Showing items 1 - 20 of 51

Your selections:

A dynamically weighted multi-modal biometric security system

  • Authors: Brown, Dane L , Bradshaw, Karen L
  • Date: 2016
  • Subjects: To be catalogued
  • Language: English
  • Type: text , article
  • Identifier: http://hdl.handle.net/10962/473684 , vital:77672 , xlink:href="https://www.researchgate.net/publication/315839228_A_Dynamically_Weighted_Multi-Modal_Biometric_Security_System"
  • Description: The face, fingerprint and palmprint feature vectors are automatically extracted and dynamically selected for fusion at the feature-level, toward an improved human identification accuracy. The feature-level has a higher potential accuracy than the match score-level. However, leveraging this potential requires a new approach. This work demonstrates a novel dynamic weighting algorithm for improved image-based biometric feature-fusion. A comparison is performed on uni-modal, bi-modal, tri-modal and proposed dynamic approaches. The proposed dynamic approach yields a high genuine acceptance rate of 99.25% genuine acceptance rate at a false acceptance rate of 1% on challenging datasets and big impostor datasets.
  • Full Text:
  • Date Issued: 2016

A multi-biometric feature-fusion framework for improved uni-modal and multi-modal human identification

  • Authors: Brown, Dane L , Bradshaw, Karen L
  • Date: 2016
  • Subjects: To be catalogued
  • Language: English
  • Type: text , article
  • Identifier: http://hdl.handle.net/10962/473696 , vital:77673 , xlink:href="https://ieeexplore.ieee.org/abstract/document/7568927"
  • Description: The lack of multi-biometric fusion guidelines at the feature-level are addressed in this work. A feature-fusion framework is geared toward improving human identification accuracy for both single and multiple biometrics. The foundation of the framework is the improvement over a state-of-the-art uni-modal biometric verification system, which is extended into a multi-modal identification system. A novel multi-biometric system is thus designed based on the framework, which serves as fusion guidelines for multi-biometric applications that fuse at the feature-level. This framework was applied to the face and fingerprint to achieve a 91.11% recognition accuracy when using only a single training sample. Furthermore, an accuracy of 99.69% was achieved when using five training samples.
  • Full Text:
  • Date Issued: 2016

An investigation of face and fingerprint feature-fusion guidelines

  • Authors: Brown, Dane L , Bradshaw, Karen L
  • Date: 2016
  • Subjects: To be catalogued
  • Language: English
  • Type: text , article
  • Identifier: http://hdl.handle.net/10962/473751 , vital:77678 , xlink:href="https://doi.org/10.1007/978-3-319-34099-9_45"
  • Description: There are a lack of multi-modal biometric fusion guidelines at the feature-level. This paper investigates face and fingerprint features in the form of their strengths and weaknesses. This serves as a set of guidelines to authors that are planning face and fingerprint feature-fusion applications or aim to extend this into a general framework. The proposed guidelines were applied to the face and fingerprint to achieve a 91.11 % recognition accuracy when using only a single training sample. Furthermore, an accuracy of 99.69 % was achieved when using five training samples.
  • Full Text:
  • Date Issued: 2016

Extended feature-fusion guidelines to improve image-based multi-modal biometrics

  • Authors: Brown, Dane L , Bradshaw, Karen L
  • Date: 2016
  • Subjects: To be catalogued
  • Language: English
  • Type: text , article
  • Identifier: http://hdl.handle.net/10962/473796 , vital:77682 , xlink:href="https://doi.org/10.1145/2987491.2987512"
  • Description: The feature-level, unlike the match score-level, lacks multi-modal fusion guidelines. This work demonstrates a practical approach for improved image-based biometric feature-fusion. The approach extracts and combines the face, fingerprint and palmprint at the feature-level for improved human identification accuracy. Feature-fusion guidelines, proposed in recent work, are extended by adding the palmprint modality and the support vector machine classifier. Guidelines take the form of strengths and weaknesses as observed in the applied feature processing modules during preliminary experiments. The guidelines are used to implement an effective biometric fusion system at the feature-level to reduce the equal error rate on the SDUMLA and IITD datasets, using a novel feature-fusion methodology.
  • Full Text:
  • Date Issued: 2016

