Comparative avifaunal richness and diversity in invasive Acacia dealbata patches and adjacent montane grasslands
- Authors: Seath, Jessica , Shackleton, Charlie M
- Date: 2022
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/406585 , vital:70287 , xlink:href="https://hdl.handle.net/10520/ejc-afzoo_v57_i1_a12"
- Description: Abstract Invasive alien species are regarded as the second greatest threat to biodiversity globally. Yet, at a local scale their effects may vary, underlying the requirement for more local-scale studies across taxa and settings. Here we consider the effects of an alien invasive tree (Acacia dealbata, 5–8 m tall) on avifaunal numbers, richness and diversity in A. dealbata patches of three sizes relative to adjacent montane grasslands. Analysis of historical aerial photographs showed that A. dealbata first occurred in the area in the late 1930s/early 1940s and has continued to spread, despite some efforts by the landowner to keep it in check. It now covers approximately 11% of the site. This has provided habitat for a number of bird species more characteristic of wooded vegetation types. The number, richness and diversity of birds were greater in A. dealbata patches than the adjacent grasslands of equivalent size. These measures increased with increasing patch size, but more rapidly for A. dealbata patches than grassland ones. Only six of the 48 species of birds recorded were common between the two vegetation types. The most common feeding guild in the A. dealbata patches was insectivores, whereas in the grasslands it was omnivores. Although the invasion of A. dealbata has added to the habitat diversity of the area, thereby facilitating increased avifaunal diversity, if it continues to spread, then the populations and perhaps richness of grassland birds are likely to be negatively affected.
- Full Text:
- Date Issued: 2022
Comparison of Task Scheduling Algorithms for Traffic Surveillance Application Using Fog Computing
- Authors: Sinqadu, Mluleki , Shibeshi, Zelalem S , Khalid, Khuram
- Date: 2022
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/429150 , vital:72563 , https://doi.org/10.1007/978-3-030-89776-5_3
- Description: One of the issues that service consumers face when using cloud-based solutions is the delay in processing large and real-time data. Fog computing has been introduced as a solution to this issue since it allows the data to be processed at the edge of a network while enabling different tasks to be scheduled for processing in fog devices at the edge network. These devices still require cloud resources to give them the capacity of processing real-time applications. However, scheduling these tasks must be made in such a way that they do not consume all the available resources on a fog device. When a task consumes all available resources, it can lead to network breakdown or high latency which is not acceptable for real-time applications. Therefore, to address this problem, this chapter proposes a task scheduling technique for traffic surveillance vehicular network application through smart cameras. We used the iFogSim simulator, where the scenario of vehicle tracking is considered. Simulations are conducted to find an efficient scheduling algorithm among a pool of available ones that can optimize the energy consumption and average delay of our proposed real-time application model. The results show that the First Come First Serve (FCFS) scheduling algorithm outperforms the Short Job First (SJF), Generalized Priority (GP) and Round Robin (RR) counterparts in terms of average latency, energy usage, execution time and network usage.
- Full Text:
- Date Issued: 2022
Conceptualising public-private partnerships for social innovation through community engagement in higher education institutions
- Authors: Sibhensana, Bertha , Maistry, Savathrie M
- Date: 2022
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/426269 , vital:72337 , xlink:href="https://hdl.handle.net/10520/ejc-high_v37_n1_a11"
- Description: The achievement of human social and economic development has been equated to social innovation. Innovation that focuses on the marginalised communities in South Africa becomes necessary to redress the inequalities created pre-democracy. As social institutions, higher education institutions are well positioned to deal with the challenges of the 21st century, which include poverty, unemployment and inequality, through promoting social innovation. In democratic South Africa the relationship between an institution of higher learning and the community can be viewed as a social innovation. This submission implies that one of the objectives of community engagement as a core function of universities, is to drive the social innovation agenda. The university’s contributions to community development can be viewed in terms of its ability to commit to social innovation. It is a better vehicle for understanding and creating social value in all its forms.
- Full Text:
- Date Issued: 2022
Conclusion. Post-pandemic epilogue-the bad old contract, an even worse contract or a better social contract for informal workers?
