Recently, a few works on recognition of handwritten Bangla characters have been reported in the literature. However, there is scope for further research in this area. In the present article, results of our recent study on recognition of handwritten Bangla basic characters will be reported. This is a 50 class problem since the alphabet of Bangla has 50 basic characters. In this study, features are obtained by computing local chain code histograms of input character shape. Comparative recognition results are obtained between computation of the above feature based on the contour and one-pixel skeletal representations of the input character image. Also, the classification results are obtained after down sampling the histogram feature by applying Gaussian filter in both these cases. Multilayer perceptrons (MLP) trained by back propagation (BP) algorithm are used as classifiers in the present study. Near exhaustive studies are done for selection of its hidden layer size. An analysis of the misclassified samples shows an interesting error pattern and this has been used for further improvement in the recognition results. Final recognition accuracies on the training and the test sets are respectively 94.65% and 92.14%.

On Recognition of handwritten bangla characters

RNN based online handwritten word recognition in Devanagari and Bengali scripts using horizontal zoning

Reaching high accuracy in handwritten character recognition is an essential challenge since it is widely used in many fields such as signature analysis and forgery detection. Recently, deep learning has demonstrated efficiency in this field. The problem with deep learning is that it uses a vast number of parameters that require a large dataset for training. To overcome this problem, an intelligent network is proposed in this study, based on the computational function of the dentate gyrus of the brain’s hippocampus. The ability to separate patterns with high overlapping is a task that is referred to as the dentate gyrus. Handwritten character images have high overlapping due to various writers’ styles, or even one writer’s style under different conditions. Therefore, proposing a network based on the dentate gyrus’ functional computation can be useful in this field. One of the prominent features of the proposed network is employing two excitation steps and two inhibition steps, augmenting the accuracy of recognizing handwritten characters. The proposed network was evaluated with six datasets of digits and characters from five languages. Experiments on all of the used datasets showed promising results. Moreover, a comparative and detailed analysis of the proposed network with other SOM-based and deep learning methods is provided. Experimental results show a significant boost in accuracy. While the character error rate (CER) was smaller than 1.85% for all the experiments, the smallest CER of 0.6% was achieved by the MNIST dataset. Moreover, in recognizing patterns with high noise, the proposed network showed satisfactory results.

/pdf/pattern-separation-network-based-on-the-hippocampus-activity-qbev7vo72m.pdf

Pattern Separation Network Based on the Hippocampus Activity for Handwritten Recognition

Deep learning systems have recently gained importance as the architecture of choice in artificial intelligence (AI). Handwritten numeral recognition is essential for the development of systems that can accurately recognize digits in different languages which is a challenging task due to variant writing styles. This is still an open area of research for developing an optimized Multilanguage writer independent technique for numerals. In this paper, we propose a deep learning architecture for the recognition of handwritten Multilanguage (mixed numerals belongs to multiple languages) numerals (Eastern Arabic, Persian, Devanagari, Urdu, Western Arabic). The overall accuracy of the combined Multilanguage database was 99.26% with a precision of 99.29% on average. The average accuracy of each individual language was found to be 99.322%. Results indicate that the proposed deep learning architecture produces better results compared to methods suggested in the previous literature.

Deep Convolutional Neural Network for Recognition of Unified Multi-Language Handwritten Numerals

In this paper, we present a system to recognize online handwritten character for the Gujarati language. Support Vector Machine (SVM) with linear, polynomial & RBF kernel, k-Nearest Neighbor (k-NN) with different values of k and multi-layer perceptron (MLP) are used to classify strokes using hybrid feature set. This system is trained using a dataset of 3000 samples and tested by 100 different writers. We have achieved highest accuracy of 91.63% with SVM-RBF kernel and lowest accuracy of 86.72% with MLP. We have achieved minimum average processing time of 0.056 seconds per stroke with SVM linear kernel and maximum average processing time of 1.062 seconds per stroke with MLP.

Online handwritten Gujarati character recognition using SVM, MLP, and K-NN

Handwriting recognition using sinusoidal model parameters

Representation of online handwriting using multi-component sinusoidal model

Hidden Markov Models (HMM) are the widely used modeling techniques for online handwriting recognition. This paper describes both stroke based and character based methods for Assamese handwritten character recognition using HMM classifier. In stroke based method, unique strokes that are used to write the characters are grouped and then HMM modeling is done for each of these selected class of strokes. A character can comprise of one or multiple strokes. Reference set is prepared by analyzing the different combinations of strokes and the degree of confusion between similar strokes. The stroke based method comprises of two stages. First, the stroke sequences in the test character is recognized by stroke based HMM classifier and in the second stage this sequence of strokes is compared against the entries of the reference set. The character corresponding to the matched stroke sequence in the reference set is considered as the recognized character. In character based method, each character as a whole is modeled using HMM and the classifier directly predicts the character class. Experiments were performed on 141 Assamese characters, collected from 100 native Assamese writers and it is observed that character based method gives better result than stroke based method.

Comparison of assamese character recognizer using stroke level and character level engines

The segmentation of unconstrained handwriting is an important issue for both recognition and synthesis systems. In this direction, hidden Markov model (HMM) has been the most popular method for segmentation of continuous handwriting. It has been employed in both implicit and explicit segmentation-based recognition systems. The main advantage of HMM-based force alignment method is that it can segment the handwriting to basic units (e.g. characters) without any knowledge of ground truth boundaries. However, the alignment acquired from an HMM framework often fails to segment the basic units to their actual boundaries. This paper analyzes the segmentation errors made by the HMM in details and identifies an early character boundary problem. Accordingly, an automatic boundary correction method is proposed which utilizes both the forward and the reverse direction alignments of handwritten data with its transcription. This improves the alignment of data and thus the character boundaries in cursive handwriting. The proposed method enhances the word recognition performance for both the Gaussian mixture model (GMM)-HMM and deep neural network (DNN)-HMM frameworks compared to the conventional approach, when evaluated on UNIPEN ICROW-03 and IAM-onDB databases.

Exploiting forced alignment of time-reversed data for improving HMM-based handwriting segmentation

In this work, we consider recognizing online handwritten Assamese word (an Indic script) using the hybrid deep neural network - hidden Markov model (DNN-HMM) framework. The recognition task is generally challenging since Assamese handwriting is mixed with the discrete and cursive writing style, and further complicated due to the placing of vowel/consonant modifier above and/or below already written character in delayed order. Also, as it contains large character set, there is lack of common definition of the basic unit (BU) for automatic recognition. As a step in this direction, first, we select 173 BU capable of characterizing 20K most frequent Assamese words. The HMMs are created for these selected BUs. Next, we create a lexicon for word recognition where each word is represented by all probable "sequence of BUs" that constitute the word. The system is developed using the state-of-the-art Kaldi Automatic speech recognition toolkit, under large vocabulary word recognition framework and is evaluated on the lexicon of sizes 1K, 5k, 10K and 20K words. To the best of our knowledge, this paper is the first of its kind that considers online handwritten Assamese word instead of isolated characters. The experiments are conducted on locally collected Assamese word database, and a promising recognition performance is obtained, noting that the DNN-HMM framework outperforms the GMM-HMM system significantly

Himakshi Choudhury

Papers

Handwriting recognition using sinusoidal model parameters

Representation of online handwriting using multi-component sinusoidal model

Comparison of assamese character recognizer using stroke level and character level engines

Exploiting forced alignment of time-reversed data for improving HMM-based handwriting segmentation

DNN-HMM Based Large Vocabulary Online Handwritten Assamese Word Recognition System