Writer Identification System Research Articles

OHSCR: Benchmarks Dataset for Offline Handwritten Sindhi Character Recognition

This research work presents a unique dataset for offline handwritten Sindhi character recognition. It has 7800 character images in total, divided into multiple categories by 150 writers of various ages, genders, and professional backgrounds. Each writer writes the 52 Sindhi characters in the designed form. With a high-quality scanner, all of the written samples were scanned. After that, all the handwritten Sindhi characters were cropped from the collected designed form, and the cropped images were saved in ‘.png’ format. For the benefit of the Sindhi research community, this work suggests an image dataset for character recognition in handwritten Sindhi. The dataset will be made publically available. For the Sindhi language, this dataset can be used to create and test handwritten character recognition systems and provide helpful insights through writer identification. The dataset has been divided into the training set and the test set, with 80% for training and 20% for testing. The different preprocessing techniques used to remove noise from scanned images to create a clean dataset. The dataset created as a result of this research is the world's first openly accessible dataset for handwritten research, and it can be useful for writer identification systems and handwriting recognition systems.

An End-to-End deep learning system for writer identification in handwritten Arabic manuscripts

An End-to-End deep learning system for writer identification in handwritten Arabic manuscripts

Comprehensive robustness evaluation of an automatic writer identification system using convolutional neural networks

<p>This research paper presents a convolutional neural network (CNN) model for identifying handwritten Urdu characters. A dataset of 38 fundamental Urdu characters from 100 different writers in the Kashmir valley was manually collected. The developed system was trained on a training dataset of 30,400 samples and verified on a test dataset of 7600 samples, and it outperformed previously proposed AI based writer identification systems in Urdu language with an identification rate of 91.44 percent for 38 classes. This study highlights the effectiveness of deep learning techniques in solving the challenging task of the Urdu writer identification. The findings demonstrate the potential of the developed CNN model for real-world applications in handwritten character recognition and verification systems. Future work involves expanding the dataset to include numerals and isolated characters for improved system performance.</p>

Offline writer identification using deep feature concatenation

Handwriting is an individual trait that serves as evidence to authenticate a particular writer. Identifying the writer of a handwritten text has shown encouraging results in examining historical and forensic documents. In this paper, we propose a novel offline writer identification system based on the challenging analysis of small amount of data to extract distinct patterns. In our deep network, the feature extraction process relies on a specially designed dual-path architecture, and the resulting embeddings are concatenated to produce the final learned features. To deal with a variety of uncertainties such as high intra-class variations and noises, we leverage the fuzzy logic in the design of a custom Convolutional Neural Network (CNN) with a type-2 fuzzy activation function for the first path. Additionally, the second path utilizes the transfer learning-based CNN to enhance the discriminability of the learned features. Our method allows for text-independent writer identification, eliminating the need for identical handwriting samples to train and test the model. Considering that various factors can influence the handwriting style, a dataset containing right-to-left handwriting samples is assembled. The proposed method is evaluated on our developed dataset and four widely-known public datasets, namely KHATT, CVL, Firemaker, and IAM. High accuracy values are achieved, with results of 99.85%, 99.83%, 99.79%, 99.64%, and 98.17% for each dataset, respectively. One noteworthy aspect of this study is that the evaluation results on diverse datasets demonstrate the applicability of the proposed model to various languages. Moreover, the model performs effectively in real-world scenarios with limited handwritten data.

Offline text-independent writer identification using a codebook with structural features.

Understanding handwritten documents is a vital and challenging problem that attracts many researchers in the fields of forensic and authentication science. This paper presents an offline system for text-independent writer identification of handwritten documents. The system extracts a handwritten connected component contour, which in turn is divided into segments of specific length. The system utilizes the concept of a bag of features in the writer recognition domain and considers handwritten contour segments to extract two conceptually simple and effective structural features. These features are the contour point curve angle and the CONtour point CONcavity/CONvexity. The system uses the proposed features to train a k-means clustering algorithm to construct a codebook of size K. The method then uses occurrence histograms of the extracted features in the codebook to create a final feature vector for each handwritten document. The effectiveness of the proposed features is evaluated in the writer identification domain using two widely used classification methods: the nearest neighbor and the support vector machine techniques. The proposed writer identification is evaluated on two large and public datasets from different language domains, the Arabic KHATT and English IAM datasets. The experimental results show that the proposed system outperforms state-of-the-art methods on the IAM dataset and provides competitive results on the KHATT dataset with respect to the identification rate.