Improved fingercode alignment for accurate and compact fingerprint recognition

  • Authors: Brown, Dane L , Bradshaw, Karen L
  • Date: 2016
  • Subjects: To be catalogued
  • Language: English
  • Type: text , article
  • Identifier: http://hdl.handle.net/10962/473807 , vital:77683 , xlink:href="https://ieeexplore.ieee.org/abstract/document/7568931"
  • Description: The traditional texture-based fingerprint recognition system known as FingerCode is improved in this work. Texture-based fingerprint recognition methods are generally more accurate than other methods, but at the disadvantage of increased storage requirements. The low storage requirements for a low resolution texture-based fingerprint recognition method known as FingerCode enables the combined use of fingerprints with the additional security of other devices such as smartcards. The low recognition accuracy of FingerCode is addressed using a novel texture alignment technique. As a result, an improved recognition accuracy is achieved without increasing storage requirements.
  • Full Text:
  • Date Issued: 2016

Enhanced biometric access control for mobile devices

  • Authors: Brown, Dane L , Bradshaw, Karen L
  • Date: 2017
  • Subjects: To be catalogued
  • Language: English
  • Type: text , article
  • Identifier: http://hdl.handle.net/10962/465678 , vital:76631
  • Description: In the new Digital Economy, mobile devices are increasingly 978-0-620-76756-9being used for tasks that involve sensitive and/or financial data. Hitherto, security on smartphones has not been a priority and furthermore, users tend to ignore the security features in favour of more rapid access to the device. We propose an authentication system that can provide enhanced security by utilizing multi-modal biometrics from a single image, captured at arm’s length, containing unique face and iris data. The system is compared to state-of-the-art face and iris recognition systems, in related studies using the CASIA-Iris-Distance dataset and the IITD iris dataset. The proposed system outperforms the related studies in all experiments and shows promising advancements to at-a-distance iris recognition on mobile devices.
  • Full Text:
  • Date Issued: 2017

Feature-fusion guidelines for image-based multi-modal biometric fusion

  • Authors: Brown, Dane L , Bradshaw, Karen L
  • Date: 2017
  • Subjects: To be catalogued
  • Language: English
  • Type: text , article
  • Identifier: http://hdl.handle.net/10962/460063 , vital:75889 , xlink:href="https://doi.org/10.18489/sacj.v29i1.436"
  • Description: The feature level, unlike the match score level, lacks multi-modal fusion guidelines. This work demonstrates a newapproach for improved image-based biometric feature-fusion. The approach extracts and combines the face, fingerprintand palmprint at the feature level for improved human identification accuracy. Feature-fusion guidelines, proposed inour recent work, are extended by adding a new face segmentation method and the support vector machine classifier.The new face segmentation method improves the face identification equal error rate (EER) by 10%. The support vectormachine classifier combined with the new feature selection approach, proposed in our recent work, outperforms otherclassifiers when using a single training sample. Feature-fusion guidelines take the form of strengths and weaknessesas observed in the applied feature processing modules during preliminary experiments. The guidelines are used toimplement an effective biometric fusion system at the feature level, using a novel feature-fusion methodology, reducingthe EER of two groups of three datasets namely: SDUMLA face, SDUMLA fingerprint and IITD palmprint; MUCT Face,MCYT Fingerprint and CASIA Palmprint.
  • Full Text:
  • Date Issued: 2017

