Age estimation method combining improved CloFormer model and ordinal regression

doi:10.11772/j.issn.1001-9081.2023081199

Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (8): 2372-2380.DOI: 10.11772/j.issn.1001-9081.2023081199

• Artificial intelligence • Previous Articles Next Articles

Age estimation method combining improved CloFormer model and ordinal regression

Shuai FU¹^,², Xiaoying GUO¹^,³(), Ruyi BAI³, Tao YAN¹^,², Bin CHEN⁴^,⁵

^1.Institute of Big Data Science and Industry，Shanxi University，Taiyuan Shanxi 030006，China
^2.School of Computer and Information Technology，Shanxi University，Taiyuan Shanxi 030031，China
^3.School of Automation and Software Engineering，Shanxi University，Taiyuan Shanxi 030031，China
^4.Chongqing Research Institute，Harbin Institute of Technology，Chongqing 401151，China
^5.International Institute of Artificial Intelligence，Harbin Institute of Technology （Shenzhen），Shenzhen Guangdong 518055，China

Received:2023-09-06 Revised:2023-10-20 Accepted:2023-11-03 Online:2024-08-22 Published:2024-08-10
Contact: Xiaoying GUO
About author:FU Shuai ， born in 1999， M. S. candidate. His research interestsinclude image ordered evaluation.
GUO Xiaoying， born in 1985， Ph. D. ， associate professor. Herresearch interests include image analysis and visual perceptionmodeling， ordered regression， machine learning.
BAI Ruyi ， born in 1987， M. S. ， lecturer. Her research interestsinclude image analysis， machine learning.
YAN Tao ， born in 1987， Ph. D. ， associate professor. Hisresearch interests include 3D reconstruction.
CHEN Bin ， born in 1970， Ph. D. ， professor. His researchinterests include machine vision.
Supported by:
This work is partially supported by Natural Science ResearchGeneral Project of Shanxi Provincial Basic Research Program（202203021221029）； Natural Science Research Youth Project of ShanxiProvincial Basic Research Program（ 202103021223030）.

改进的CloFormer模型与有序回归相结合的年龄评估方法

付帅¹^,², 郭小英¹^,³(), 白茹意³, 闫涛¹^,², 陈斌⁴^,⁵

^1.山西大学大数据科学与产业研究院，太原 030006
^2.山西大学计算机与信息技术学院，太原 030031
^3.山西大学自动化与软件学院，太原 030031
^4.哈尔滨工业大学重庆研究院，重庆 401151
^5.哈尔滨工业大学（深圳）国际人工智能研究院，广东深圳 518055

通讯作者: 郭小英
作者简介:付帅（1999—），男，山西吕梁人，硕士研究生，主要研究方向：图像有序评估
郭小英（1985—），女，山西忻州人，副教授，博士，主要研究方向：图像分析与视觉感知建模、有序回归、机器学习 guoxiaoying@sxu.edu.cn
白茹意（1987—），女，山西吕梁人，讲师，硕士，主要研究方向：图像分析、机器学习
闫涛（1987—），男，山西定襄人，副教授，博士，CCF会员，主要研究方向：三维重建
陈斌（1970—），男，四川广汉人，教授，博士，主要研究方向：机器视觉。
基金资助:
山西省基础研究计划自然科学研究面上项目(202203021221029);山西省基础研究计划自然科学研究青年项目(202103021223030)

Abstract

Abstract:

Existing methods for age estimation typically employ ordinal regression based on Convolutional Neural Network （CNN）. However， when predicting adjacent ages， CNN is difficult in capturing global feature representations， resulting in a decrease in prediction accuracy. In order to solve the problem， an age estimation method was proposed， which combined an enhanced CloFormer model with ordinal regression. Compared to traditional CNN-based ordinal regression， CloFormer， when capturing image features， can better utilize self-attention mechanism to capture relationships between different regions in an image， thereby improving the learning of feature differences between adjacent ages. In the proposed method， firstly， the CloFormer model was optimized， and then the optimized CloFormer model was combined with ordinal regression to better utilize the age sequence information， achieving more precise age estimation. Subsequently， through end-to-end optimization training of the improved CloFormer model and ordinal regression model， the proposed method was able to better learn the relationships between facial features and age sequences. Finally， comparative experiments were conducted on multiple publicly available datasets. Experimental results show that on CACD， AFAD， and UTKFace datasets， the Root Mean Square Error （RMSE） of the proposed method is 7.36， 4.62， and 8.28， respectively. In comparison to existing age estimation methods such as Ordinal Regression with CNN （OR-CNN） and COnsistent RAnk Logits （CORAL）， the RMSEs are reduced by 0.25 and 0.05 respectively on CACD dataset， 0.18 and 0.03 respectively on AFAD dataset， and 0.97 and 0.53 respectively on UTKFace dataset， illustrating that the proposed method has better age estimation results.

Key words: age estimation, computer vision, feature extraction, CloFormer, ordinal regression, facial feature

摘要：

现有的年龄评估方法通常采用基于卷积神经网络（CNN）的有序回归，然而在预测相邻年龄时，CNN难以捕获全局特征表示，进而导致预测精度的下降。为了解决该问题，提出一种新的将改进的CloFormer模型与有序回归相结合的年龄评估方法。相较于传统的基于CNN的有序回归，CloFormer在捕捉图像特征时能够利用自注意力机制更好地捕捉图像中不同区域之间的关系，从而更好地学习相邻年龄之间的特征差异。首先，优化CloFormer模型；然后，将优化后的CloFormer模型与有序回归相结合，以便更好地利用年龄序列信息，实现更精准的年龄预测；接着，通过端到端优化训练改进后的CloFormer模型和有序回归模型，更好地学习面部特征和年龄序列的关系；最后，在多个公开数据集上对比实验。实验结果表明，所提方法在CACD、AFAD、UTKFace数据集上的均方根误差（RMSE）分别为7.36、4.62、8.28，与基于CNN的有序回归（OR-CNN）、秩一致性有序回归模型（CORAL）等现有年龄评估方法相比，在CACD数据集上分别减小了0.25、0.05，在AFAD数据集上分别减小了0.18、0.03，在UTKFace数据集上分别减小了0.97、0.53，可见所提方法取得了较好的年龄评估结果。

关键词: 年龄评估, 计算机视觉, 特征提取, CloFormer, 有序回归, 面部特征

CLC Number:

TP391.4

Shuai FU, Xiaoying GUO, Ruyi BAI, Tao YAN, Bin CHEN. Age estimation method combining improved CloFormer model and ordinal regression[J]. Journal of Computer Applications, 2024, 44(8): 2372-2380.

付帅, 郭小英, 白茹意, 闫涛, 陈斌. 改进的CloFormer模型与有序回归相结合的年龄评估方法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2372-2380.