- Authors: Alfers, Laura C , Chen, Martha A , Plagerson, Sophie
- Date: 2022
- Subjects: To be catalogued
- Language: English
- Type: text , book chapter
- Identifier: http://hdl.handle.net/10962/478183 , vital:78162 , ISBN 9781839108068 , https://doi.org/10.4337/9781839108068.00017
- Description: Since we started working on this book, the world has changed profoundly, calling further into question the fairness and adequacy of current social contracts. For informal workers, the COVID-19 crisis has had devasting economic and social impacts: it has upended livelihoods, accentuated health risks, interrupted schooling and forced many households into deeper debt. Many informal workers live in crowded informal settlements with little or no access to water and sanitation, and limited access to health care. Because informal workers depend on their daily earnings to survive, they face the risk of falling into extreme poverty as a result of government-ordered lockdowns and other economic disruptions. Women informal workers face additional challenges because of their care and domestic responsibilities. The pandemic recession intensified workers’ existing vulnerabilities as many were not able to work indefinitely without any kind of social or financial protection to fall back upon.
- Full Text:
- Date Issued: 2022
Constellations, technicality, iconisation and Eskom: A case from South Africa’s Business Day
- Authors: Siebörger, Ian , Adendorff, Ralph D
- Date: 2022
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/385350 , vital:68010 , xlink:href="https://doi.org/10.2989/16073614.2022.2040369"
- Description: This article uses Legitimation Code Theory (LCT) and systemic functional linguistics (SFL) to explore interactions between various resources for building economic and political knowledge in a 2015 article from Business Day, a South African newspaper, concerning the country’s energy crisis. We use LCT to observe how three constellations are built in the article: a ‘developmental state’ constellation; a ‘neo-liberal’ constellation; and another underarticulated constellation that selectively draws ideas from both the preceding constellations. These constellations are built through the unfolding of the text using various linguistic resources, which we describe using SFL, including technicality and iconisation. We identify instances where words are charged with both ideational and axiological meaning concurrently, challenging existing understandings of the process of iconisation.
- Full Text:
- Date Issued: 2022
Constellations, technicality, iconisation and Eskom: A case from South Africa’s Business Day
- Authors: Siebörger, Ian , Adendorff, Ralph D
- Date: 2022
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/469337 , vital:77233 , https://doi.org/10.2989/16073614.2022.2040369
- Description: This article uses Legitimation Code Theory (LCT) and systemic functional linguistics (SFL) to explore interactions between various resources for building economic and political knowledge in a 2015 article from Business Day, a South African newspaper, concerning the country’s energy crisis. We use LCT to observe how three constellations are built in the article: a ‘developmental state’ constellation; a ‘neo-liberal’ constellation; and another underarticulated constellation that selectively draws ideas from both the preceding constellations. These constellations are built through the unfolding of the text using various linguistic resources, which we describe using SFL, including technicality and iconisation. We identify instances where words are charged with both ideational and axiological meaning concurrently, challenging existing understandings of the process of iconisation.
- Full Text:
- Date Issued: 2022
Copyright complications and consequences at the International Library of African Music, Rhodes University: A case study
- Authors: McConnachie, Boudina E
- Date: 2022
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/480183 , vital:78404 , xlink:href="https://hdl.handle.net/10520/ejc-samus1-v41_42-n1-a11"
- Description: This research aims to explore the position of copyright in contemporary South African legislation, with the International Library of African Music (ILAM) being used as a case study. The catalyst was a contract between the Smithsonian Institution, U.S.A. and ILAM for the Smithsonian Global Sound Network project which requested ILAM to trace and find performers of archived materials to pay out royalties. The research was conducted using various approaches, namely qualitative, quantitative and historical methods which were accomplished through substantial internet and library research coupled with source field research. Recorded interviews provided essential historical and qualitative data, while quantitative data was gathered from various sources. The focus of the investigation concentrated on the 1000 tracks from the Sound of Africa Series, which were delivered to the Smithsonian Global Network under a licensing agreement. In an endeavour to assess the feasibility of the GSN/ILAM Contract stipulations, field work was undertaken using both video and audio recordings to detail the complications of trying to locate, if not the original performer of the contracted tracks, then the surviving members of their families in South Africa. The bulk of the research, however, related to deciphering the contract and its associated implications for ILAM and the musicians recorded. The research took place in the Eastern Cape of South Africa and the trial research intervention was confined to a single performer who was recorded by Hugh Tracey in the Ngqushwa (Peddie) District. The research remains relevant, and findings show that all archives currently involved in field recording need to put careful policies in place. Benefit-sharing agreements and Memoranda of Understandings relating to clear copyright and intellectual property ownership declarations must be signed upfront to reassure creatives and musicians that their rights are valued and that the researchers’ obligations will be followed through.