An Unsupervised Writer Identification Based on Generating Clusterable燛mbeddings

The writer identification system identifies individuals based on their handwriting is a frequent topic in biometric authentication and verification systems. Due to its importance, numerous studies have been conducted in various languages. Researchers have established several learning methods for writer identification including supervised and unsupervised learning. However, supervised methods require a large amount of annotation data, which is impossible in most scenarios. On the other hand, unsupervised writer identification methods may be limited and dependent on feature extraction that cannot provide the proper objectives to the architecture and be misinterpreted. This paper introduces an unsupervised writer identification system that analyzes the data and recognizes the writer based on the inter-feature relations of the data to resolve the uncertainty of the features. A pairwise architecture-based Autoembedder was applied to generate clusterable embeddings for handwritten text images. Furthermore, the trained baseline architecture generates the embedding of the data image, and the K-means algorithm is used to distinguish the embedding of individual writers. The proposed model utilized the IAM dataset for the experiment as it is inconsistent with contributions from the authors but is easily accessible for writer identification tasks. In addition, traditional evaluation metrics are used in the proposed model. Finally, the proposed model is compared with a few unsupervised models, and it outperformed the state-of-the-art deep convolutional architectures in recognizing writers based on unlabeled data.

A deep learning based system for writer identification in handwritten Arabic historical manuscripts

A deep learning based system for writer identification in handwritten Arabic historical manuscripts

WRITER IDENTIFICATION: THE EFFECT OF IMAGE RESIZING ON CNN PERFORMANCE

Abstract. Introducing Deep Learning has been successful in improving the performance of automated writer identification systems. However, using very large patch sizes as input to CNN consumes a lot of machine resources and requires a lot of training time. To overcome this problem, many researchers use resized images.In this paper, we will try to make a comparative study between several patches sizes which were then resized to a normalized size of 32 × 32. Our aim is to elaborate the best recommendations for choosing the image resizing in order to increase the CNN performance. Thus, we will carry our tests on three databases. The first is CVL, a Latin dataset with 310 writers, the second is CERUG-CH a Chinese dataset with 105 writers and the last is KHATT that contains the Arabic writings of 1000 writers. To see if the type of CNN model impacts the results conducted on resized images, we deploy two models: ResNet-18 and MobileNet. The main finding is that the best results correspond to the resizing values of the images which makes it possible to have the average line height of the writings closer to the height of the CNN patches.

Writer Identification using Deep Learning with FAST Keypoints and Harris corner detector

Writer identification from offline images of handwriting is an interesting pattern classification problem that has been investigated for many decades now. Despite significant research endeavors, the problem still remains challenging due to high intra-class variations and, at times, high similarity between writings of two individuals. This paper presents a writer identification system that relies on extraction of key points from handwriting and feeding small patches around these key points to a convolutional neural network for feature learning and classification. More specifically, we employ FAST key points and Harris corner detector to identify points of interest in the handwriting. A deep CNN is trained using small patches centered around these key points. Classification is carried out in an end-to-end manner as well as by encoding features extracted from one of the convolutional layers. Experimental study is carried out on three different datasets namely IAM, QUWI and IFN/ENIT and high identification rates are reported for each of these datasets.

Deep bidirectional long short-term memory for online multilingual writer identification based on an extended Beta-elliptic model and fuzzy elementary perceptual codes

The development of pattern recognition and artificial intelligence domains owes the writer identification challenge greatly. In fact, writer identification is still a challenging task in the definition of a set of features able to characterize the various handwritten documents. These handwritten documents are not generally stable and show a wide variability from the same person over time, or from different writers. The capacity to identify the documents’ writers provides further chances of using these handwritten documents for several applications like forensic science, control access, digital rights management and financial transactions. In this paper, we propose a novel system to text-independent online multilingual writer identification. Our system is based on new model that we named the Extended Beta-Elliptic Model. Moreover, we are interested in using the Fuzzy Elementary Perceptual Codes to characterize the handwriting of writers well. In addition, we adopted the use of Recurrent Neural Network with Deep Bidirectional Long Short-Term Memory in the training and identification phases. Experiments are conducted on IBM_UB_1 and ADAB datasets with 98.44% and 100% writer identification rates respectively. The proposed system using the combination of the Extended Beta-Elliptic model and the Fuzzy Elementary Perceptual Codes in features extraction and the Deep Bidirectional Long Short-Term Memory in classification outperforms the existing online writer identification systems on both Latin and Arabic scripts.