Figures/Tables 16

References 36

1	HAN H， OTTO C， JAIN A K. Age estimation from face images： human vs. machine performance［C］// Proceedings of the 2013 International Conference on Biometrics. Piscataway： IEEE， 2013： 1-8.
2	ALKASS K， BUCHHOLZ B A， OHTANI S， et al. Age estimation in forensic sciences： application of combined aspartic acid racemization and radiocarbon analysis［J］. Molecular and Cellular Proteomics， 2010， 9（5）：1022-1030.
3	ROTHE R， TIMOFTE R， VAN GOOL L. Deep expectation of real and apparent age from a single image without facial landmarks［J］. International Journal of Computer Vision， 2018， 126（2/3/4）： 144-157.
4	ZHANG K， LIU N， YUAN X， et al. Fine-grained age estimation in the wild with attention LSTM networks［J］. IEEE Transactions on Circuits and Systems for Video Technology， 2020， 30（9）： 3140-3152.
5	LI W， LU J， FENG J， et al. BridgeNet： a continuity-aware probabilistic network for age estimation［C］// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2019： 1145-1154.
6	SHIN N H， LEE S H， KIM C S. Moving window regression： a novel approach to ordinal regression［C］// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2022： 18739-18748.
7	NIU Z， ZHOU M， WANG L， et al. Ordinal regression with multiple output CNN for age estimation［C］// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2016： 4920-4928.
8	CHEN S， ZHANG C， DONG M， et al. Using ranking-CNN for age estimation［C］// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2017： 742-751.
9	PAN H， HAN H， SHAN S， et al. Mean-variance loss for deep age estimation from a face［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2018： 5285-5294.
10	WEN X， LI B， GUO H， et al. Adaptive variance based label distribution learning for facial age estimation［C］// Proceedings of the 16th European Conference on Computer Vision， LNCS 12368. Cham： Springer， 2020： 379-395.
11	何建辉，胡春龙，束鑫. 基于多峰标签分布学习的多任务年龄估计方法［J］. 计算机应用， 2023， 43（5）： 1578-1583.
	HE J H， HU C L， SHU X. Multi-task age estimation method based on multi-peak label distribution learning［J］. Journal of Computer Applications， 2023， 43（5）： 1578-1583.
12	SHEN W， GUO Y， WANG Y， et al. Deep regression forests for age estimation［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2018： 2304-2313.
13	SHEN W， ZHAO K， GUO Y， et al. Label distribution learning forests［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2017： 834-843.
14	YANG T Y， HUANG Y H， LIN Y Y， et al. SSR-Net： a compact soft stagewise regression network for age estimation［C］// Proceedings of the 27th International Joint Conference on Artificial Intelligence. California： ijcai.org， 2018： 1078-1084.
15	李丽莹，王阳，马军山. 基于深度学习的人脸表观年龄估计［J］. 软件导刊， 2021， 20（6）： 54-58.
	LI L Y， WANG Y， MA J S. Apparent age estimation based on deep learning［J］. Software Guide， 2021， 20（6）： 54-58.
16	李珏，卢鹤. 基于深度学习的人脸图像年龄估计［J］. 现代信息科技， 2019， 3（18）： 40-42.
	LI J， LU H. Age estimation of face images based on deep learning［J］. Modern Information Technology， 2019， 3（18）： 40-42.
17	ROTHE R， TIMOFTE R， VAN GOOL L. DEX： deep expectation of apparent age from a single image［C］// Proceedings of the 2015 IEEE International Conference on Computer Vision Workshop. Piscataway： IEEE， 2015： 252-257.
18	FAN Q， HUANG H， GUAN J， et al. Rethinking local perception in lightweight vision transformer［EB/OL］. （2023-06-01）［2023-09-05］..
19	SIFRE L， MALLAT S. Rigid-motion scattering for texture classification［EB/OL］. （2014-03-07）［2023-09-05］..
20	HOWARD A G， ZHU M， CHEN B， et al. MobileNets： efficient convolutional neural networks for mobile vision applications［EB/OL］. （2017-04-17）［2023-09-05］..
21	CAO W， MIRJALILI V， RASCHKA S. Rank consistent ordinal regression for neural networks with application to age estimation［J］. Pattern Recognition Letters， 2020， 140： 325-331.
22	HAN K， WANG Y， CHEN H， et al. A survey on vision transformer［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2023， 45（1）： 87-110.
23	ZHU Z， HUANG G， DENG J， et al. WebFace260M： a benchmark unveiling the power of million-scale deep face recognition［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2021： 10487-10497.
24	XUE F， WANG Q， GUO G. TransFER： learning relation-aware facial expression representations with transformers［C］// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2021： 3581-3590.
25	HE S， GRANT P E， OU Y M. Global-local transformer for brain age estimation［J］. IEEE Transactions on Medical Imaging， 2022， 41（1）： 213-224.
26	QIN L， WANG M， DENG C， et al. SwinFace： a multi-task transformer for face recognition， expression recognition， age estimation and attribute estimation［J］. IEEE Transactions on Circuits and Systems for Video Technology， 2024， 34（4）： 2223-2234.
27	GUTIÉRREZ P A， PÉREZ-ORTIZ M， SÁNCHEZ-MONEDERO J， et al. Ordinal regression methods： survey and experimental study［J］. IEEE Transactions on Knowledge and Data Engineering， 2016， 28（1）： 127-146.
28	VARGAS V M， GUTIÉRREZ P A， HERVÁS C. Deep ordinal classification based on the proportional odds model［C］// Proceedings of the 2019 International Work-Conference on the Interplay Between Natural and Artificial Computation， LNCS 11487. Cham： Springer， 2019： 441-451.
29	LEE J， LEE I， KANG J. Self-attention graph pooling［C］// Proceedings of the 36th International Conference on Machine Learning. New York： JMLR.org， 2019：3734-3743.
30	CHEN B C， CHEN C S， HSU W H. Cross-age reference coding for age-invariant face recognition and retrieval［C］// Proceedings of the 13th European Conference on Computer Vision， LNCS 8694. Cham： Springer， 2014： 768-783.
31	ZHANG Z， SONG Y， QI H. Age progression/regression by conditional adversarial autoencoder［C］// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2017： 4352-4360.
32	ZHANG K， ZHANG Z， LI Z， et al. Joint face detection and alignment using multitask cascaded convolutional networks［J］. IEEE Signal Processing Letters， 2016， 23（10）： 1499-1503.
33	TOUVRON H， CORD M， DOUZE M， et al. Training data-efficient image transformers & distillation through attention［C］// Proceedings of the 38th International Conference on Machine Learning. New York： JMLR.org， 2021： 10347-10357.
34	KINGMA D P， BA J L. Adam： a method for stochastic optimization［EB/OL］. （2017-01-30）［2023-09-05］..
35	DOSOVITSKIY A， BEYER L， KOLESNIKOV A， et al. An image is worth 16x16 words： Transformers for image recognition at scale［EB/OL］. （2017-01-30）［2023-09-05］. .
36	LIN Y， SHEN J， WANG Y， et al. FP-Age： leveraging face parsing attention for facial age estimation in the wild［J］. IEEE Transactions on Image Processing， 2022（Early Access）： 1.

