computational time to classify handwritten digits [36][37][38][39]. With extensive literature survey, it comes to know that accuracy of various reported CNN models is not up to the mark as mentioned in Table 3.…”

Section: Introductionmentioning

confidence: 70%

“…Ciresan et al [35] presented convolutional neural network committees for handwritten character classification. Arora [36] employed two architectures: feed-forward neural network (FWNN) and convolutional neural network (CNN) for feature extraction, training and classification of MNIST dataset constituting handwritten images. Outcomes reveal that for the handwritten digit recognition, CNN attains greater accuracy than FWNN.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An efficient and improved scheme for handwritten digit recognition based on convolutional neural network

et al. 2019

View full text Add to dashboard Cite

Character recognition from handwritten images has received greater attention in research community of pattern recognition due to vast applications and ambiguity in learning methods. Primarily, two steps including character recognition and feature extraction are required based on some classification algorithm for handwritten digit recognition. Former schemes exhibit lack of high accuracy and low computational speed for handwritten digit recognition process. The aim of the proposed endeavor was to make the path toward digitalization clearer by providing high accuracy and faster computational for recognizing the handwritten digits. The present research employed convolutional neural network as classifier, MNIST as dataset with suitable parameters for training and testing and DL4J framework for hand written digit recognition. The aforementioned system successfully imparts accuracy up to 99.21% which is higher than formerly proposed schemes. In addition, the proposed system reduces computational time significantly for training and testing due to which algorithm becomes efficient.

show abstract

Section: Introductionmentioning

confidence: 70%

Section: Introductionmentioning

confidence: 99%

An efficient and improved scheme for handwritten digit recognition based on convolutional neural network

et al. 2019

View full text Add to dashboard Cite

show abstract

“…However, the results show the potential of this methodology even without freezing and demonstrate that being able to freeze the pre-trained section should increase the performance of EXPANSE in the future. We chose the MNIST dataset [27,28] and a deep neural network model similar to [29,28] for our evaluation process. This dataset consists of 60,000 handwritten digits for the training set and 10,000 samples for testing.…”

Section: Discussionmentioning

confidence: 99%

EXPANSE: A Deep Continual / Progressive Learning System for Deep Transfer Learning

Iman¹,

Miller²,

Rasheed³

et al. 2022

Preprint

View full text Add to dashboard Cite

Deep transfer learning (DTL) techniques try to tackle the limitations of deep learning, the dependency on extensive training data and the training costs, by reusing obtained knowledge from source data for target data. However, the current DTL techniques suffer from either catastrophic forgetting dilemma (losing the previously obtained knowledge) or overly biased pre-trained models (harder to adapt to target data) in finetuning pre-trained models or freezing a part of the pre-trained model, respectively. Progressive learning, a sub-category of DTL, reduces the effect of the overly biased model in the case of freezing earlier layers by adding a new layer to the end of a frozen pre-trained model. Even though it has been successful in many cases, it cannot yet handle distant source and target data. We propose a new continual/progressive learning approach for deep transfer learning to tackle these limitations. To avoid both catastrophic forgetting dilemma and overly biased-model problem, we expand the pre-trained model by expanding pre-trained layers (adding new nodes to each layer) in the model instead of only adding new layers. Hence the method is named EXPANSE. Our experimental results confirm that we can tackle distant source and target data using this technique. At the same time, the final model is still valid on the source data, achieving a promising deep continual learning approach. Moreover, we offer a new way of training deep learning models inspired by the human education system. We termed this two-step training: learning basics first, then adding complexities and uncertainties. The evaluation implies that the two-step training extracts more meaningful features and a finer basin on the error surface since it can achieve better accuracy in comparison to regular training. EXPANSE (model expansion Preprint. Under review.

show abstract

“…The proposed system in [4] used the following methods to recognize characters in Tamil and English languages -pre-processing, segmentation, feature extraction, and classification and recognition. The authors in [5] have used Keras for the classification MNIST dataset in which feed-forward neural network and convolutional neural network were used for feature extraction. It was observed that convolutional neural network performed better than the feed-forward neural network.…”

Section: Related Workmentioning

confidence: 99%

Offline Handwritten Text Recognition and Signature Verification

Arai¹,

A²,

Jain³

et al. 2021

Preprint

View full text Add to dashboard Cite

Offline Handwritten Text Recognition (HTR) is one of the most interesting challenges in today's date in the field of Image processing. This paper introduces a novel technique to recognize the handwritten text by using Convolutional Recurrent Neural Network along with Connectionist Temporal Classification. This model makes use of the IAM dataset. Offline Signature Verification (SV) is another challenging task in the field of biometrics. This paper demonstrates a novel technique to verify the signature as an original or forged one, and makes use of the Convolutional Siamese network.

show abstract

Handwriting recognition using Deep Learning in Keras

Cited by 28 publications

References 6 publications

An efficient and improved scheme for handwritten digit recognition based on convolutional neural network

An efficient and improved scheme for handwritten digit recognition based on convolutional neural network

EXPANSE: A Deep Continual / Progressive Learning System for Deep Transfer Learning

Offline Handwritten Text Recognition and Signature Verification

Contact Info

Product

Resources

About