- Full Text:
- Date Issued: 2022
COVID-19 and informal work in 11 cities: recovery pathways amidst continued crisis
- Authors: Alfers, Laura C , Braham, Christy , Chen, Martha A , Grapsa, Erofili , Harvey, Jenna , Ismail, Ghida , Ogando, Ana C , Reed, Sarah O , Roever, Sally , Rogan, Michael , Sinha, Shalini , Skinner, Caroline , Valdivia, Marcela
- Date: 2022
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/473850 , vital:77687 , https://www.wiego.org/publications/covid-19-and-informal-work-11-cities-recovery-pathways-amidst-continued-crisis
- Description: The majority of the global workforce–61%–is informal and has been disproportionately impacted by measures to prevent the spread of COVID-19 and by the accompanying economic down-turn. The focus on aggregate job and livelihood losses masks the multiple drivers behind these losses that are leaving labour mar-kets in general, but particularly in developing countries, without a viable path to recovery. The global informal workforce is diverse, and understanding experiences of workers in different contexts and sectors is required to design effective recovery policies. This Working Paper reflects the findings from the longitudinal study of nearly 2,000 informal workers in 11 cities around the world. Sur-veys and in-depth interviews were conducted with domestic workers, home-based workers, street vendors and market traders, and waste pickers in mid-2020 and then again in mid-2021. The findings reveal the differentiated pathways of impact and thus re-covery for different groups of informal workers approximately a year and a half into the pandemic. The study shows that the eco-nomic fallout of the COVID-19 crisis remains deep and persistent for workers at the base of the economy. Key findings include: Earnings for informal workers interviewed are still far below their pre-pandemic levels. Most respondents have not fully recovered their ability to work. By mid-2021, the typical worker was only earning 64% of her/his pre-COVID-19 earnings. In addition, the average number of days worked per week was only four in mid-2021, still considerably lower than the 5.5-day average in the pre-pandemic period.
- Full Text:
- Date Issued: 2022
COVID-19 and informal work: Degrees and pathways of impact in 11 cities around the world
- Authors: Chen, Martha A , Grapsa, Erofili , Ismail, Ghida , Reed, Sarah O , Rogan, Michael , Valdivia, Marcela
- Date: 2022
- Subjects: To be catalogued
- Language: English
- Type: text , book
- Identifier: http://hdl.handle.net/10962/478150 , vital:78159 , ISBN 978-92-9267-176-1 , doi:10.35188/UNU-WIDER/2022/176-1
- Description: This paper presents findings from two rounds (2020 and 2021) of a study on the impact of the COVID-19 crisis on informal workers in 11 cities across five regions of the world (Africa, Asia, Eastern Europe, Latin America, and North America). The study, carried out by the WIEGO network in partnership with local organizations of informal workers in each city, included a survey questionnaire and key informant interviews, both conducted by phone. The study findings confirm that the pandemic recession severely undermined the livelihoods of informal workers with limited recovery by mid-2021. The study also examined the degree-and pathways-of impact between, and within, different sectors of informal workers and provides insights and demands from informal workers in their own words.
- Full Text:
- Date Issued: 2022
COVID-19 and informal work: Evidence from 11 cities
- Authors: Chen, Martha A , Grapsa, Erofili , Ismail, Ghida , Rogan, Michael , Valdivia, Marcela , Alfers, Laura C , Harvey, Jenna , Ogando, Ana C , Reed, Sarah O , Roever, Sally
- Date: 2022
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/473839 , vital:77686 , https://doi.org/10.1111/ilr.12221
- Description: This article presents the findings for 11 cities across five geographical regions from a study led by Women in Informal Employment: Globalizing and Organizing, investigating the impacts of the COVID-19 crisis on different groups of informal workers and their households. Detailing impacts on work and income, food and hunger, care and other household responsibilities, and on the coping strategies of informal worker households, the article also compares the roles of government and informal worker organizations in providing relief and other support. Based on worker demands, the authors present guiding principles for a better deal for informal workers going forward.
