The cluster assessment of facial attractiveness using fuzzy neural network classifier based on 3D Moiré features

Chiang, Wen-Chung; Lin, Hsiu-Hsia; Huang, Chiung-Shing; Lo, Lun-Jou; Wan, Shu-Yen

doi:10.1016/j.patcog.2013.09.007

Cited by 32 publications

(12 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some ideal facial models were established using computer software [20], and made further efforts to sum up four main geometric features which had the greatest influences on FBP. Also, new geometric features based on 3D face images was proposed [21], and the advantage of a fuzzy neural network is utilized to improve the performance of FBP. Zhang et al [22] mapped faces onto an average face shape space by using facial landmarks.…”

Section: Related Workmentioning

confidence: 99%

Asian Female Facial Beauty Prediction Using Deep Neural Networks via Transfer Learning and Multi-Channel Feature Fusion

Zhai

Huang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Facial beauty plays an important role in many fields today, such as digital entertainment, facial beautification surgery and etc. However, the facial beauty prediction task has the challenges of insufficient training datasets, low performance of traditional methods, and rarely takes advantage of the feature learning of Convolutional Neural Networks. In this paper, a transfer learning based CNN method that integrates multiple channel features is utilized for Asian female facial beauty prediction tasks. Firstly, a Large-Scale Asian Female Beauty Dataset (LSAFBD) with a more reasonable distribution has been established. Secondly, in order to improve CNN's self-learning ability of facial beauty prediction task, an effective CNN using a novel Softmax-MSE loss function and a double activation layer has been proposed. Then, a data augmentation method and transfer learning strategy were also utilized to mitigate the impact of insufficient data on proposed CNN performance. Finally, a multi-channel feature fusion method was explored to further optimize the proposed CNN model. Experimental results show that the proposed method is superior to traditional learning method combating the Asian female FBP task. Compared with other state-of-the-art CNN models, the proposed CNN model can improve the rank-1 recognition rate from 60.40% to 64.85%, and the pearson correlation coefficient from 0.8594 to 0.8829 on the LSAFBD and obtained 0.9200 regression prediction results on the SCUT dataset. INDEX TERMS Convolutional neural network (CNN), double activation layer, facial beauty prediction (FBP), feature fusion, softmax-MSE loss, transfer learning.

show abstract

Section: Related Workmentioning

confidence: 99%

Asian Female Facial Beauty Prediction Using Deep Neural Networks via Transfer Learning and Multi-Channel Feature Fusion

Zhai

Huang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…This would make the registration unreliable. Specifically, landmarks can be greatly displaced in case of superimposing pre-and post-surgical images [5][6][7]: facial features may be shifted, distorted or even missing after a surgery [8].…”

Section: Introductionmentioning

confidence: 99%

Disturbance-Region Removal on Landmark-less Registration of Craniofacial Images Acquired by CBCT and 3D Photography

Wan¹,

Lo²,

Chang³

2021

IJETAE

Self Cite

View full text Add to dashboard Cite

Superimposition of cranio-maxillofacial images acquired from cone-beam computed tomography (CBCT) and facial images acquired from three-dimensional photography (3D photography) can assist in diagnosis and surgical planning. Conventional approaches individually identified prominent facial landmarks on both modalities, respectively and assessed their correspondence. Considering, however, variation of facial expressions or drastic feature distortion when the face or head was imaged at different timing, landmark registration can become challenging. This paper proposes a disturbance-region removal (DRR) procedure to improve the efficacy of registration. The disturbance regions (DRs) are defined as those exhibiting strong responses in the concavity intensity maps that are computed from the facial surface mesh. Following this identification process for the DRs, an adapted symmetric region growing algorithm is used to form the connected DRs that are to be removed prior to superimposition of both modalities. The results show a twenty-eight percent better match of overall correspondence of the facial fiducial markers. Instead of being the registration guides in conventional approaches, in this study the fiducial markers are employed as only a means to assess the performance of registration

show abstract

“…We find that FBP have been formulated the recognition of facial beauty as a specific supervised learning problem of classification [15], [20], [27], [30], regression [13], [19], [23], [29], [38] or ranking [24], [25], [37]. It indicates that FBP is intrinsically a computation problem with multiple paradigms.…”

Section: Introductionmentioning

confidence: 99%

SCUT-FBP5500: A Diverse Benchmark Dataset for Multi-Paradigm Facial Beauty Prediction

Liang

Lin

Jin

et al. 2018

2018 24th International Conference on Pattern Recognition (ICPR)

146

110

View full text Add to dashboard Cite

Facial beauty prediction (FBP) is a significant visual recognition problem to make assessment of facial attractiveness that is consistent to human perception. To tackle this problem, various data-driven models, especially state-of-the-art deep learning techniques, were introduced, and benchmark dataset become one of the essential elements to achieve FBP. Previous works have formulated the recognition of facial beauty as a specific supervised learning problem of classification, regression or ranking, which indicates that FBP is intrinsically a computation problem with multiple paradigms. However, most of FBP benchmark datasets were built under specific computation constrains, which limits the performance and flexibility of the computational model trained on the dataset. In this paper, we argue that FBP is a multi-paradigm computation problem, and propose a new diverse benchmark dataset, called SCUT-FBP5500, to achieve multi-paradigm facial beauty prediction. The SCUT-FBP5500 dataset has totally 5500 frontal faces with diverse properties (male/female, Asian/Caucasian, ages) and diverse labels (face landmarks, beauty scores within [1,5], beauty score distribution), which allows different computational models with different FBP paradigms, such as appearance-based/shape-based facial beauty classification/regression model for male/female of Asian/Caucasian. We evaluated the SCUT-FBP5500 dataset for FBP using different combinations of feature and predictor, and various deep learning methods. The results indicates the improvement of FBP and the potential applications based on the SCUT-FBP5500.

show abstract

The cluster assessment of facial attractiveness using fuzzy neural network classifier based on 3D Moiré features

Cited by 32 publications

References 30 publications

Asian Female Facial Beauty Prediction Using Deep Neural Networks via Transfer Learning and Multi-Channel Feature Fusion

Asian Female Facial Beauty Prediction Using Deep Neural Networks via Transfer Learning and Multi-Channel Feature Fusion

Disturbance-Region Removal on Landmark-less Registration of Craniofacial Images Acquired by CBCT and 3D Photography

SCUT-FBP5500: A Diverse Benchmark Dataset for Multi-Paradigm Facial Beauty Prediction

Contact Info

Product

Resources

About