Demographic handwriting-based classification problems, such as gender and handedness categorizations, present interesting applications in disciplines like Forensic Biometrics. This work describes an experimental study on the suitability of deep neural networks to three automatic demographic problems: gender, handedness, and combined gender-and-handedness classifications, respectively. Our research was carried out on two public handwriting databases: the IAM dataset containing English texts and the KHATT one with Arabic texts. The considered problems present a high intrinsic difficulty when extracting specific relevant features for discriminating the involved subclasses. Our solution is based on convolutional neural networks since these models had proven better capabilities to extract good features when compared to hand-crafted ones. Our work also describes the first approach to the combined gender-and-handedness prediction, which has not been addressed before by other researchers. Moreover, the proposed solutions have been designed using a unique network configuration for the three considered demographic problems, which has the advantage of simplifying the design complexity and debugging of these deep architectures when handling related handwriting problems. Finally, the comparison of achieved results to those presented in related works revealed the best average accuracy in the gender classification problem for the considered datasets.

/pdf/gender-and-handedness-prediction-from-offline-handwriting-13xh1d049p.pdf

Gender and Handedness Prediction from Offline Handwriting Using Convolutional Neural Networks

Due to constant advancement of computer tools, automated conversion of images of typed, handwritten and printed text is important for various applications, which has led to intense research for several years in the field of offline handwritten character recognition. Handwritten character recognition is complex because characters differ by writing style, shapes and writing devices. To resolve this problem, we propose a fuzzy-based multi-kernel spherical support vector machine. Initially, the input image is fed into the pre-processing step to acquire suitable images. Then, histogram of oriented gradient (HOG) descriptor is utilised for feature extraction. The HOG descriptor constitutes a histogram estimation and normalisation computation. The features are then classified using the proposed classifier for character recognition. In the proposed classifier, we design a new multi-kernel function based on the fuzzy triangular membership function. Finally, a newly developed multi-kernel function is incorporated into the spherical support vector machine to enhance the performance significantly. The experimental results are evaluated and performance is analysed by metrics such as false acceptance rate, false rejection rate and accuracy, which is implemented in MATLAB. Then, the performance is compared with existing systems based on the percentage of training data samples. Thus, the outcome of our proposed system attains 99% higher accuracy, which ensures efficient recognition performance.

/pdf/fuzzy-based-multi-kernel-spherical-support-vector-machine-3btwmevt5w.pdf

Fuzzy-based multi-kernel spherical support vector machine for effective handwritten character recognition

Handwritten Digit Recognition (HDR) is one of the most challenging tasks in the domain of Optical Character Recognition (OCR). Irrespective of language, there are some inherent challenges of HDR, which mostly arise due to the variations in writing styles across individuals, writing medium and environment, inability to maintain the same strokes while writing any digit repeatedly, etc. In addition to that, the structural complexities of the digits of a particular language may lead to ambiguous scenarios of HDR. Over the years, researchers have developed numerous offline and online HDR pipelines, where different image processing techniques are combined with traditional Machine Learning (ML)-based and/or Deep Learning (DL)-based architectures. Although evidence of extensive review studies on HDR exists in the literature for languages, such as English, Arabic, Indian, Farsi, Chinese, etc., few surveys on Bengali HDR (BHDR) can be found, which lack a comprehensive analysis of the challenges, the underlying recognition process, and possible future directions. In this paper, the characteristics and inherent ambiguities of Bengali handwritten digits along with a comprehensive insight of two decades of state-of-the-art datasets and approaches towards offline BHDR have been analyzed. Furthermore, several real-life application-specific studies, which involve BHDR, have also been discussed in detail. This paper will also serve as a compendium for researchers interested in the science behind offline BHDR, instigating the exploration of newer avenues of relevant research that may further lead to better offline recognition of Bengali handwritten digits in different application areas.