Feature-fusion guidelines for image-based multi-modal biometric fusion

  • Authors: Brown, Dane L , Bradshaw, Karen L
  • Date: 2017
  • Subjects: To be catalogued
  • Language: English
  • Type: text , article
  • Identifier: http://hdl.handle.net/10962/465689 , vital:76632 , xlink:href="https://hdl.handle.net/10520/EJC-90afb1388"
  • Description: The feature level, unlike the match score level, lacks multi-modal fusion guidelines. This work demonstrates a new approach for improved image-based biometric feature-fusion. The approach extracts and combines the face, fingerprint and palmprint at the feature level for improved human identification accuracy. Feature-fusion guidelines, proposed in our recent work, are extended by adding a new face segmentation method and the support vector machine classifier. The new face segmentation method improves the face identification equal error rate (EER) by 10%. The support vector machine classifier combined with the new feature selection approach, proposed in our recent work, outperforms other classifiers when using a single training sample. Feature-fusion guidelines take the form of strengths and weaknesses as observed in the applied feature processing modules during preliminary experiments. The guidelines are used to implement an effective biometric fusion system at the feature level, using a novel feature-fusion methodology, reducing the EER of two groups of three datasets namely: SDUMLA face, SDUMLA fingerprint and IITD palmprint; MUCT Face, MCYT Fingerprint and CASIA Palmprint.
  • Full Text:
  • Date Issued: 2017

Efficient Biometric Access Control for Larger Scale Populations

  • Authors: Brown, Dane L , Bradshaw, Karen L
  • Date: 2018
  • Subjects: To be catalogued
  • Language: English
  • Type: text , article
  • Identifier: http://hdl.handle.net/10962/465667 , vital:76630 , xlink:href="https://www.researchgate.net/profile/Dane-Brown-2/publication/335378829_Efficient_Biometric_Access_Control_for_Larger_Scale_Populations/links/5d61159ea6fdccc32ccd2c8a/Efficient-Biometric-Access-Control-for-Larger-Scale-Populations.pdf"
  • Description: Biometric applications and databases are growing at an alarming rate. Processing large or complex biometric data induces longer wait times that can limit usability during application. This paper focuses on increasing the processing speed of biometric data, and calls for a parallel approach to data processing that is beyond the capability of a central processing unit (CPU). The graphical processing unit (GPU) is effectively utilized with compute unified device architecture (CUDA), and results in at least triple the processing speed when compared with a previously presented accurate and secure multimodal biometric system. When saturating the CPU-only implementation with more individuals than the available thread count, the GPU-assisted implementation outperforms it exponentially. The GPU-assisted implementation is also validated to have the same accuracy of the original system, and thus shows promising advancements in both accuracy and processing speed in the challenging big data world.
  • Full Text:
  • Date Issued: 2018

Improved palmprint segmentation for robust identification and verification

  • Authors: Brown, Dane L , Bradshaw, Karen L
  • Date: 2019
  • Subjects: To be catalogued
  • Language: English
  • Type: text , article
  • Identifier: http://hdl.handle.net/10962/460576 , vital:75966 , xlink:href="https://doi.org/10.1109/SITIS.2019.00013"
  • Description: This paper introduces an improved approach to palmprint segmentation. The approach enables both contact and contactless palmprints to be segmented regardless of constraining finger positions or whether fingers are even depicted within the image. It is compared with related systems, as well as more comprehensive identification tests, that show consistent results across other datasets. Experiments include contact and contactless palmprint images. The proposed system achieves highly accurate classification results, and highlights the importance of effective image segmentation. The proposed system is practical as it is effective with small or large amounts of training data.
  • Full Text:
  • Date Issued: 2019

Multi-angled face segmentation and identification using limited data

  • Authors: Brown, Dane L
  • Date: 2019
  • Subjects: To be catalogued
  • Language: English
  • Type: text , article
  • Identifier: http://hdl.handle.net/10962/465711 , vital:76634 , xlink:href="https://ieeexplore.ieee.org/abstract/document/9067899"
  • Description: This paper introduces a different approach to face segmentation that aims to improve face recognition when given large pose angles and limited training data. Face segmentation is achieved by extracting landmarks which are manipulated in such a way as to normalize unseen data with a classification model. The approach is compared with related systems, followed by further tests that show consistent results across other datasets. Experiments include frontal and non-frontal training images for classification of various face pose angles. The proposed system is a promising contribution, and especially shows the importance of face segmentation. The results are achieved using minimal training data, such that both accurate and practical face recognition systems can be constructed.
  • Full Text:
  • Date Issued: 2019