- Full Text:
- Date Issued: 2022
COVID-19 et travail informel: les enseignements d'une étude sur la situation dans onze grandes villes
- Authors: Chen, Martha A , Grapsa, Erofili , Ismail, Ghida , Rogan, Michael , Valdivia, Marcela , Alfers, Laura C , Harvey, Jenna , Ogando, Ana C , Reed, Sarah O , Roever, Sally
- Date: 2022
- Subjects: To be catalogued
- Language: French
- Type: text , article
- Identifier: http://hdl.handle.net/10962/473861 , vital:77688 , https://doi.org/10.1111/ilrf.12230
- Description: Les auteurs présentent les conclusions d'une étude dirigée par le réseau Femmes dans l'emploi informel: globalisation et organisation (WIEGO) sur les effets de la crise du COVID‐19 sur les travailleurs informels. L'analyse porte sur quatre professions et onze grandes villes de cinq régions. Il y est question du travail et des revenus, de l'accès à l'alimentation et de la faim, des responsabilités familiales et domestiques, ainsi que des stratégies d'adaptation des ménages. Les auteurs évoquent également les mesures de soutien proposées par les gouvernements et les organisations de travailleurs informels. Enfin, ils énoncent une série de principes devant guider l'action en faveur de ce groupe.
- Full Text:
- Date Issued: 2022
COVID-19 y trabajo informal: evidencia de once ciudades
- Authors: Chen, Martha A , Grapsa, Erofili , Ismail, Ghida , Rogan, Michael , Valdivia, Marcela , Alfers, Laura C , Harvey, Jenna , Ogando, Ana C , Reed, Sarah O , Roever, Sally
- Date: 2022
- Subjects: To be catalogued
- Language: French
- Type: text , article
- Identifier: http://hdl.handle.net/10962/473872 , vital:77689 , https://doi.org/10.1111/ilrs.12231
- Description: Se presentan las conclusiones de un estudio dirigido por la red Mujeres en Empleo Informal: Globalizando y Organizando (WIEGO), en el que se investigan las repercusiones de la crisis de la COVID‐19 en diferentes grupos de personas trabajadoras informales y en sus hogares en términos de empleo, ingresos, alimentación y hambre, cuidado y otras responsabilidades domésticas, así como las estrategias de afrontamiento de estas personas. Se comparan los roles de los gobiernos y de las organizaciones de personas trabajadoras informales en la prestación de diversas ayudas. Basándose en las reivindicaciones de estas personas, se plantean principios rectores para mejorar su situación en el futuro.
- Full Text:
- Date Issued: 2022
Cross boundary fluxes: Basal resource use by aquatic invertebrates matches fatty acid transfers from river to land
- Authors: Moyo, Sydney , Richoux, Nicole B
- Date: 2022
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/454304 , vital:75334 , xlink:href="https://doi.org/10.1016/j.limno.2022.126035"
- Description: Emerging insects transfer valuable lipids originating in aquatic food sources to terrestrial consumers. The objective of this study was to determine how the export of physiologically important fatty acids from a river to adjacent land via insect emergence relates to the type and quality of the aquatic food consumed, and which emerging insects were primarily responsible for these fluxes. We ran mixing models and hypervolumes incorporating stable carbon isotope ratios of basal resources and emergent invertebrates to determine the major contributors to insect larvae diets. Our data revealed that aquatic food sources (epiphyton, epilithon and suspended particulate matter) were the major organic matter sources (more than 50 %) supporting consumers (Diptera, Ephemeroptera, Odonata and Trichoptera), with allochthonous food sources (C3 plants) being of importance at upstream sites. We calculated fluxes of highly unsaturated fatty acids (HUFAs) via emerging insects and found that these corresponded with the spatial and temporal patterns in the nutritional quality of these same basal resources in the river (quality measured as concentrations of HUFAs). These patterns provide evidence of a direct coupling between food quality and trophic subsidy fluxes from water to land, particularly by emergent dipterans and ephemeropterans.