A Thresholded Gabor-CNN Based Writer Identification System for Indic Scripts

Writer identification is the procedure of identifying individuals from handwriting. Writer identification is a common interest in biometric authentication and verification systems, and numerous studies are available for English, Chinese, Arabic, and Persian specific handwriting. This paper introduces a supervised offline Indic script writer identification system that can identify individuals using less than a single page of handwriting. A lightweight Convolutional Neural Network (CNN) architecture fused with non-trainable Gabor filters is used as an identification model that can recognize writers from scarce data. For the experiment, we used BanglaWriting dataset, which is openly available for Bengali writing and writer recognition. Further, we added Devanagari and Telugu datasets for evaluation. The overall evaluation shows that the proposed thresholded Gabor-based CNN architecture performs superior to numerous deep CNN architectures for Indic writer recognition.

Hybrid Trainable System for Writer Identification of Arabic Handwriting

Hybrid Trainable System for Writer Identification of Arabic Handwriting

Towards a novel biometric system for forensic document examination

Biometric systems have demonstrated an important enhancement in writer identification from online handwriting. Indeed, writer identification is still a challenging task in the definition of a set of features able to characterize the different samples of handwriting documents. These samples are not usually stable and show a vast variability from the same writer over time, or from different writers. The ability to identify the documents’ authors provides more chances for using these documents for various purposes and especially in forensic analysis. In this paper, we present a biometric based recognition system for forensic document examination capable of identifying a document's author. This system consists of the preprocessing and the segmentation of online handwriting into a sequence of strokes in a first step. Then, from each stroke, we extract a set of static and dynamic features. Next, all the segments which are composed of two consecutive strokes are categorized into groups and subgroups according to their position and their geometric characteristics. Finally, Deep Neural Network is used as a classifier. Experiments which are conducted on IBM_UB_1, IAM OnDB, NLPR Handwriting and ADAB databases, demonstrate that the proposed system outperforms the existing writer identification systems on Latin and Arabic scripts. This justifies its usefulness in forensic examination of handwriting.

Local gradient full-scale transform patterns based off-line text-independent writer identification

Handwriting based writer identification is one of the reliable components of behavioral biometrics. A huge effort has been done in recent years to improve the writer identification performance. Our paper presents a new and effective off-line text-independent system for writer identification. Extracting features from handwriting substantially impacts the ability of the classification process to identify the query writers. With the use of suitable classifier, a well-designed and discriminative feature extraction improves the classification performance. For that, we introduce a discriminative yet simple feature method, referred to as Local gradient full-Scale Transform Patterns (LSTP). The proposed LSTP algorithm captures salient local writing structure at small regions of interest of the writing. These writing regions are termed as connected components. In the classification stage, we perform Hamming distance based NN classifier to compare and match LSTP feature vectors. The proposed framework is evaluated on 9 well-known handwritten benchmarks. Experimental results show high identification performance against the current state-of-the-art.

Online writer identification system using adaptive sparse representation framework

This study explores an adaptive sparse representation approach for online writer identification. The main focus is on employing prior information that quantifies the degree of importance of a dictionary atom concerning a given writer. This information is proposed by a fusion of two derived components. The first component is a saliency measure obtained from the sum-pooled sparse coefficients corresponding to the sub-strokes of a set of enrolled writers. The second component is a similarity score, computed for each dictionary atom with regards to a given writer, that is related to the reconstruction error of the sub-stroke based feature vectors. The proposed identification is accomplished with an ensemble of support vector machines (SVMs), wherein the input to the SVM trained for a writer is obtained by incorporating the adapted saliency values of that writer on the document descriptor obtained via average pooling of sparse codes. Experiments performed on the IAM and IBM-UB1 online handwriting databases demonstrate the efficacy of the proposed scheme.

A Survey on Writer Identification System for Indic Scripts

Handwriting is a skill, expression of someone’s personality that cannot be imitated. It is a physical way of communicating thoughts and ideas and a method for speaking with others. Handwriting is considered as the behavioural characteristic of a person. It is concerned with the sentiments, attitude and brain of a person. Thus no two persons can have the same handwriting. Indeed, even indistinguishable twins who share appearance and hereditary qualities do not have the same handwriting. Handwriting based writer identification has attracted a great deal of attention by researchers to prove someone’s authenticity. It is the process of identifying a person through his/her handwriting. This paper introduces a survey on the work accomplished for writer identification for Indic scripts. The work done on Indic scripts is confined as compared to the non-Indic scripts due to non-availability of the dataset. The anatomy of the paper comprises introduction, stages of writer identification system, applications, reported work and conclusion. The primary focus of this paper is to present the review on writer identification system for Indic scripts, mainly, Devanagari, Gurumukhi, Tamil, Telugu, Bengali, Kannada, Gujarati, Oriya, and Malayalam. This study provides guidance to the research analysts in this area by giving the studies of work done on Indic scripts.

