Dynamic Horizontal Voting Ensemble Deep Learning Approach to Combined Classification for Human Age, Gender and Ethnicity Soft Biometric Using Fingerprint Pattern (original) (raw)
Related papers
International Journal of Advances in Intelligent Informatics, 2022
Despite significant progress in gender equality, there are still key gender gaps particularly in education, health, right to job opportunities and other basic needs of livelihood. Case instance is in Afghanistan under the control of the Taliban, there have been news of violation against women and girls' rights. There are evidences that the Taliban will implement policies that will restrain women and girl from accessing education, confinement to their home or even denying them access to most jobs [1]. Hence, gender inequality and other associated issues are major problem in our world. International donor agencies, such as World Bank, European Union, African Development Bank (AfDB) and many others, identifies gender identity system as a vital stepping-stone for the female, particularly, as a means of empowering and given them access to peculiar services and other privileges as a citizen [2]. An effective gender identification system has been discovered to be an important enabler for attaining a number of key development results toward eradicating gender inequality, poverty and financial exclusion. The good thing is that there are several methods to verify the identity of people. However, biometric system offers a better approach for personal identification with numerous gains over other methods [3].
ETHNICITY CLASSIFICATION USING A DYNAMIC HORIZONTAL VOTING ENSEMBLE APPROACH BASED ON FINGERPRINT
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, 2022
Today, there is a fierce rivalry between ethnic groups in Nigeria on a number of issues, such as the division of power and resources, aversion to dominance, and uneven growth. Ethnicity as an identity naturally occupies a prominent position in the political arena. It is the simplest and most natural way for people to mobilize around essential human needs such as security, food, shelter, economical well-being, inequity, land distribution, autonomy, and recognition. Recent research has revealed the potential to determine an individual's ethnicity based on biometric data automatically. These studies reported significant advancements in automatically predicting demographics based on facial and iris traits. This success has been ascribed to the availability of a sufficient amount of high-quality data. There needs to be more data about the likelihood that fingerprints can disclose an individual's ethnicity. A need for more data causes this difficulty. This study aims to obtain fingerprint pictures via live scan among the major ethnic groups in Nigeria. For training and classification of the fingerprint images, the proposed Dynamic Horizontal Voting Ensemble (DHVE) deep learning with a Hybrid of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) as the base learner was employed. Standard performance classification metrics such as Accuracy, Recall, Precision, and F1 score were used to evaluate the performance analysis of the model. This study demonstrated an accuracy of over 98% in predicting a person's ethnicity. Additionally, the proposed model outperformed existing state-of-the-art models.
Gender recognition based fingerprints using dynamic horizontal voting ensemble deep learning
International Journal of Advances in Intelligent Informatics
Despite tremendous advancements in gender equality, there are still persistent gender disparities, especially in important human activities. Consequently, gender inequality and related concerns are serious problems in our global society. Major players in the global economy have identified the gender identity system as a crucial stepping stone for bridging the enormous gap in gender-based problems. Extensive research conducted by forensic scientists has uncovered a unique pattern in the fingerprint, and these distinguishing characteristics of fingerprints can be utilized to determine the gender of individuals. Numerous research has revealed various fingerprint-based approaches to gender recognition. This research aims to present a novel dynamic horizontal voting ensemble model with a hybrid Convolutional Neural Network and Long Short Term Memory (CNN-LSTM) deep learning algorithm as the base learner to determine human gender attributes based on fingerprint patterns automatically. Mor...
Gender classification from fused multi-fingerprint types
Information Security Journal: A Global Perspective, 2020
There has been a growing need for demographic information in security applications. These range from token-based demographic information elicitation to automatic gender classification or age estimation from biometric traits. Gender has been classified from facial images, voice utterances, fingerprints, hand images and emerging biometrics in the literature using local statistical or structural feature descriptors extracted from these traits. We propose a deep learning based convolutional neural network architecture for classifying gender from fingerprints of each of the five finger types and evaluate performances across trained models. We demonstrate that performance can be improved by classifying gender from fingerprints of fused combinations amongst the five right-hand finger types. The default method has been to classify gender from the index finger. However, our results show that certain finger types classify a certain gender better than the other. Leveraging on these varying strengths of the finger types we employ a fusion scheme at the abstract level, of odd number of models, trained with these fingerprint types to improve performance. Male, female and overall classification accuracies of the best fusion model are 94.7%, 88.0% and 91.3%, thus, proffering 31.02%, 7.82% and 18.72% improvement, respectively.