Plant disease detection and classification for farmers and everyday gardeners

  • Authors: Poole, Louise C , Brown, Dane L
  • Date: 2019
  • Subjects: To be catalogued
  • Language: English
  • Type: text , article
  • Identifier: http://hdl.handle.net/10962/465722 , vital:76635 , xlink:href="https://www.researchgate.net/profile/Dane-Brown-2/publication/335378684_Plant_Disease_Detection_and_Classification_for_Farmers_and_Everyday_Gardeners/links/5d611905299bf1f70b090b54/Plant-Disease-Detection-and-Classification-for-Farmers-and-Everyday-Gardeners.pdf"
  • Description: Identifying and rating diseases by hand is an expensive, time consuming, subjective and unreliable method as compared to what computers can provide. Image processing and machine learning enable automated disease identification. Research has proven that automated disease identification systems can be used as a preventative measure against plant rot and death. This paper narrows down the best techniques to segment images of leaves toward improved classification of diseases found on those leaves. An investigation is conducted on image segmentation and machine learning techniques, including state-of-the-art systems, to determine the most appropriate approach to prevent death and rot in plants. Promising results were observed during testing, and show that a system can be implemented to assist with plant health that is relevant to both home gardeners and farmers.
  • Full Text:
  • Date Issued: 2019

Poacher detection and wildlife counting system

  • Authors: Brown, Dane L , Schormann, Daniel
  • Date: 2019
  • Subjects: To be catalogued
  • Language: English
  • Type: text , article
  • Identifier: http://hdl.handle.net/10962/465733 , vital:76636 , xlink:href="https://www.researchgate.net/profile/Dane-Brown-2/publication/335378767_Poacher_Detection_and_Wildlife_Counting_System/links/5d6117c7a6fdccc32ccd2cac/Poacher-Detection-and-Wildlife-Counting-System.pdf"
  • Description: The illegal hunting of wildlife is a serious problem, causing a large number of animals to approach extinction or worse. Drones provide a viable option for constant surveillance and multiple instances of using drones for this purpose have been tried. However, existing methods predominantly rely on manual surveillance from camera feeds. This paper shows that using either visible or thermal cameras, with modern image processing and machine learning techniques, enables a system to autonomously detect humans, while tracking animals by their identity number (id). The thermal characteristics of special but inexpensive cameras are used for object detection with centroid tracking, and convolutional neural networks are used to classify humans and wildlife. Classification also enables the counting of wildlife by id, which can help game reserves keep track of wildlife.
  • Full Text:
  • Date Issued: 2019

Virtual Gym Instructor

  • Authors: Brown, Dane L , Ndleve, Mixo
  • Date: 2019
  • Subjects: To be catalogued
  • Language: English
  • Type: text , article
  • Identifier: http://hdl.handle.net/10962/465744 , vital:76637 , xlink:href="https://www.researchgate.net/profile/Dane-Brown-2/publication/335378603_Virtual_Gym_Instructor/links/5d6118a892851c619d7268c1/Virtual-Gym-Instructor.pdf"
  • Description: The fourth industrial revolution and the continuous development of new technologies have presented a golden platter for sedentary living. Noncommunicable diseases such as, cancers, cardiovascular and respiratory deficiencies, and diabetes have reached epidemic levels as a consequence. A traditional gym instructor screens clients to prescribe exercise programs that can help them lower the risk of noncommunicable lifestyle diseases. However, gym instructors often come at a cost and are not always affordable, available or accessible. This research investigated whether modern computing power can be utilized to develop a system in the form of a cost effective alternative exercise program – Virtual Gym Instructor. The system demonstrated perfect realtime object detection and tracking up to four metres away from the camera and produced results for distances up to eight metres away.
  • Full Text:
  • Date Issued: 2019