https://ieeexplore.ieee.org/ielx7/6287639/6514899/09869842.pdf

Two Decades of Bengali Handwritten Digit Recognition: A Survey

Handwritten Digit Recognition (HDR) is one of the most challenging tasks in the domain of Optical Character Recognition (OCR). Irrespective of language, there are some inherent challenges of HDR, which mostly arise due to the variations in writing styles across individuals, writing medium and environment, inability to maintain the same strokes while writing any digit repeatedly, etc. In addition to that, the structural complexities of the digits of a particular language may lead to ambiguous scenarios of HDR. Over the years, researchers have developed numerous offline and online HDR pipelines, where different image processing techniques are combined with traditional Machine Learning (ML)-based and/or Deep Learning (DL)-based architectures. Although evidence of extensive review studies on HDR exists in the literature for languages, such as English, Arabic, Indian, Farsi, Chinese, etc., few surveys on Bengali HDR (BHDR) can be found, which lack a comprehensive analysis of the challenges, the underlying recognition process, and possible future directions. In this paper, the characteristics and inherent ambiguities of Bengali handwritten digits along with a comprehensive insight of two decades of the state-of-the-art datasets and approaches towards offline BHDR have been analyzed. Furthermore, several real-life application-specific studies, which involve BHDR, have also been discussed in detail. This paper will also serve as a compendium for researchers interested in the science behind offline BHDR, instigating the exploration of newer avenues of relevant research that may further lead to better offline recognition of Bengali handwritten digits in different application areas. 

/pdf/two-decades-of-bengali-handwritten-digit-recognition-a-7jcj0924.pdf

The eye is a non-invasive window where clinicians can observe and study in vivo the retinal vasculature, allowing the early detection of different relevant pathologies. In this paper, we present a complete methodology for the automatic vascular detection in retinal OCT images. To achieve this, we analyse the intensity profiles between representative layers of the retina, layers that are previously segmented. Then, we propose the use of two threshold-based strategies for vessel detection, a fixed and an adaptive approach. Both methods have been tested and validated with 128 OCT images, that include 560 vessels that were labelled by an ophthalmologist. The approaches provided satisfactory results, facilitating the doctors’ work and allowing better analysis and treatment of vascular diseases.

Biomedical Applications Based on Natural and Artificial Computing

This paper presents a comprehensive review of Handwritten Character Recognition (HCR) in English language.The handwritten character recognition has been applied in variety of applications like Banking sectors, Health care industries and many such organizations where handwritten documents are dealt with. Handwritten Character Recognition is the process of conversion of handwritten text into machine readable form. For handwritten characters there are difficulties like it differs from one writer to another, even when same person writes same character there is difference in shape, size and position of character. Latest research in this area has used different types of method, classifiers and features to reduce the complexity of recognizing handwritten text.

/pdf/handwritten-character-recognition-in-english-a-survey-17mq7v4gnr.pdf

Handwritten Character Recognition in English: A Survey

Author Profiling is a kind of text classification method that is used for detecting the personality profiles such as age, gender, educational background, place of origin, personality traits, native language, etc., of authors by processing their written texts. Several applications like forensic analysis, security and marking are used the techniques of author profiling for finding the basic details of authors. The main problem in the domain of author profiling is preparation of suitable dataset for predicting the characteristics of authors. PAN is one organization conducting competitions on various types of shared tasks. In 2013, PAN organizers presented the task of author profiling in their series of competitions and continued this task in further years. They arranged different kinds of datasets in different varieties of languages. From 2013 onwards several researchers proposed solutions for author profiling to predict different personality features of authors by utilizing the datasets provided in PAN competitions. Researchers used different kinds of features like character based, lexical or word based, structural features, syntactic, content based, style based features for distinguishing the author’s writing styles in their texts. Most of the researchers observed that the content based features like words or phrases those are used in the text are most useful for detecting the personality features of authors. In this work, the experiment conducted with the content based features like most important words or terms for predicting age group and gender from the PAN competition datasets. Two datasets such as PAN 2014 and 2016 author profiling datasets are used in this experiment. The documents of dataset are converted in to a vector representation which is a suitable format for giving training to machine learning algorithms. The term representation in a document vector plays a crucial role to improve the performance of gender and age group prediction.The Term Weight Measures (TWMs) are such techniques used for this purpose to represent the significance of a term value in document vector representation. In this work, we developed a new TWM for representing the term value in document vector representation. The proposed TWM’s efficiency is compared with the efficiency of other existing TWMs. Two Machine Learning (ML) algorithms like SVM (Support Vector Machine) and RF (Random Forest) are considered in this experiment for estimating the accuracy of proposed approach. We recognized that the proposed TWM accomplished best accuracies for gender and age prediction in two PAN Datasets.

Monica Patel

Papers

Handwritten Character Recognition in English: A Survey

A New Term Representation Method for Gender and Age Prediction