Facial age estimation using pre-trained CNN and transfer learning

Dagher, Issam; Barbara, Dany

doi:10.1007/s11042-021-10739-w

Cited by 20 publications

(10 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The resolution of each figure was at least 224 × 224 pixels and a minimum of 46 figures were obtained from different views for each species. The dataset was later randomly divided into two sets based on [30,[60][61][62][63]: a training set of 80% and a validation set of 20%. The samples used are indicated in the following Fig.…”

Section: Results and Analysis 41 Experimental Settingsmentioning

confidence: 99%

“…Due to the ability of reducing the need for an annotation process based on the knowledge from a previous task [28], the performance of the adaptation of the transfer learned model to a new target dataset with minimum effort is promising. As known in the literature [23,29], transfer learning has been proved to be a better solution for image recognition when compared to training millions of parameter networks or building new paradigms from scratch [30]. Several research works have recently applied transfer learning in some pre-trained CNNs such as VGG, Res-Net, Google-Net, Alex-Net [27,[30][31][32][33], and ImageNet [27,28,[34][35][36] with significant benefits on shorting the training time.…”

Section: Literature Reviewmentioning

confidence: 99%

“…As known in the literature [23,29], transfer learning has been proved to be a better solution for image recognition when compared to training millions of parameter networks or building new paradigms from scratch [30]. Several research works have recently applied transfer learning in some pre-trained CNNs such as VGG, Res-Net, Google-Net, Alex-Net [27,[30][31][32][33], and ImageNet [27,28,[34][35][36] with significant benefits on shorting the training time. The ImageNet is a larger dataset with 1,281,167 and 50,000 images for training and validation, respectively, which are organized into 1000 classes [37].…”

Section: Literature Reviewmentioning

confidence: 99%

“…The FT technique was also used to re-train some of the layers of the baseline model by transferring their weights to the new model [33]. Several research works successfully used this method to improve the accuracy of models in several applications [30,33,34]. Moreover, the softmax used as an activation function represented in Eq.…”

Section: Batch Normalization Dropout Fully-connected (Bndfc) Layersmentioning

confidence: 99%

See 3 more Smart Citations

An Improved Transfer-Learning for Image-Based Species Classification of Protected Indonesians Birds

Yang¹,

Harjoseputro²,

Hu³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

This research proposed an improved transfer-learning bird classification framework to achieve a more precise classification of Protected Indonesia Birds (PIB) which have been identified as the endangered bird species. The framework takes advantage of using the proposed sequence of Batch Normalization Dropout Fully-Connected (BNDFC) layers to enhance the baseline model of transfer learning. The main contribution of this work is the proposed sequence of BNDFC that can be applied to any Convolutional Neural Network (CNN) based model to improve the classification accuracy, especially for image-based species classification problems. The experiment results show that the proposed sequence of BNDFC layers outperform other combination of BNDFC. The addition of BNDFC can improve the model's performance across ten different CNN-based models. On average, BNDFC can improve by approximately 19.88% in Accuracy, 24.43% in F-measure, 17.93% in G-mean, 23.41% in Sensitivity, and 18.76% in Precision. Moreover, applying fine-tuning (FT) is able to enhance the accuracy by 0.85% with a smaller validation loss of 18.33% improvement. In addition, MobileNetV2 was observed to be the best baseline model with the lightest size of 35.9 MB and the highest accuracy of 88.07% in the validation set.

show abstract

Section: Results and Analysis 41 Experimental Settingsmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Section: Batch Normalization Dropout Fully-connected (Bndfc) Layersmentioning

confidence: 99%

See 2 more Smart Citations

An Improved Transfer-Learning for Image-Based Species Classification of Protected Indonesians Birds

Yang¹,

Harjoseputro²,

Hu³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…Transfer learning in deep learning is widely used in small-sample learning, and the results are typically good [19], [27]- [30]. For example, Issam Dagher and Dany Barbara used networks such as VGG, ResNet, and Inception for transfer learning to solve problems related to face age estimation [31]. Li Miao and Wang Jingxian et al applied a transfer learning method for crop disease recognition [32].…”

Section: Introductionmentioning

confidence: 99%

Research on Spider Sex Recognition From Images Based on Deep Learning

Chen¹,

Ding

Liu

et al. 2021

IEEE Access

View full text Add to dashboard Cite

The rapid and accurate identification of spider sex is the first step in spider image recognition. The traditional artificial method used to identify the sex of mature spiders is mainly based on their genital structures (male palps or female epigynum) and highly dependent on the professional background of the identifiers. This article uses computer-based deep learning and transfer learning to identify the sex of spider, explores the design and application of convolutional neural networks in deep learning for spider sex recognition from images, and establishes a neural network model that displays excellent performance in experiments. In addition to optimizing the network model, we select appropriate hyperparameters to improve the accuracy of recognition and reduce the influence of human factors in the identification process. Through a comparison of multiple sets of experiments based on existing sample data collected in the laboratory, we find that the transfer learning method based on Xception can obtain better prediction accuracy than ResNet-152. After data augmentation, the optimization of a combined activation function and the fine-tuning of frozen layers, the prediction accuracy reaches 98.02%, and for an actual measurement of independent samples, the recognition accuracy reaches 92.38%. Therefore, the proposed method can basically replace manual identification and provide a reference for the artificial intelligence-based identification of spider species. Additionally, the model results indicate that male and female dimorphism may exist beyond the non-genital characteristics of spiders. INDEX TERMS deep learning; transfer learning; convolutional neural network; spider sex identification

show abstract

Deep Learning for Age Estimation Using EfficientNet

Aruleba

Viriri

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Facial age estimation using pre-trained CNN and transfer learning

Cited by 20 publications

References 40 publications

An Improved Transfer-Learning for Image-Based Species Classification of Protected Indonesians Birds

An Improved Transfer-Learning for Image-Based Species Classification of Protected Indonesians Birds

Research on Spider Sex Recognition From Images Based on Deep Learning

Deep Learning for Age Estimation Using EfficientNet

Contact Info

Product

Resources

About