- Full Text:
- Date Issued: 2022
Cultural Seascapes in the ‘Sea of Calms’ and La Restinga Coast
- Authors: De la Cruz-Modino, Raquel , Piñeiro-Corbeira, Cristina , Aswani, Shankar , González-Cruz, Carla , Domínguez, David , Ordóñez García, Paula , Santana-Talavera, Agustín , Pascual-Fernández, José
- Date: 2022
- Subjects: To be catalogued
- Language: English
- Type: text , book
- Identifier: http://hdl.handle.net/10962/391319 , vital:68641 , ISBN 978-3-031-07289-5 , https://doi.org/10.1007/978-3-031-07289-5
- Description: El Hierro has been characterized by the balance between human development and environmental sustainability. The island was historically far from the mass tourism developments dominant on the other Canary Islands. Tourism accommodations in El Hierro are few compared to more developed coastal areas in the Archipelago, and recreational activities are mainly linked to cultural and natural sites and resources. This chapter focuses on La Restinga fishing village and its coasts, where the ‘Sea of Calms’ and one multiple-use Marine Reserve (MR) are located, both of which became popular over the last decade. The tourist development experience has promoted a new way of looking at the sea and conceptualizing its habitats and populations. In 2014, after the submarine volcano eruption occurred in 2011, we estimated that at least 25,391 dives had been carried out in the diving spots established by the MR and other diving sites close to La Restinga. Despite the difficulties experienced after the volcano eruption, a unique imaginaire has been consolidated, thanks to the image of the island's exclusive nature and iconic elements. In addition, the rapid recovery of the destination is an excellent example of how the tourism system can adapt and incorporate unexpected events such as volcanic eruptions.
- Full Text:
- Date Issued: 2022
Dark brown three-legged round African clay pot
- Date: 2022 , 2022-10-05
- Subjects: Bam, Brigalia , Pottery, African
- Language: English
- Type: realia
- Identifier: http://hdl.handle.net/10948/56874 , vital:57197
- Description: Dark brown round African clay pot, with three legs and a shield pattern. Interior of pot is cream coloured. , Donated/gifted to Nelson Mandela University Archives , Forms part of: Brigalia Bam collection
- Full Text: false
- Date Issued: 2022
Deciphering Isoniazid Drug Resistance Mechanisms on Dimeric Mycobacterium tuberculosis KatG via Post-molecular Dynamics Analyses Including Combined Dynamic Residue Network Metrics
- Authors: Barozi, Victor , Musyoka, Thommas M , Sheik Amamuddy, Olivier , Tastan Bishop, Özlem
- Date: 2022
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/474493 , vital:77713 , https://doi.org/10.1021/acsomega.2c01036
- Description: Resistance mutations in Mycobacterium tuberculosis (Mtb) catalase peroxidase protein (KatG), an essential enzyme in isoniazid (INH) activation, reduce the sensitivity of Mtb to first-line drugs, hence presenting challenges in tuberculosis (TB) management. Thus, understanding the mutational imposed resistance mechanisms remains of utmost importance in the quest to reduce the TB burden. Herein, effects of 11 high confidence mutations in the KatG structure and residue network communication patterns were determined using extensive computational approaches. Combined traditional post-molecular dynamics analysis and comparative essential dynamics revealed that the mutant proteins have significant loop flexibility around the heme binding pocket and enhanced asymmetric protomer behavior with respect to wild-type (WT) protein. Heme contact analysis between WT and mutant proteins identified a reduction to no contact between heme and residue His270, a covalent bond vital for the heme-enabled KatG catalytic activity. Betweenness centrality calculations showed large hub ensembles with new hubs especially around the binding cavity and expanded to the dimerization domain via interface in the mutant systems, providing possible compensatory allosteric communication paths for the active site as a result of the mutations which may destabilize the heme binding pocket and the loops in its vicinity. Additionally, an interesting observation came from Eigencentrality hubs, most of which are located in the C-terminal domain, indicating relevance of the domain in the protease functionality. Overall, our results provide insight toward the mechanisms involved in KatG-INH resistance in addition to identifying key regions in the enzyme functionality, which can be used for future drug design.
- Full Text:
- Date Issued: 2022
Decoration of glass wool with zinc (II) phthalocyanine for the photocatalytic transformation of methyl orange
- Authors: Sindelo, Azole , Britton, Jonathan , Lanterna, Anabel E , Scaiano, Juan C , Nyokong, Tebello
- Date: 2022
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/295742 , vital:57374 , xlink:href="https://doi.org/10.1016/j.jphotochem.2022.114127"
- Description: Zinc phthalocyanines containing one (mono carboxy phenoxy, ZnMCPPc), four (tetra carboxy phenoxy, ZnTCPPc), and eight (tetra isophthalic acid, ZnTIPAPc) carboxyl groups were covalently conjugated to amine-functionalized glass wool (GW). The GW-Pcs were characterized and evaluated for singlet oxygen generation. The photocatalytic efficiencies of the GW-Pcs were assessed using methyl orange. Glass wool alone and the modified conjugates exhibited low to no degradation of methyl orange in the dark. The improved catalytic rate was observed for GW-ZnMCPPc and GW-ZnTCPPc compared to GW-ZnTIPAPc due to the latter's lower singlet oxygen quantum yield generation. In addition, the modified glass wool was recyclable, making it suitable candidates for future environmental applications.
