Child Face Recognition with Deep Learning

Oo, Shun Lei Myat; Oo, Aung Nway

doi:10.1109/aitc.2019.8921152

Cited by 7 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For children identification, mostly face recognition is used. Face recognition has been applied to find missing children, support school safety and even social network activities of children (Oo & Oo, 2019). Children face long-term recognition is a challenging task, because children face is hard to recognize.…”

Section: Methodsmentioning

confidence: 99%

“…Authors use three CNN for children face recognition to evaluate accuracy of networks, one VGG Face based and two VGG16 and ResNet50 based. Research authors conclude that MobileFaceNet data set provide best examples to train algorithms with improved accuracy (Oo & Oo, 2019). Children attendance to examinations to identify authenticity of person who takes the test has been also researched with implementation of deep learning functionality into schools CCTV systems (Othman & Aydin, 2019).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning solution for children long-term identification

Bumanis¹,

Vītols²,

Arhipova³

et al. 2020

Research for Rural Development

View full text Add to dashboard Cite

Deep learning algorithms are becoming default solution for application in business processes where recognition, identification and automated learning are involved. For human identification, analysis of various features can be applied. Face feature analysis is most popular method for identification of person in various stages of life, including children and infants. The aim of this research was to propose deep learning solution for long-term identification of children in educational institutions. Previously proposed conceptual model for long-term re-identification was enhanced. The enhancements include processing of unexpected persons’ scenarios, knowledge base improvements based on results of supervised and unsupervised learning, implementation of video surveillance zones within educational institutions and object tracking results’ data chaining between multiple logical processes. Object tracking results are the solution we found for long-term identification realization.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Deep learning solution for children long-term identification

Bumanis¹,

Vītols²,

Arhipova³

et al. 2020

Research for Rural Development

View full text Add to dashboard Cite

show abstract

“…Unfortunately, these are usually done for the facilitation of school related activities with no real purpose but mainly to conduct just to have the record your performance. According to the study of Prof. Mya Oo (2016), the need to form a professional learning community in every school, where teacher, administrators, parents, and students work together to seek out best practices, test them in the classroom, continuously improve practices, and focus on results. Prof. Oo"s study focuses on the Deming"s Plan-Do-Check-Act (PDCA) cycle which assess impact of teaching and systematize continuous improvement, corroborated the study on the level of assessment in the three phases Assess, Plan, and Act.…”

Section: Profile Of the Parents And Lgu Representativesmentioning

confidence: 99%

Assessment of School Improvement Plan 2013-2015: Basis for the Technical Assistance Plan

Craus,

Geroso,

Maguate

2023

int.jour.sci.res.mana

View full text Add to dashboard Cite

This study aimed to determine the level of assessment of School Improvement Plan 2013-2015: basis for the Technical Assistance Plan in the Division of Sagay City, Negros Occidental. The respondents of the study were the 72 school heads, 72 teachers-representatives who were member of the school planning team, 72 parents and 25 LGU representatives in the Division of Sagay City. The validated instruments were distributed and discussed during the Focus Group Discussion to the four group of respondents. The study employed the descriptive research design. The processing of data was done with the use of Statistical Package for Social Sciences (SPSS) Software.The mean was used to determine the level of assessment of the four groups of respondents in the three phases and when they are grouped according to their profile variables. Mann-Whitney U-Test was used to determine whether or not significant difference existed on the level of assessment of school improvement plan in the three phases when the four group of respondents were grouped and compared according to their profile variables. Qualitative questions were classified, grouped and synthesized based on the magnitude of observation for intervention. Results of the study showed that the level of assessment of the school heads revealed a very high rating in the Assess, Plan and Act phases and when taken as a whole. Teachers rated the three phases in a high level. Parents rated the Assess phase in a high level, while Plan and Act phases in a moderate level. Likewise, LGU representatives rates the Assess phase in a very high level, Plan phase as high level and the Act phase as moderate level. When differences were considered school heads, parents and LGU representatives find no significant difference on the level of assessment on school improvement plan. Teachers revealed a significant difference in the Assess phase when grouped and compared according to position title. For the Plan phase, a significant difference found when grouped according to highest educational attainment, position title and average family monthly income. Further, for Act phase, a significant difference existed when grouped according to age. The rest of the responses find no significant difference. Examining deeper the results of the study reveals that it is essential for DepEd Division of Sagay City to package technical assistance plan for the four respondents on various issues contributory to the crafting of School Improvement Plan.

show abstract