Handwritten Script Identification Research Articles

DIFFERENT APPROACHES OF HANDWRITTEN BENGALI CHARACTER RECOGNITION FROM DOCUMENT IMAGE

Handwritten character recognition from a document image is no-doubt a challenging task and active research filed of interest because of its several application domain. It becomes more challenging in pattern recognition domain because of variability of human writing style, skew and orientation. Noises, smears and faded ink makes it more complicated. OCR research success has limited to very few scripts like Roman, English and Chinese. Among Indian script, Bengali Handwritten Script identification is still an open and active research area. In this paper some popular approach are discussed to indentify the handwritten Bengali character recognition process.

Recognition of Kannada Character Scripts Using Hybrid Feature Extraction and Ensemble Learning Approaches

An automated handwritten script identification system seeks more attention in the academic research field and commercial applications. Recognizing the handwritten Kannada scripts in recent years is an active research area. But, it is a much more challenging one in the pattern recognition field owing to the complexity of structural hierarchy, huge vocabulary count, and distinct people’s diverse handwriting styles. Therefore, this paper aims to develop Kannada handwritten script recognition framework by ensemble methods. Initially, the essential Kannada handwritten text images are collected. These collected images are used for pre-processing with the CLAHE and filtering techniques and followed by segmentation with the active contour approach. The segmented images are utilized using the Adaptive Local Tetra Pattern with freeman chain code histogram techniques. Here, the parameters in the LTrP are tuned with Hybrid Honey Badger Henry Gas Solubility Optimization. Finally, the handwritten recognition is performed by Hybrid Feature Extraction with Ensemble Deep Learning (HFE-EDH). Further, the recognition rate is elevated with the parameter optimization in deep learning approaches using the HGSO + HBA algorithm. Throughout the result analysis, the accuracy of the designed method attains 96%. Thus, the proposed method reveals better performance regarding various performance measures.

Classification of North and South Indian Handwritten Scripts using Gabor Wavelet Features

Objectives: Handwritten script identification plays a vital role in processing handwritten data electronically. Most of the methods fail to provide accuracy due to variation in handwriting, hence the classification of the Indic script before providing it to OCR is crucial. The anticipated work helps increase the accuracy by categorizing the handwritten documents as north or South Indic script before further classification. Methods: This study has proposed a method, using Gabor filters to extract features from the text image for recognizing the kind of script, and seven widely used Indian scripts were considered for this experiment. The handwritten documents were collected from distinct individuals on request, under supervision. The database was manually created by extracting portions of lines from the scanned document images. Findings: A recognition accuracy of 100% was obtained for classifying North and South scripts while an average accuracy of 92% was obtained for biscript classification using KNN classifier at a portion of the line level. Novelty: The proposed method improves the accuracy by acting as a pre-processor to the OCR system by classifying the script according to North Indian script or South Indian Script. Further, it can be processed to find out the script type within the North or South Indian Scripts. Keywords: Handwritten Script; Gabor Filter; KNN Classifier; OCR; Indic Script

Multi-Feature based Handwritten Script Identification at word level

SIFT and LBP are two popular techniques used for obtaining “feature description" of the object. SIFT identifies key points that are locations with distinct image information and robust to scaling and rotation whereas, LBP transforms an image into an array of integer labels describing small scale appearance of the image. In this paper, we present an efficient method wherein “feature description” of handwritten document images at word level are computed using SIFT and LBP. Identification of script type is done using KNN and SVM classifiers. Experimental results show that the performance of SVM is better over KNN. Further, the proposed method is compared with other methods in the literature to demonstrate the efficacy of the proposed method.

Indian Handwritten Script Identification System Based on Random Forest Tree Ensembles

The work proposal addresses to introduce a methodology for Indian unconstrained handwritten script identification by practicing distinct features and classifiers. By utilizing classifiers like RF, SVM, k-NN, and LDA for Indian script identification using statistical, geometric, and structural features. To preserve all the information present on handwritten documents such as historical, medieval, inscription, financial administration, public records, government archives, letters, land councils, various agreements, etc. in digitalize form needs textual document processing system (e.g. OCR). To build a precise and productive multi-script/language textual document processing system must have script identification. For this study use, total 1288 (line wise) samples of ten scripts use in India are collected from different persons of different gender, age, education and region (rural or urban). After successful training and testing, 81.8% and 0.252 accuracies and the OOB error rate are achieved by Random Forest respectively. And 77.8%, 73.5%, and 65.5% accuracy is achieved in SVM, k-NN and LDA classifiers respectively.

