Facial Beauty Prediction and Analysis based on Deep Convolutional Neural Network: A Review

Saeed, Jwan Najeeb; Abdulazeez, Adnan Mohsin

doi:10.30880/jscdm.2021.02.01.001

Cited by 36 publications

(29 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Damage to this area will lead to the loss of multisensory information and the decline of integration function. In addition, this area is also a behavioral area, the region where the reaction starts [ 14 – 16 ].…”

Section: Related Workmentioning

confidence: 99%

Neural Network Model for Perceptual Evaluation of Product Modelling Design Based on Multimodal Image Recognition

Jia

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

With the homogenization of product function and performance, the design technology for product appearance quality has been increasingly valued by academia and industry and has become an effective technical way to meet the continuously growing diversified and personalized needs of consumers. The appearance quality attribute of a product can be characterized or described by its appearance image. Data-driven product appearance image design is based on the quantitative data of product appearance and consumer emotional needs and completes the product appearance through computer-aided design technology and intelligent algorithms. Design innovation can help companies quickly respond to consumers’ emotional needs and effectively improve design quality and product competitiveness. When visual objects are disturbed in complex scenes, the issues such as how the human brain coordinates multisensory information processing and what neural processing mechanisms follow are still unclear. In this paper, a visual object recognition experiment in a complex scene was designed and the brain activation signals of three modalities of noise, added audio-visual (AVd), single visual noise and noise (Vd), and single-audio (A), were recorded. The properties and neural processing mechanisms of multisensory modulation of auditory stimuli during noisy image recognition were explored. Using the conjunction method combined with the classic “max criterion” rule, it was found that only when a certain amount of noise was added to the visual stimulus, the integration area changed. The product appearance has a decisive influence on the user’s product perceptual attribute preference and greatly affects the consumer’s satisfaction. The importance of product appearance image design is increasingly prominent. In addition, pattern analysis of brain activation signals confirmed that semantically consistent sounds can facilitate the recognition of noisy images and this facilitation shows a certain category selectivity when subdivided into categories. Using the analysis method of functional connectivity, a functional connectivity network containing nodes at different integration levels was constructed to explore the overall characteristics and processing patterns of the multisensory network. Through the analysis of the network connection relationship, it is found that the prefrontal cortex, STS, and lateral occipital lobe are the nodes with more aggregation in the network, and their functions are similar to the hub in the network. The brain functional network was constructed, and functional connectivity was used to explore the connection characteristics of the network and the multisensory modulation mechanism between different processing levels of the brain.

show abstract

Section: Related Workmentioning

confidence: 99%

Neural Network Model for Perceptual Evaluation of Product Modelling Design Based on Multimodal Image Recognition

Jia

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…The neurons are triggered by means of weighted neuron connections. In order to achieve non-linearity, all intermediate layers are always activated [41] [42]. In tasks like image recognition neural networks have achieved great success; handwriting recognition and optical character [43] [44].…”

Section: Neural Networkmentioning

confidence: 99%

Image Compression Using Neural Networks: A Review

et al. 2021

View full text Add to dashboard Cite

Computer images consist of huge data and thus require more memory space. The compressed image requires less memory space and less transmission time. Imaging and video coding technology in recent years has evolved steadily. However, the image data growth rate is far above the compression ratio growth, Considering image and video acquisition system popularization. It is generally accepted, in particular that further improvement of coding efficiency within the conventional hybrid coding system is increasingly challenged. A new and exciting image compression solution is also offered by the deep convolution neural network (CNN), which in recent years has resumed the neural network and achieved significant success both in artificial intelligent fields and in signal processing. In this paper we include a systematic, detailed and current analysis of image compression techniques based on the neural network. Images are applied to the evolution and growth of compression methods based on the neural networks. In particular, the end-to-end frames based on neural networks are reviewed, revealing fascinating explorations of frameworks/standards for next-generation image coding. The most important studies are highlighted and future trends even envisaged in relation to image coding topics using neural networks.

show abstract

“…Facial geometry, color, texture, and other local characteristics are some examples of featurebased representation. Nonetheless, the effectiveness of statistical and traditional machinelearning techniques for extracting and predicting beauty features diminishes with the emergence of sophisticated deep neural networks [5]. The remarkable capability of CNNs to learn discriminative features has led to significant advancements in computer vision.…”

Section: Introductionmentioning

confidence: 99%

Automatic Facial Aesthetic Prediction Based on Deep Learning with Loss Ensembles

Saeed,

Abdulazeez,

Ibrahim

2023

Applied Sciences

View full text Add to dashboard Cite

Deep data-driven methodologies have significantly enhanced the automatic facial beauty prediction (FBP), particularly convolutional neural networks (CNNs). However, despite its wide utilization in classification-based applications, the adoption of CNN in regression research is still constrained. In addition, biases in beauty scores assigned to facial images, such as preferences for specific, ethnicities, or age groups, present challenges to the effective generalization of models, which may not be appropriately addressed within conventional individual loss functions. Furthermore, regression problems commonly employ L2 loss to measure error rate, and this function is sensitive to outliers, making it difficult to generalize depending on the number of outliers in the training phase. Meanwhile, L1 loss is another regression-loss function that penalizes errors linearly and is less sensitive to outliers. The Log-cosh loss function is a flexible and robust loss function for regression problems. It provides a good compromise between the L1 and L2 loss functions. The Ensemble of multiple loss functions has been proven to improve the performance of deep-learning models in various tasks. In this work, we proposed to ensemble three regression-loss functions, namely L1, L2, and Log-cosh, and subsequently averaging them to create a new composite cost function. This strategy capitalizes on the unique traits of each loss function, constructing a unified framework that harmonizes outlier tolerance, precision, and adaptability. The proposed loss function’s effectiveness was demonstrated by incorporating it with three pretrained CNNs (AlexNet, VGG16-Net, and FIAC-Net) and evaluating it based on three FBP benchmarks (SCUT-FBP, SCUT-FBP5500, and MEBeauty). Integrating FIAC-Net with the proposed loss function yields remarkable outcomes across datasets due to its pretrained task of facial-attractiveness classification. The efficacy is evident in managing uncertain noise distributions, resulting in a strong correlation between machine- and human-rated aesthetic scores, along with low error rates.

show abstract

Facial Beauty Prediction and Analysis based on Deep Convolutional Neural Network: A Review

Cited by 36 publications

References 47 publications

Neural Network Model for Perceptual Evaluation of Product Modelling Design Based on Multimodal Image Recognition

Neural Network Model for Perceptual Evaluation of Product Modelling Design Based on Multimodal Image Recognition

Image Compression Using Neural Networks: A Review

Automatic Facial Aesthetic Prediction Based on Deep Learning with Loss Ensembles

Contact Info

Product

Resources

About