Human Gender Prediction on Facial Mobil Images using Convolutional Neural Networks

Hacıbeyoğlu, Mehmet; Ibrahim, Mohammed H.

doi:10.18201/ijisae.2018644778

Cited by 11 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chan et al [21] conducted an experiment comparing six shortest path algorithms: Dijkstra's, Symmetrical Dijkstra's, A*, Bellman-Ford, Floyd-Warshall, and Genetic Algorithm. They concluded that the Bellman algorithm was superior among other algorithms as it produced the optimal solution in a short time.…”

Section: Lacorte and Chavezmentioning

confidence: 99%

An Optimised Shortest Path Algorithm for Network Rotuting & SDN

Saxena,

Sabharwal,

Bajaj

2023

IJRITCC

View full text Add to dashboard Cite

Network routing algorithms form the backbone of data transmission in modern network architectures, with implications for efficiency, speed, and reliability. This research aims to critically investigate and compare three prominent routing algorithms: Bellman-Ford, Shortest Path Faster Algorithm (SPFA), and our novel improved variant of Bellman-Ford, the Space-efficient Cost-Balancing Bellman-Ford (SCBF). We evaluate the performance of these algorithms in terms of time and space complexity, memory utilization, and routing efficacy, within a simulated network environment. Our results indicate that while Bellman-Ford provides consistent performance, both SPFA and SCBF present improvements in specific scenarios with the SCBF showing notable enhancements in space efficiency. The innovative SCBF algorithm provides competitive performance and greater space efficiency, potentially making it a valuable contribution to the development of network routing protocols. Further research is encouraged to optimize and evaluate these algorithms in real-world network conditions. This study underscores the continuous need for algorithmic innovation in response to evolving network demands.

show abstract

Section: Lacorte and Chavezmentioning

confidence: 99%

An Optimised Shortest Path Algorithm for Network Rotuting & SDN

Saxena,

Sabharwal,

Bajaj

2023

IJRITCC

View full text Add to dashboard Cite

show abstract

“…Gender prediction models are widely used across different domains such as advertising, security and human–computer interaction. Similar to [ 2 , 6 , 19 , 26 , 36 , 37 , 58 , 77 ], we focus on gender prediction from facial images. Some of these works [ 2 , 19 , 26 , 36 , 58 ] proposed the use of CNN models to predict the gender.…”

Section: Related Workmentioning

confidence: 99%

“…Similar to [ 2 , 6 , 19 , 26 , 36 , 37 , 58 , 77 ], we focus on gender prediction from facial images. Some of these works [ 2 , 19 , 26 , 36 , 58 ] proposed the use of CNN models to predict the gender. Abirami et al [ 2 ] used a CNN model to jointly predict the gender and the age of a person from facial images.…”

Section: Related Workmentioning

confidence: 99%

“…Similarly to the main body of recent works on gender recognition in images, we also employ a CNN model. Different from all the works mentioned so far [ 2 , 19 , 26 , 36 , 58 ], which identify the gender in fully visible faces, we focus on a harder problem, that of predicting the gender in strongly occluded faces. More precisely, we aim to identify the gender of a person wearing a surgical mask, half of the face being occluded.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Teacher–student training and triplet loss to reduce the effect of drastic face occlusion

Duta

Ionescu

2021

Machine Vision and Applications

View full text Add to dashboard Cite

We study a series of recognition tasks in two realistic scenarios requiring the analysis of faces under strong occlusion. On the one hand, we aim to recognize facial expressions of people wearing virtual reality headsets. On the other hand, we aim to estimate the age and identify the gender of people wearing surgical masks. For all these tasks, the common ground is that half of the face is occluded. In this challenging setting, we show that convolutional neural networks trained on fully visible faces exhibit very low performance levels. While fine-tuning the deep learning models on occluded faces is extremely useful, we show that additional performance gains can be obtained by distilling knowledge from models trained on fully visible faces. To this end, we study two knowledge distillation methods, one based on teacher–student training and one based on triplet loss. Our main contribution consists in a novel approach for knowledge distillation based on triplet loss, which generalizes across models and tasks. Furthermore, we consider combining distilled models learned through conventional teacher–student training or through our novel teacher–student training based on triplet loss. We provide empirical evidence showing that, in most cases, both individual and combined knowledge distillation methods bring statistically significant performance improvements. We conduct experiments with three different neural models (VGG-f, VGG-face and ResNet-50) on various tasks (facial expression recognition, gender recognition, age estimation), showing consistent improvements regardless of the model or task.

show abstract

“…GF addition also reduces the crack width and negative temperature effects [12,13]. Data based prediction models including ANN, Multiple Linear Regression (MLR) are widely used in various engineering applications [14][15][16][17]. These models can give further information for a better understanding of the material properties [18].…”

Section: Introductionmentioning

confidence: 99%

Prediction of Bending Strength of Self-Leveling Glass Fiber Reinforced Concrete

Yıldızel¹,

Uzun²,

Çöğürcü³

2019

ijisae

View full text Add to dashboard Cite

Many studies have been conducted on the prediction of fiber reinforced concrete strength; however, there are very rare data concerning the prediction of bending strength values of self-leveling glass fiber reinforced concrete. And there is no study for prediction of bending strength of self-leveling glass fiber reinforced concrete from mixture ingredients and slump values. In the present study, relationships between the bending strength and the mixture proportions are explored. An artificial neural network model (ANN) is designed with an extensive experimental data including 395 four-point bending tests, and input parameters as white cement amount, maximum aggregate size, glass fiber content, water cement ratio, superplasticizer and metakaolin content and slump test results. Effect of each parameter on the bending strength is investigated with the developed model. An empirical and user-friendly formula was obtained with the generalization capabilities of the ANN. Results showed that the prediction results are in good agreement with the field data. And these numerical results with high efficiency can make it possible to use the neural design for real-life self-leveling glass fiber reinforced concrete applications.

show abstract

Human Gender Prediction on Facial Mobil Images using Convolutional Neural Networks

Cited by 11 publications

References 21 publications

An Optimised Shortest Path Algorithm for Network Rotuting & SDN

An Optimised Shortest Path Algorithm for Network Rotuting & SDN

Teacher–student training and triplet loss to reduce the effect of drastic face occlusion

Prediction of Bending Strength of Self-Leveling Glass Fiber Reinforced Concrete

Contact Info

Product

Resources

About