方法	CACD		AFAD		UTKFace
方法	MAE	RMSE	MAE	RMSE	MAE	RMSE
DWconv（无OR）	6.02	8.54	3.86	5.20	6.54	11.23
DSC（无OR）	5.68	8.14	3.73	5.37	6.32	10.24
DWconv+OR	5.53	7.78	3.77	5.10	5.85	9.13
DSC+OR	5.18	7.36	3.58	4.62	5.34	8.28

方法	CACD		AFAD		UTKFace
方法	MAE	RMSE	MAE	RMSE	MAE	RMSE
DWconv（无OR）	6.02	8.54	3.86	5.20	6.54	11.23
DSC（无OR）	5.68	8.14	3.73	5.37	6.32	10.24
DWconv+OR	5.53	7.78	3.77	5.10	5.85	9.13
DSC+OR	5.18	7.36	3.58	4.62	5.34	8.28

方法	CACD		AFAD		UTKFace
方法	MAE	RMSE	MAE	RMSE	MAE	RMSE
CE-CNN^［21］	5.74	8.20	3.58	5.01	6.47	10.43
OR-CNN^［7］	5.36	7.61	3.56	4.80	5.74	9.25
CORAL-CNN^［21］	5.25	7.41	3.42	4.65	5.64	8.81
ViT-B-16^［35］	6.22	—	4.04	—	6.88	—
本文方法	5.18	7.36	3.54	4.62	5.34	8.28

方法	CACD		AFAD		UTKFace
方法	MAE	RMSE	MAE	RMSE	MAE	RMSE
CE-CNN^［21］	5.74	8.20	3.58	5.01	6.47	10.43
OR-CNN^［7］	5.36	7.61	3.56	4.80	5.74	9.25
CORAL-CNN^［21］	5.25	7.41	3.42	4.65	5.64	8.81
ViT-B-16^［35］	6.22	—	4.04	—	6.88	—
本文方法	5.18	7.36	3.54	4.62	5.34	8.28

方法	训练集		验证集		测试集
方法	MAE	RMSE	MAE	RMSE	MAE	RMSE
LDLFs^［13］	4.73	—	6.77	—	—	—
DRFs^［12］	4.64	—	5.77	—	—	—
CE-CNN^［21］	4.36	6.63	5.67	8.08	5.74	8.20
OR-CNN^［7］	1.64	2.56	5.28	7.56	5.36	7.61
FP-Age^［36］	4.33	—	4.95	—	—	—
CORAL-CNN^［21］	1.50	2.20	5.17	7.29	5.25	7.41
MWR^［6］	4.41	—	5.68	—	—	—
ViT-B-16^［35］	—	—	—	—	6.22	—
本文方法	1.47	2.23	5.12	7.30	5.18	7.36

