Prediction of the Age and Gender Based on Human Face Images Based on Deep Learning Algorithm

Haseena, S.; Subbaraj, Saroja; Madavan, R.; Karthick, Alagar; Pant, Bhaskar; Kifetew, Melkamu

doi:10.1155/2022/1413597

Cited by 20 publications

(6 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We are interested in combining the Inception-v3 model and the support vector machine (SVM) algorithm, using polynomial, radial basis function (RBF), and sigmoid kernel functions, in facial image-based gender classification. Recent research on facial image-based gender classification we found included: a gender classification using the logistic regression, support vector machine, K-nearest neighbors, naive-Bayes, and decision trees with a FaceNet Inception network embedded facial image, where the average accuracy obtained from this research is 92.084% [6], an emotion, age group and gender classification using the convolutional neural network model with cropped facial image, where the gender classification shows an excellent performance with an accuracy value of 96.65% [7], and the gender prediction using a combination of Inception V3 network and support vector algorithm, where the results show that this combination gave an accuracy value of 93.61% [8]. These results indicate that combining the convolutional neural networks and machine learning algorithms has an excellent performance in classifying human gender based on an input of facial images.…”

Section: Imentioning

confidence: 76%

Transfer Learning for Feral Cat Classification Using Logistic Regression

Tambunan¹,

Rosnelly

Situmorang³

2023

ICoSTEC

View full text Add to dashboard Cite

Machine learning is an alternative tool for classifying animal species, especially feral cats. In this research, we use a machine learning algorithm to classify three species of feral cats: American Wildcat, Black-footed Cat, and European Wildcat. We also use a transfer learning model using the VGG-19 network for extracting the features in the feral cat images. By combining the VGG-19 and logistic regression algorithm, we build six models and compare which one is the best to solve the problem. We evaluate and analyze all models using a 5-fold, 10-fold, and 20- fold cross-validation, with accuracy, precision, and recall as the base performance value. The best result obtained is a model with a lasso regularization and cost parameter value of 1, with an accuracy value of 0.846667, a precision value of 0.845389, and a recall value of 0.846667. We also tune the C parameter in each LR model with values such as 0.1, 0.5, and 1. The most optimum C value for the lasso and ridge regularization is one, resulting in an average value of accuracy = 0.813, precision = 0.812, and recall = 0.813.

show abstract

Section: Imentioning

confidence: 76%

Transfer Learning for Feral Cat Classification Using Logistic Regression

Tambunan¹,

Rosnelly

Situmorang³

2023

ICoSTEC

View full text Add to dashboard Cite

show abstract

“…We use six pre-built, CNNs with weights that have been trained on ImageNet. With the use of a transfer learning technique, technique to extract features from preprocessed hand photos [25]. CNN architectures like VGG16, DeseNet121, MobileNet, NASNet, Xception, and EfficientNet are used in the suggested work [26].…”

Section: Literature Reviewmentioning

confidence: 99%

Age and gender classification with bone images using deep learning algorithms

Sundarasamy,

Kuttuva Rajendran

2023

IJEECS

View full text Add to dashboard Cite

In paediatrics, bone age is a crucial indicator of how a child's skeleton is developing. They have had great success ever since the creation of deep learning (DL)-based bone age prediction tools. Deep features learning, however, has a significant computing overhead problem. Deep convolution layers are used in this technique to learn representative features in the small yet useful regions that are extracted for feature learning. This work suggests using an extreme learning machine algorithm as the fundamental architecture in the final bone age assessment study to realise the rapid computation speed and feature interaction. The viability and efficacy of the suggested strategy have been verified by experiments using data that is openly accessible. The suggested model is explicitly trained using a cutting-edge end-to-end learning architecture employing bone scans to extract the most discriminative patches from the original high-resolution image. The bone picture is the foundation of the procedure. Our main objective is to categorize individuals by age using convolution neural network (CNN) classification models, such as the Xception and Mobile Net models. As a result, we have achieved results that are 90% and 94% accurate in classifying people by age using CNN models.

show abstract

“…A real-time fraud detection technique based on recurrent neural networks was suggested by Wang et al [16]. Many researchers use CNN in various applications [17][18][19]. Suresh Kumar et al, [20] in their study seek to forecast the occurrence of fraud using different machine learning algorithms such as support vector machine (SVM), k-nearest neighbour (KNN), and artificial neural network (ANN).…”

Section: Related Workmentioning

confidence: 99%

An intelligent approach for anomaly detection in credit card data using bat optimization algorithm

Sikkandar,

et al. 2023

View full text Add to dashboard Cite

As technology advances, many people are utilising credit cards to purchase their necessities, and the number of credit card scams is increasing tremendously. However, illegal card transactions have been on the rise, costing financial institutions millions of dollars each year. The development of efficient fraud detection techniques is critical in reducing these deficits, but it is difficult due to the extremely unbalanced nature of most credit card datasets. As compared to conventional fraud detection methods, the proposed method will help in automatically detecting the fraud, identifying hidden correlations in data and reduced time for verification process. This is achieved by selecting relevant and unique features by using Bat Optimization Algorithm (BOA). Next, balancing is performed in the highly imbalanced credit card fraud dataset using Synthetic Minority over-sampling technique (SMOTE). Then finally the CNN model for anomaly detection in credit card data is built using full center loss function to improve fraud detection performance and stability. The proposed model is tested with Kaggle dataset and yields around 99% accuracy.

show abstract

Prediction of the Age and Gender Based on Human Face Images Based on Deep Learning Algorithm

Cited by 20 publications

References 60 publications

Transfer Learning for Feral Cat Classification Using Logistic Regression

Transfer Learning for Feral Cat Classification Using Logistic Regression

Age and gender classification with bone images using deep learning algorithms

An intelligent approach for anomaly detection in credit card data using bat optimization algorithm

Contact Info

Product

Resources

About