2019
DOI: 10.1186/s41074-019-0054-2
|View full text |Cite
|
Sign up to set email alerts
|

Gait-based age estimation using multi-stage convolutional neural network

Abstract: Gait-based age estimation has been extensively studied for various applications because of its high practicality. In this paper, we propose a gait-based age estimation method using convolutional neural networks (CNNs). Because gait features vary depending on a subject's attributes, i.e., gender and generation, we propose the following three CNN stages: (1) a CNN for gender estimation, (2) a CNN for age-group estimation, and (3) a CNN for age regression. We conducted experiments using a large population gait da… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
29
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
5
3

Relationship

2
6

Authors

Journals

citations
Cited by 35 publications
(29 citation statements)
references
References 26 publications
0
29
0
Order By: Relevance
“…In training CNNs, even if the same data are given, different parts of the data can be learned depending on the task 40 . With CNNs, multi-task learning has become possible, and this method improves the accuracy of a target task by simultaneously learning targets and by recognizing related adjacent structures 41 . Thus, this characteristic of an AI-based age-group estimation model is a very useful aspect in forensic dental medicine that can generally be well applied across various people and age groups.…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…In training CNNs, even if the same data are given, different parts of the data can be learned depending on the task 40 . With CNNs, multi-task learning has become possible, and this method improves the accuracy of a target task by simultaneously learning targets and by recognizing related adjacent structures 41 . Thus, this characteristic of an AI-based age-group estimation model is a very useful aspect in forensic dental medicine that can generally be well applied across various people and age groups.…”
Section: Discussionmentioning
confidence: 99%
“…First, for a wide range of age determination (20 y intervals, three groups in total), the accuracy of the AI model was analyzed. The young adults' group, which had the largest number of samples, was further divided into three subgroups (ages 20-29, ages 30-39, and ages [40][41][42][43][44][45][46][47][48][49]. Therefore, we compared the results obtained by dividing the participants into three age groups, and the results obtained by subdividing the young adults into further groups, thereby generating a total of five age groups.…”
Section: Methodsmentioning
confidence: 99%
“…For example, Sakata et al [21] used DenseNet [37], which is a state-of-the-art deep neural network architecture, and validated its effectiveness in the gait-based age estimation task. In addition to age, other attributes, such as gender, age group, and/or identity, have been incorporated into multi-task learning frameworks [16], [26] and a multi-stage learning framework [38]. Moreover, a gait-based age estimation method that is robust against a carried object was proposed in [27].…”
Section: Gait-based Age Estimationmentioning
confidence: 99%
“…Two major output/ground-truth representations exist: a scalar value for regression-based methods [13], [14], [21], [23], [38] and a one-hot vector for classification-based methods [15]. Different from these approaches, in this paper, we incorporate the idea of label distribution [32], [40].…”
Section: Output Representationsmentioning
confidence: 99%
“…In their group-dependent framework based on manifold, they achieved excellent results. In another work exploring multi-stage CNN by [49], video-based gait-based age was estimated. In this paper, they introduced CNN-based models for gender estimation method, age-group estimation, and age regression.…”
Section: Related Workmentioning
confidence: 99%