Age estimation method combining improved CloFormer model and ordinal regression

改进的CloFormer模型与有序回归相结合的年龄评估方法

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 16

References 36

Related Articles 15

Recommended Articles

Metrics

[1]	Xin YANG, Xueni CHEN, Chunjiang WU, Shijie ZHOU. Short-term traffic flow prediction of urban highway based on variant residual model and Transformer [J]. Journal of Computer Applications, 2024, 44(9): 2947-2951.
[2]	Yexin PAN, Zhe YANG. Optimization model for small object detection based on multi-level feature bidirectional fusion [J]. Journal of Computer Applications, 2024, 44(9): 2871-2877.
[3]	Chun SUN, Chunlong HU, Shucheng HUANG. Consistency preserving age estimation method by ensemble ranking [J]. Journal of Computer Applications, 2024, 44(8): 2381-2386.
[4]	Tong CHEN, Fengyu YANG, Yu XIONG, Hong YAN, Fuxing QIU. Construction method of voiceprint library based on multi-scale frequency-channel attention fusion [J]. Journal of Computer Applications, 2024, 44(8): 2407-2413.
[5]	Wudan LONG, Bo PENG, Jie HU, Ying SHEN, Danni DING. Road damage detection algorithm based on enhanced feature extraction [J]. Journal of Computer Applications, 2024, 44(7): 2264-2270.
[6]	Ruihua LIU, Zihe HAO, Yangyang ZOU. Gait recognition algorithm based on multi-layer refined feature fusion [J]. Journal of Computer Applications, 2024, 44(7): 2250-2257.
[7]	Sailong SHI, Zhiwen FANG. Gaze estimation model based on multi-scale aggregation and shared attention [J]. Journal of Computer Applications, 2024, 44(7): 2047-2054.
[8]	Ziwen SUN, Lizhi QIAN, Chuandong YANG, Yibo GAO, Qingyang LU, Guanglin YUAN. Survey of visual object tracking methods based on Transformer [J]. Journal of Computer Applications, 2024, 44(5): 1644-1654.
[9]	Zhihao WU, Ziqiu CHI, Ting XIAO, Zhe WANG. Meta-learning adaption for few-shot text-to-speech [J]. Journal of Computer Applications, 2024, 44(5): 1629-1635.
[10]	Chenhui CUI, Suzhen LIN, Dawei LI, Xiaofei LU, Jie WU. Infrared dim small target tracking method based on Siamese network and Transformer [J]. Journal of Computer Applications, 2024, 44(2): 563-571.
[11]	Wenjie YAN, Dongyue DANG. Broad quantum state tomography model based on adaptive feature extraction [J]. Journal of Computer Applications, 2024, 44(12): 3861-3866.
[12]	Yudong PANG, Zhixing LI, Weijie LIU, Tianhao LI, Ningning WANG. Small target detection model in overlooking scenes on tower cranes based on improved real-time detection Transformer [J]. Journal of Computer Applications, 2024, 44(12): 3922-3929.
[13]	Yiyang FAN, Yang ZHANG, Shang ZENG, Yu ZENG, Maoli FU. Multivariate long-term series forecasting model based on decomposition and frequency domain feature extraction [J]. Journal of Computer Applications, 2024, 44(11): 3442-3448.
[14]	Pei ZHAO, Yan QIAO, Rongyao HU, Xinyu YUAN, Minyue LI, Benchu ZHANG. Multivariate time series anomaly detection based on multi-domain feature extraction [J]. Journal of Computer Applications, 2024, 44(11): 3419-3426.
[15]	Tao LIU, Shihong JU, Yimeng GAO. Small object detection algorithm from drone perspective based on improved YOLOv8n [J]. Journal of Computer Applications, 2024, 44(11): 3603-3609.