CNN based common approach to handwritten character recognition of multiple scripts

  title={CNN based common approach to handwritten character recognition of multiple scripts},
  author={Durjoy Sen Maitra and Ujjwal Bhattacharya and Swapan K. Parui},
  journal={2015 13th International Conference on Document Analysis and Recognition (ICDAR)},
There are many scripts in the world, several of which are used by hundreds of millions of people. Handwritten character recognition studies of several of these scripts are found in the literature. Different hand-crafted feature sets have been used in these recognition studies. However, convolutional neural network (CNN) has recently been used as an efficient unsupervised feature vector extractor. Although such a network can be used as a unified framework for both feature extraction and… 

Figures and Tables from this paper

Design and Development of a 2D-Convolution CNN model for Recognition of Handwritten Gurumukhi and Devanagari Characters

A deep learning paradigm using a Convolution Neural Network (CNN) which is implemented for handwritten Gurumukhi and devanagari character recognition (HGDCR) and it was concluded that the training and classification through the network design performed about 10 times faster than on a moderately fast CPU.

An Efficient CNN Model for Automated Digital Handwritten Digit Classification

The proposed best CNN model has the simplest architecture that provides a higher accuracy for different datasets and takes less computational time and the validation accuracy of the proposed model is also higher than those of in past works.

A Deep Learning Approach to Recognize Handwritten Telugu Character Using Convolution Neural Networks

A qualified analysis proved the efficiency of the proposed CNN against previous methods in an interesting dataset and the conclusion is improved than some recently proposed literature used for the identification of online handwritten Telugu characters.

OCR System Framework for MODI Scripts using Data Augmentation and Convolutional Neural Network

An ACNN model is proposed using the on-the-fly data augmentation method and convolution neural network to recognition of handwritten MODI script and it is found that the proposed method outperforms the other method.

A Novel Deep Convolutional Neural Network Architecture Based on Transfer Learning for Handwritten Urdu Character Recognition

A novel deep convolutional neural network is proposed for handwritten Urdu character recognition by transfer learning three pre-trained CNN models which outperforms the individual CNNs and numerous conventional classification methods.

Towards a Complete Character Set Meitei Mayek Handwritten Character Recognition

A Convolutional Neural Network model is proposed to recognize characters of a fairly large dataset consisting of 38,500 samples and achieves an accuracy of 93.64% and 92.29% on the dataset of 54 and 55 classes respectively.

Offline Handwritten Malayalam Word Recognition Using a Deep Architecture

A pioneering development of a database for offline handwritten word samples of Malayalam script and its benchmark recognition results based on a transfer learning strategy which involves a deep convolutional neural network (CNN) architecture for feature extraction and a support vector machine (SVM) for classification are presented.

Deep Learning Algorithms for Arabic Handwriting Recognition: A Review

The pre-processing and binarization methods that have been used in the literature along with proposed numerous directions for developing are highlighted along with several recommendations including a framework based deep learning approach that is particularly applicable for dealing with cursive nature languages.

A comparison study between MLP and convolutional neural network models for character recognition

A comparison between MLP and CNN is established and it is demonstrated that the used real-time CNN is 2x more relevant than MLP when classifying characters.

Online Handwritten Bangla Character Recognition Using CNN: A Deep Learning Approach

A detailed analysis about the effects of using different kernel variations, pooling strategies, and activation functions in the CNN architecture has been performed and the outcome is better than some recently proposed handcrafted features used for the recognition of online handwritten Bangla characters.



Neural Combination of ANN and HMM for Handwritten Devanagari Numeral Recognition

In this article, a two-stage classification system for recognition of handwritten Devanagari numerals is presented. A shape feature vector computed from certain directional-view-based strokes of an

Handwritten character recognition using gradient feature and quadratic classifier with multiple discrimination schemes

  • Hailong LiuXiaoqing Ding
  • Computer Science
    Eighth International Conference on Document Analysis and Recognition (ICDAR'05)
  • 2005
Several state-of-the-art techniques of handwritten character recognition on this baseline system to improve the recognition accuracy are applied and lead to improvement on the character recognition rate.

Gradient-based learning applied to document recognition

This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task, and Convolutional neural networks are shown to outperform all other techniques.

Handwritten Numeral Databases of Indian Scripts and Multistage Recognition of Mixed Numerals

P pioneering development of two databases for handwritten numerals of two most popular Indian scripts, a multistage cascaded recognition scheme using wavelet based multiresolution representations and multilayer perceptron classifiers and application for the recognition of mixed handwritten numeral recognition of three Indian scripts Devanagari, Bangla and English.

Performance evaluation of pattern classifiers for handwritten character recognition

The results indicate that pattern classifiers have complementary advantages and they should be appropriately combined to achieve higher performance.

Offline recognition of handwritten Bangla characters: an efficient two-stage approach

The present work deals with recognition of handwritten characters of Bangla, a major script of the Indian sub-continent. The main contributions presented here are (a) generation of a database of

SVM-based hierarchical architectures for handwritten Bangla character recognition

Three different two-stage hierarchical learning architectures (HLAs) are proposed using the three grouping schemes and the HLA scheme with overlapped groups outperforms the other two HLA schemes.

Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks

This work designs a method to reuse layers trained on the ImageNet dataset to compute mid-level image representation for images in the PASCAL VOC dataset, and shows that despite differences in image statistics and tasks in the two datasets, the transferred representation leads to significantly improved results for object and action classification.

An HMM Based Recognition Scheme for Handwritten Oriya Numerals

A novel hidden Markov model (HMM) for recognition of handwritten Oriya numerals is proposed, where the HMM states are not determined a priori, but are determined automatically based on a database of handwritten numeral images.

Databases for research on recognition of handwritten characters of Indian scripts

Three image databases of handwritten isolated numerals of three different Indian scripts namely Devnagari, Bangla and Oriya are described in this paper. Grayscale images of 22556 Devnagari numerals