- Full Text:
- Date Issued: 2022
Deep face-iris recognition using robust image segmentation and hyperparameter tuning
- Authors: Brown, Dane L
- Date: 2022
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/465145 , vital:76577 , xlink:href="https://link.springer.com/chapter/10.1007/978-981-16-3728-5_19"
- Description: Biometrics are increasingly being used for tasks that involve sensitive or financial data. Hitherto, security on devices such as smartphones has not been a priority. Furthermore, users tend to ignore the security features in favour of more rapid access to the device. A bimodal system is proposed that enhances security by utilizing face and iris biometrics from a single image. The motivation behind this is the ability to acquire both biometrics simultaneously in one shot. The system’s biometric components: face, iris(es) and their fusion are evaluated. They are also compared to related studies. The best results were yielded by a proposed lightweight Convolutional Neural Network architecture, outperforming tuned VGG-16, Xception, SVM and the related works. The system shows advancements to ‘at-a-distance’ biometric recognition for limited and high computational capacity computing devices. All deep learning algorithms are provided with augmented data, included in the tuning process, enabling additional accuracy gains. Highlights include near-perfect fivefold cross-validation accuracy on the IITD-Iris dataset when performing identification. Verification tests were carried out on the challenging CASIA-Iris-Distance dataset and performed well on few training samples. The proposed system is practical for small or large amounts of training data and shows great promise for at-a-distance recognition and biometric fusion.
- Full Text:
- Date Issued: 2022
Deep Learning Approach to Image Deblurring and Image Super-Resolution using DeblurGAN and SRGAN
- Authors: Kuhlane, Luxolo L , Brown, Dane L , Connan, James , Boby, Alden , Marais, Marc
- Date: 2022
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/465157 , vital:76578 , xlink:href="https://www.researchgate.net/profile/Luxolo-Kuhlane/publication/363257796_Deep_Learning_Approach_to_Image_Deblurring_and_Image_Super-Resolution_using_DeblurGAN_and_SRGAN/links/6313b5a01ddd44702131b3df/Deep-Learning-Approach-to-Image-Deblurring-and-Image-Super-Resolution-using-DeblurGAN-and-SRGAN.pdf"
- Description: Deblurring is the task of restoring a blurred image to a sharp one, retrieving the information lost due to the blur of an image. Image deblurring and super-resolution, as representative image restoration problems, have been studied for a decade. Due to their wide range of applications, numerous techniques have been proposed to tackle these problems, inspiring innovations for better performance. Deep learning has become a robust framework for many image processing tasks, including restoration. In particular, generative adversarial networks (GANs), proposed by [1], have demonstrated remarkable performances in generating plausible images. However, training GANs for image restoration is a non-trivial task. This research investigates optimization schemes for GANs that improve image quality by providing meaningful training objective functions. In this paper we use a DeblurGAN and Super-Resolution Generative Adversarial Network (SRGAN) on the chosen dataset.
- Full Text:
- Date Issued: 2022
Deep Palmprint Recognition with Alignment and Augmentation of Limited Training Samples
- Authors: Brown, Dane L , Bradshaw, Karen L
- Date: 2022
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/440249 , vital:73760 , xlink:href="https://doi.org/10.1007/s42979-021-00859-3"
- Description: This paper builds upon a previously proposed automatic palmprint alignment and classification system. The proposed system was geared towards palmprints acquired from either contact or contactless sensors. It was robust to finger location and fist shape changes—accurately extracting the palmprints in images without fingers. An extension to this previous work includes comparisons of traditional and deep learning models, both with hyperparameter tuning. The proposed methods are compared with related verification systems and a detailed evaluation of open-set identification. The best results were yielded by a proposed Convolutional Neural Network, based on VGG-16, and outperforming tuned VGG-16 and Xception architectures. All deep learning algorithms are provided with augmented data, included in the tuning process, enabling significant accuracy gains. Highlights include near-zero and zero EER on IITD-Palmprint verification using one training sample and leave-one-out strategy, respectively. Therefore, the proposed palmprint system is practical as it is effective on data containing many and few training examples.
- Full Text:
- Date Issued: 2022