A Robust Portable Environment for First-Year Computer Science Students

  • Authors: Brown, Dane L , Connan, James
  • Date: 2021
  • Subjects: To be catalogued
  • Language: English
  • Type: text , article
  • Identifier: http://hdl.handle.net/10962/465113 , vital:76574 , xlink:href="https://link.springer.com/chapter/10.1007/978-3-030-92858-2_6"
  • Description: Computer science education in both South African universities and worldwide often aim at making students confident at problem solving by introducing various programming exercises. Standardising a computer environment where students can apply their computational thinking knowledge on a more even playing field – without worrying about software issues – can be beneficial for problem solving in classroom of diverse students. Research shows that having consistent access to this exposes students to core concepts of Computer Science. However, with the diverse student base in South Africa, not everyone has access to a personal computer or expensive software. This paper describes a new approach at first-year level that uses the power of a modified Linux distro on a flash drive to enable access to the same, fully-fledged, free and open-source environment, including the convenience of portability. This is used as a means to even the playing field in a diverse country like South Africa and address the lack of consistent access to a problem solving environment. Feedback from students and staff at the Institution are effectively heeded and attempted to be measured.
  • Full Text:
  • Date Issued: 2021

Adaptive machine learning based network intrusion detection

  • Authors: Chindove, Hatitye E , Brown, Dane L
  • Date: 2021
  • Subjects: To be catalogued
  • Language: English
  • Type: text , article
  • Identifier: http://hdl.handle.net/10962/464052 , vital:76471 , xlink:href="https://doi.org/10.1145/3487923.3487938"
  • Description: Network intrusion detection system (NIDS) adoption is essential for mitigating computer network attacks in various scenarios. However, the increasing complexity of computer networks and attacks make it challenging to classify network traffic. Machine learning (ML) techniques in a NIDS can be affected by different scenarios, and thus the recency, size and applicability of datasets are vital factors to consider when selecting and tuning a machine learning classifier. The proposed approach evaluates relatively new datasets constructed such that they depict real-world scenarios. It includes analyses of dataset balancing and sampling, feature engineering and systematic ML-based NIDS model tuning focused on the adaptive improvement of intrusion detection. A comparison between machine learning classifiers forms part of the evaluation process. Results on the proposed approach model effectiveness for NIDS are discussed. Recurrent neural networks and random forests models consistently achieved high f1-score results with macro f1-scores of 0.73 and 0.87 for the CICIDS 2017 dataset; and 0.73 and 0.72 against the CICIDS 2018 dataset, respectively.
  • Full Text:
  • Date Issued: 2021

Adaptive network intrusion detection using optimised machine learning models

  • Authors: Chindove, Hatitye E , Brown, Dane L
  • Date: 2021
  • Subjects: To be catalogued
  • Language: English
  • Type: text , article
  • Identifier: http://hdl.handle.net/10962/465634 , vital:76627 , xlink:href="https://www.researchgate.net/publication/358046953_Adaptive_Network_Intrusion_Detection_using_Optimised_Machine_Learning_Models"
  • Description: Network intrusion detection system (NIDS) adoption is essential for mitigating computer network attacks in various scenarios. However, the increasing complexity of computer networks and attacks make it challenging to classify network traffic. Machine learning (ML) techniques in a NIDS can be affected by different scenarios, and thus the recency, size and applicability of datasets are vital factors to consider when selecting and tuning a machine learning classifier. The proposed approach evaluates relatively new datasets constructed such that they depict real-world scenarios. It includes empirical analyses of practical, systematic ML-based NIDS with significant network traffic for improved intrusion detection. A comparison between machine learning classifiers, including deep learning, form part of the evaluation process. Results on how the proposed approach increased model effectiveness for NIDS in a more practical setting are discussed. Recurrent neural networks and random forests models consistently achieved the best results.
  • Full Text:
  • Date Issued: 2021

An Evaluation of Machine Learning Methods for Classifying Bot Traffic in Software Defined Networks