Feature Selection Using Harmony Search for Script Identification from Handwritten Document Images

Abstract The feature selection process can be considered a problem of global combinatorial optimization in machine learning, which reduces the irrelevant, noisy, and non-contributing features, resulting in acceptable classification accuracy. Harmony search algorithm (HSA) is an evolutionary algorithm that is applied to various optimization problems such as scheduling, text summarization, water distribution networks, vehicle routing, etc. This paper presents a hybrid approach based on support vector machine and HSA for wrapper feature subset selection. This approach is used to select an optimized set of features from an initial set of features obtained by applying Modified log-Gabor filters on prepartitioned rectangular blocks of handwritten document images written in either of 12 official Indic scripts. The assessment justifies the need of feature selection for handwritten script identification where local and global features are computed without knowing the exact importance of features. The proposed approach is also compared with four well-known evolutionary algorithms, namely genetic algorithm, particle swarm optimization, tabu search, ant colony optimization, and two statistical feature dimensionality reduction techniques, namely greedy attribute search and principal component analysis. The acquired results show that the optimal set of features selected using HSA gives better accuracy in handwritten script recognition.

AUTOMATIC LINE-LEVEL SCRIPT IDENTIFICATION FROM HANDWRITTEN DOCUMENT IMAGES - A REGION-WISE CLASSIFICATION FRAMEWORK FOR INDIAN SUBCONTINENT

Script identification is a well-studied problem for automatic processing of document images. Several attempts have been made so far, but it is still far ahead from the complete solution. In this paper, an automatic approach for line-level handwritten script identification (HSI), considering eight official Indic scripts namely: Bangla, Devanagari, Kannada, Malayalam, Oriya, Roman, Telugu, and Urdu is proposed. We consider a 148-dimensional feature vector using: image component fractal dimension, structural and visual appearance, directional stroke, interpolation and Gabor energy based texture features. For classification, we divide the whole script dataset based on different regions of India, to study a region-wise classification performance. Experimentation was carried out using the state-of-the-art classifiers: multilayer perceptron (MLP), support vector machine (SVM), random forest (RF), and fuzzy unordered rule induction algorithm (FURIA). Among all, we found that MLP as the best performer in terms of average accuracy of 98.2%, 99.5%, 99.1%, 99.5%, 99.9%, 98%, 98.9% for eight-script, bi-script, eastern, north, south Indian script groups, scripts with ‘matra’ vs without ‘matra’, and dravidian vs. non-dravidian groups respectively.

Smart Device Authentication Based on Online Handwritten Script Identification and Word Recognition in Indic Scripts Using Zone-Wise Features

Secure authentication is a vital component for device security. The most basic form of authentication is by using passwords. With the evolution of smart devices, selecting stronger and unbreakable passwords have become a challenging task. Such passwords if written in native languages tend to offer improved security since attackers having no knowledge of such scripts finding it hard to crack. This article proposes two zone-wise feature extraction approaches - zone-wise structural and directional (ZSD) and zone-wise slopes of dominant points (ZSDP), to recognize online handwritten script and word in four major Indic scripts - Devanagari, Bengali, Telugu and Tamil. These features have been used separately and in combination in HMM-based platform for recognition purpose. The dimension reduction of the ZSD-ZSDP combination with factor analysis has shown the best performance in all the four scripts. This work can be utilized for setting up the authentication schemes with the Indic scripts' passwords thus rendering it difficult to crack by hackers having no knowledge of such scripts.

Separating Indic Scripts with matra for Effective Handwritten Script Identification in Multi-Script Documents

We present a novel approach for separating Indic scripts with ‘matra’, which is used as a precursor to advance and/or ease subsequent handwritten script identification in multi-script documents. In our study, among state-of-the-art features and classifiers, an optimized fractal geometry analysis and random forest are found to be the best performer to distinguish scripts with ‘matra’ from their counterparts. For validation, a total of 1204 document images are used, where two different scripts with ‘matra’: Bangla and Devanagari are considered as positive samples and the other two different scripts: Roman and Urdu are considered as negative samples. With this precursor, an overall script identification performance can be advanced by more than 5.13% in accuracy and 1.17 times faster in processing time as compared to conventional system.

PHDIndic_11: page-level handwritten document image dataset of 11 official Indic scripts for script identification

Without publicly available dataset, specifically in handwritten document recognition (HDR), we cannot make a fair and/or reliable comparison between the methods. Considering HDR, Indic script’s document recognition is still in its early stage compared to others such as Roman and Arabic. In this paper, we present a page-level handwritten document image dataset (PHDIndic_11), of 11 official Indic scripts: Bangla, Devanagari, Roman, Urdu, Oriya, Gurumukhi, Gujarati, Tamil, Telugu, Malayalam and Kannada. PHDIndic_11 is composed of 1458 document text-pages written by 463 individuals from various parts of India. Further, we report the benchmark results for handwritten script identification (HSI). Beside script identification, the dataset can be effectively used in many other applications of document image analysis such as script sentence recognition/understanding, text-line segmentation, word segmentation/recognition, word spotting, handwritten and machine printed texts separation and writer identification.