Deep Gender Identification Model with Biometric Fingerprint Data
Zenodo (CERN European Organization for Nuclear Research), 2023
People may be easily distinguished from one another thanks to their distinctive and special traits, which also serve as a means of identification. One of the most important pieces of identification information is gender. If we can confidently determine a person's gender, it will reduce the number of inquiries and shorten the search period while increasing the likelihood that someone will be recognized. In this work, we apply deep convolution Neural Network to classify fingerprints by means of gender. The proposed model achieves an validation accuracy of 96.46% for the classification of gender. Publicly available Sokoto Coventry Fingerprint Dataset (SOCOFing) is applied as a benchmark for the outcome of the classification accuracy of the proposed network.
Multimodal Biometrics Data Analysis for Gender Estimation Using Deep Learning
International journal of data science and analysis, 2020
In the recent past with the rapid growing technology security problem is ubiquitous to our daily life pertinent to it, now a day the usage of biometrics is becoming inevitable. Correspondingly, the field of biometrics has gained tremendous acceptance because of its individualistic and authentication capabilities. In many practical scenario the multimodal-based gender estimation will helps to increase the security and efficiency of other biometrics system. Likewise, in contrast to it uni-modal biometric, the multimodal biometrics system would be very difficult to spoof because of its multiple distinct biometrics features. Gender identification using biometrics traits are mainly used for reducing the search space list, indexing and generating statistical reports etc In this paper, a robust multimodal gender identification method based on the deep features are computed using the off-the-shelf pre-trained deep convolution neural network architecture based on AlexNet. The proposed model consists of 20 subsequent layers which contain different window size of convolutional layers following with fully connected layers for feature extraction and classification. Extensive experiments have been conducted on a homologous SDUMLA-HMT (Shandong University Group of Machine Learning and Applications) multimodal database with 15052 images. The proposed method achieved the accuracy of 99.9% which outperforms the results noticed in the literature.
Multi-Level Pooling Model for Fingerprint-Based Gender Classification
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer
It has been widely reported that CNN (Convolutional Neural Network) has shown satisfactory results in classifying images. The strength of CNN lies in the type and the number of layers that construct it. However, the most apparent drawbacks of CNN are the requirement for a large labeled dataset and its lengthy training time. Although datasets are available, labeling that data is a significant problem. This work mimics the CNN model but only utilizes its pooling layers. The novelty of this model is removing convolution layers and directly processing fingerprint images using pooling layers. Three pooling layer models, namely maximum pooling, average pooling, and minimum pooling, are used to generate fingerprint features to classify their owner gender. These pooling layers are arranged consecutively up to eight levels. Removing convolution layers makes the process straightforward, and the computation is much faster. This study utilized 200 fingerprint datasets from the NIST (National In...
A Fingerprint-based Age and Gender Detector System using Fingerprint Pattern Analysis
2016
Humans have distinctive and unique traits which can be used to distinguish them thus, acting as a form of identification. Biometrics identify people by measuring some aspect of individual‟s anatomy or physiology such as hand geometry or fingerprint which consists of a pattern of interleaved ridges and valleys. The year 2015 election in Nigeria was greeted by some petitions including under-aged voters. The need for an age and gender detector system is a major concern for organizations at all levels where integrity of information cannot be compromised. This work developed a system that determines human age-range and gender using fingerprint analysis trained with Back Propagation Neural Network (for gender classification) and DWT+PCA (for age classification). A total of 280 fingerprint samples of people with various age and gender were collected. 140 of these samples were used for training the system‟s Database; 70 males and 70 females respectively. This was done for age groups 1-10, 1...
A Soft Computing Model of Soft Biometric Traits for Gender and Ethnicity Classification
International Journal of Engineering and Manufacturing, 2019
There is paucity of information on the possibility of ethnicity identification through fingerprint biometric characteristics and so, this work is set to combine two soft biometric traits (Gender and Ethnicity) in order to ascertain if individual of different ethnicity and gender bias can be identified through their fingerprint. Live scan mechanism was used in order to minimize human errors and as well speed up the rate of fingerprint acquisition which unequivocally ensure good quality capturing of the fingerprint image. In this work, fingerprints of over a thousand people from three different ethnic groups of both male and female gender in Nigeria were captured and subjected to training, testing and classification using Gabor filter and K-NN respectively. Histogram equalization was used for image enhancement and the system performance was evaluated on the basis of some selected metrics such as Recognition Accuracy, Average Recognition Time, Specificity and Sensitivity. Result of this work indicated over 96% accuracy in predicting person's ethnicity and gender with an average recognition time of less than 2secs.