Cross multi-scale locally encoded gradient patterns for off-line text-independent writer identification

Writer identification is experiencing a revival of activity in recent years and continues to attract great deal of attention as a challenging and important area of research in the field of forensic and authentication. In this work, we introduce a reliable off-line system for text-independent writer identification of handwritten documents. Feature engineering is an essential component of a pattern recognition system, which can enhance or decrease the classification performance. A well-designed and defined feature extraction method improves the classification task. This paper proposes, for feature extraction, an effective, yet high-quality and conceptually simple feature image descriptor referred to as Cross multi-scale Locally encoded Gradient Patterns (CLGP). The proposed CLGP feature extraction method, which is expected to better represent salient local writing structure, operates at small observation regions (i.e., connected component sub-images) of the writing sample. CLGP histogram feature vectors computed from all these observation regions in all writing samples are considered as classification inputs to identify query writers using the Nearest Neighbor Classifier (1-NN). Our system is evaluated on six standard databases (IFN/ENIT, AHTID/MW, CVL, IAM, Firemaker, and ICDAR2011) including handwritten samples in Arabic, English, French, Greek, German, and Dutch languages. Comparing the identification performance with old and recent state-of-the-art methods, the proposed system achieves the highest performance on IFN/ENIT, AHTID/MW, and ICDAR2011 databases, and demonstrates competitive performance on IAM, CVL, and Firemaker databases.

An end-to-end deep learning system for medieval writer identification

This paper presents an end-to-end system to identify writers in medieval manuscripts. The proposed system consists in a three-step model for detection and classification of lines in the manuscript and page writer identification. The first two steps are based on deep neural networks trained with transfer learning techniques and specialized to solve the task in hand. The third stage is a weighted majority vote row-decision combiner that assigns to each page a writer. The main goal of this paper is to study the applicability of deep learning in this context when a relatively small training dataset is available. We tested our system with several state-of-the-art deep architectures on a digitized manuscript known as the Avila Bible, using only 9.6% of the total pages for training. Our approach proves to be very effective in identifying page writers, reaching a peak of 96.48% of accuracy and 96.56% of F1 score.

Writer identification system for pre-segmented offline handwritten Devanagari characters using k-NN and SVM

A biometric identification system based on single and multiple modalities has been an evolving concept for solving criminal issues, security and privacy maintenance and for checking the authentication of an individual. The writer identification system is a type of biometric identification in which handwriting of an individual is taken as a biometric identifier. It is a system in which the writer can be identified based on his handwritten text. These systems employ machine learning and pattern recognition algorithms for the generation of a framework. In this paper, the authors have presented a novel system for the writer identification based upon the pre-segmented characters of Devanagari script and also presenting comprehensive state-of-the-art work. The experiment is performed on the corpus consisting of five copies of each character of Devanagari script written by 100 different writers, selected randomly at the public places and consisting of total 24,500 samples of Devanagari characters. Four feature extraction methodologies such as zoning, diagonal, transition and peak extent-based features and classification methods such as k-NN and linear SVM are used with identification accuracy of 91.53% when using zoning, transition and peak extent-based features with a linear SVM classifier.

An effective and conceptually simple feature representation for off-line text-independent writer identification

Feature engineering forms an important component of machine learning and pattern recognition. It is a fundamental process for off-line writer identification of handwritten documents, which continues to be an interesting subject of research in various forensic and authentication areas. In this work, we propose an efficient, yet computationally and conceptually simple framework for off-line text independent writer identification using local textural features in characterizing the writing style of each writer. These include Local Binary Patterns (LBP), Local Ternary Patterns (LTP), and Local Phase Quantization (LPQ). Our approach focuses on exploiting the writing images at small observation regions where a set of connected component sub-images are cropped and extracted from each handwriting sample (document or set of word/text line images). These connected components are seen as texture images where each one of them is subjected to feature extraction using LBP, LPQ, or LTP. Then, a histogram sequence concatenation is applied to the feature image after dimensionality reduction followed by image subdivision into a number of non-overlapping regions. For classification, the 1-NN (Nearest Neighbor) classifier is used to identify the writer of the questioned samples based on the dissimilarity of feature vectors computed from all components in the writing. Experiments on IFN/ENIT (411 writers/Arabic), AHTID/MW (53 writers/Arabic), CVL (309 writers/English), and IAM (657 writers/English) databases demonstrate that our proposed system outperforms old and recent state-of-the-art writer identification systems on Arabic script, and demonstrates a competitive performance on English ones.