  • Authors: Van Staden, Joshua , Brown, Dane L
  • Date: 2021
  • Subjects: To be catalogued
  • Language: English
  • Type: text , article
  • Identifier: http://hdl.handle.net/10962/465645 , vital:76628 , xlink:href="https://link.springer.com/chapter/10.1007/978-981-19-7874-6_72"
  • Description: Internet security is an ever-expanding field. Cyber-attacks occur very frequently, and so detecting them is an important aspect of preserving services. Machine learning offers a helpful tool with which to detect cyber attacks. However, it is impossible to deploy a machine-learning algorithm to detect attacks in a non-centralized network. Software Defined Networks (SDNs) offer a centralized view of a network, allowing machine learning algorithms to detect malicious activity within a network. The InSDN dataset is a recently-released dataset that contains a set of sniffed packets within a virtual SDN. These sniffed packets correspond to various attacks, including DDoS attacks, Probing and Password-Guessing, among others. This study aims to evaluate various machine learning models against this new dataset. Specifically, we aim to evaluate their classification ability and runtimes when trained on fewer features. The machine learning models tested include a Neural Network, Support Vector Machine, Random Forest, Multilayer Perceptron, Logistic Regression, and K-Nearest Neighbours. Cluster-based algorithms such as the K-Nearest Neighbour and Random Forest proved to be the best performers. Linear-based algorithms such as the Multilayer Perceptron performed the worst. This suggests a good level of clustering in the top few features with little space for linear separability. The reduction of features significantly reduced training time, particularly in the better-performing models.
  • Full Text:
  • Date Issued: 2021

An Evaluation of YOLO-Based Algorithms for Hand Detection in the Kitchen

  • Authors: Van Staden, Joshua , Brown, Dane L
  • Date: 2021
  • Subjects: To be catalogued
  • Language: English
  • Type: text , article
  • Identifier: http://hdl.handle.net/10962/465134 , vital:76576 , xlink:href="https://ieeexplore.ieee.org/abstract/document/9519307"
  • Description: Convolutional Neural Networks have offered an accurate method with which to run object detection on images. Specifically, the YOLO family of object detection algorithms have proven to be relatively fast and accurate. Since its inception, the different variants of this algorithm have been tested on different datasets. In this paper, we evaluate the performances of these algorithms on the recent Epic Kitchens-100 dataset. This dataset provides egocentric footage of people interacting with various objects in the kitchen. Most prominently shown in the footage is an egocentric view of the participants' hands. We aim to use the YOLOv3 algorithm to detect these hands within the footage provided in this dataset. In particular, we examine the YOLOv3 algorithm using two different backbones: MobileNet-lite and VGG16. We trained them on a mixture of samples from the Egohands and Epic Kitchens-100 datasets. In a separate experiment, average precision was measured on an unseen Epic Kitchens-100 subset. We found that the models are relatively simple and lead to lower scores on the Epic Kitchens 100 dataset. This is attributed to the high background noise on the Epic Kitchens 100 dataset. Nonetheless, the VGG16 architecture was found to have a higher Average Precision (AP) and is, therefore, more suited for retrospective analysis. None of the models was suitable for real-time analysis due to complex egocentric data.
  • Full Text:
  • Date Issued: 2021

Early dehydration detection using infrared imaging

  • Authors: Poole, Louise C , Brown, Dane L , Connan, James
  • Date: 2021
  • Subjects: To be catalogued
  • Language: English
  • Type: text , article
  • Identifier: http://hdl.handle.net/10962/465656 , vital:76629 , xlink:href="https://www.researchgate.net/profile/Louise-Poole-3/publication/357578445_Early_Dehydration_Detection_Using_Infrared_Imaging/links/61d5664eb8305f7c4b231d50/Early-Dehydration-Detection-Using-Infrared-Imaging.pdf"
  • Description: Crop loss and failure have devastating impacts on a country’s economy and food security. Developing effective and inexpensive systems to minimize crop loss has become essential. Recently, multispectral imaging—in particular visible and infrared imaging—have become popular for analyzing plants and show potential for early identification of plant stress. We created a directly comparable visible and infrared image dataset for dehydration in spinach leaves. We created and compared various models trained on both datasets and concluded that the models trained on the infrared dataset outperformed all of those trained on the visible dataset. In particular, the models trained to identify early signs of dehydration yielded 45% difference in accuracy, with the infrared model obtaining 70% accuracy and the visible model obtaining 25% accuracy. Infrared imaging thus shows promising potential for application in early plant stress and disease identification.
  • Full Text:
  • Date Issued: 2021
  • Disclaimer
  • Privacy
  • Copyright
  • Contact