Handwritten Marathi Compound Character Segmentation Using Minutiae Detection Algorithm

Segmentation process is the heart of handwritten Script Identification system. Aside from the large variation of individual's handwriting, many researchersfound difficulty to separate characters from scanned word document Image. The key factor of selection of segmentation algorithm is used to improve efficiency of character segmentation as well as good feature extraction. One of the feature of Marathi script is Compound Character, derived from Devnagari, occur rarely in the script. Segmentation of such type characters is very difficult due to their complex structure. This paper proposed new technique for segmentation of handwritten Marathi compound characters. The Proposed algorithm used the concept of Minutiae extraction for fingerprint for segmenting the compound character. Basically Segmentation is carried out using morphological operations such as erosion and dilation. For segmenting the character from compound character our aim to find termination point and bifurcation points. And for finding the termination and bifurcation point proposed algorithm used the morphological operation hit or miss transform. The experimentalresults shows 90% accuracy in finding termination and bifurcation points.

Word-Level Script Identification Using Texture Based Features

Script identification is an appealing research interest in the field of document image analysis during the last few decades. The accurate recognition of the script is paramount to many post-processing steps such as automated document sorting, machine translation and searching of text written in a particular script in multilingual environment. For automatic processing of such documents through Optical Character Recognition (OCR) software, it is necessary to identify different script words of the documents before feeding them to the OCR of individual scripts. In this paper, a robust word-level handwritten script identification technique has been proposed using texture based features to identify the words written in any of the seven popular scripts namely, Bangla, Devanagari, Gurumukhi, Malayalam, Oriya, Telugu, and Roman. The texture based features comprise of a combination of Histograms of Oriented Gradients (HOG) and Moment invariants. The technique has been tested on 7000 handwritten text words in which each script contributes 1000 words. Based on the identification accuracies and statistical significance testing of seven well-known classifiers, Multi-Layer Perceptron (MLP) has been chosen as the final classifier which is then tested comprehensively using different folds and with different epoch sizes. The overall accuracy of the system is found to be 94.7% using 5-fold cross validation scheme, which is quite impressive considering the complexities and shape variations of the said scripts. This is an extended version of the paper described in (Singh et al., 2014).

A System for Handwritten Script Identification From Indian Document

A System for Handwritten Script Identification From Indian Document

Handwriting Recognition in Indian Regional Scripts

Offline handwriting recognition in Indian regional scripts is an interesting area of research as almost 460 million people in India use regional scripts. The nine major Indian regional scripts are Bangla (for Bengali and Assamese languages), Gujarati, Kannada, Malayalam, Oriya, Gurumukhi (for Punjabi language), Tamil, Telugu, and Nastaliq (for Urdu language). A state-of-the-art survey about the techniques available in the area of offline handwriting recognition (OHR) in Indian regional scripts will be of a great aid to the researchers in the subcontinent and hence a sincere attempt is made in this article to discuss the advancements reported in this regard during the last few decades. The survey is organized into different sections. A brief introduction is given initially about automatic recognition of handwriting and official regional scripts in India. The nine regional scripts are then categorized into four subgroups based on their similarity and evolution information. The first group contains Bangla, Oriya, Gujarati and Gurumukhi scripts. The second group contains Kannada and Telugu scripts and the third group contains Tamil and Malayalam scripts. The fourth group contains only Nastaliq script (Perso-Arabic script for Urdu), which is not an Indo-Aryan script. Various feature extraction and classification techniques associated with the offline handwriting recognition of the regional scripts are discussed in this survey. As it is important to identify the script before the recognition step, a section is dedicated to handwritten script identification techniques. A benchmarking database is very important for any pattern recognition related research. The details of the datasets available in different Indian regional scripts are also mentioned in the article. A separate section is dedicated to the observations made, future scope, and existing difficulties related to handwriting recognition in Indian regional scripts. We hope that this survey will serve as a compendium not only for researchers in India, but also for policymakers and practitioners in India. It will also help to accomplish a target of bringing the researchers working on different Indian scripts together. Looking at the recent developments in OHR of Indian regional scripts, this article will provide a better platform for future research activities.

Offline Handwritten Script Identification in Document Images

Automatic handwritten script identification from document images facilitates many important applications such as sorting, transcription of multilingual documents and indexing of large collection of such images, or as a precursor to optical character recognition (OCR). In this paper, we investigate a texture as a tool for determining the script of handwritten document image, based on the observation that text has a distinct visual texture. Further, K nearest neighbour algorithm is used to classify 300 text blocks as well as 400 text lines into one of the three major Indian scripts: English, Devnagari and Urdu, based on 13 spatial spread features extracted using morphological filters. The proposed algorithm attains average classification accuracy as high as 99.2% for bi-script and 88.6% for tri-script separation at text line and text block level respectively with five fold cross validation test. General Terms Pattern Recognition, Document Image Analysis