• Journal of Oral Medicine and Pain
• /
• v.43 no.4
• /
• pp.118-124
• /
• 2018

Purpose: Age estimation is often used in the identification of living persons. Various methods are used for age estimation using teeth, and there are many studies on the methodology. But the study of changes in the social aspects of age estimation with the passage of times is still insufficient. Therefore, the purpose of this study is to analyze the age estimation cases in the social aspects and to investigate the changes of age estimation cases in Jeollabuk-do. Methods: From January 2008 to December 2015, 76 cases of age estimation were collected. The collected data were organized and analyzed. The distribution of patients by age and year, the difference between alleged and registered age, the purpose of age estimation, and regional distribution were examined. In addition, we compared the previous study which analyzed the age estimation cases in Jeollabuk-do from 2000 to 2007. Results: According to the distribution by age, the age distribution was the largest in the 50s and 60s, with 69.8%. The most reason to correct age was related to welfare benefits (38.2%), and most of the people who corrected for welfare benefits were over 50 years old. The age correction for purpose of welfare benefits existed every year during the study period. As the result of comparison with previous study, total number of age estimation cases was decreased very sharply, and distribution by age group was also changed. Conclusions: Changes in age estimation cases were observed when compared to the previous study. A significant decrease in the total number of age estimation cases was observed, but the number of age estimation in the 50s did not decrease. Although the total number of age estimation requests decreases, age estimation in the elderly are likely to persist. Thus, it is necessary to study new age estimation methods suitable for the elderly.

• Journal of Korean Dental Science
• /
• v.15 no.1
• /
• pp.31-50
• /
• 2022

Purpose: This study was to investigate the types of imaging modalities, analytical methods for age estimation, and the age of the subjects in research on age estimation using dental radiography through a scoping review, and to investigate the overall trends in age estimation studies. Materials and Methods: A scoping review was designed according to the Arksey and O'Malley guidelines and the Preferred Reporting Items for Systematic Review and Meta-analysis (PRISMA) statement. Three electronic databases were used as search sources (Medline, Embase, and Cochrane Library). Studies were classified according to the three main components of the research question. "What are the imaging modalities, analytical methods, and target age in dental imaging-based age estimation studies?" Result: The final 198 studies were selected by two reviewers. The most common imaging modality used in studies was panoramic radiography (69.7%), and studies using cone-beam computed tomography have increased over time. Analytical methods for age estimation were 62.6% in studies based on tooth development and 26.3% in studies using pulp/tooth ratio. The subject age was 27.8% for children and 27.3% for adults. Studies conducted in all age groups comprised the smallest category (5.2%). Conclusion: Panoramic radiography has been the most used types of imaging modalities for age estimation, and the most common analytical method was analysis of tooth development. Most studies targeted specific ages, and very few involved all age groups. Dental age estimation studies should be carried out with appropriate consideration of the imaging modality that is analyzed, the methods that are used, and the age that is targeted.

• Journal of Oral Medicine and Pain
• /
• v.14 no.1
• /
• pp.43-55
• /
• 1989

The need of age estimation for identification was increased by complexity of society, and the tooth was used widely for age estimation because of less individual deviation than the other organ. The age estimation using the tooth had several methods. Recently, the one using the racemization of aminoacid in the tooth was admitted more accurate than the other methods, especially in old age. But, this study was not tried in our country, and I would report the result of experiment about age estimation using racemization of dentine. I selected 40-Whole dentine sample from extracted teeth, those were reserved in natural dried condition for 2 weeks~ 1year and calculated the estimation of age from the ratio of D-aminoacid and L-aminoacid (D/L ratio) using gaschromatography and the results were below. 1. The aminoacids showed apparent K/L ratio in dentine were aspartic acid, serine. 2. The aspartic acid showed the highest racemic rate and its rate was 0.0012$\pm$0.0003/yr. 3. The relation between the actual age and K/L ratio was very positive correlation(r+0.954) in the estimation of age using aspartic acid. 4. The deviation between the estimated age using D/L ratio of aspartic acid and actual age was $\pm$3.32.

• International journal of advanced smart convergence
• /
• v.9 no.2
• /
• pp.203-211
• /
• 2020

This study proposes a method for estimating gender and age that is robust to various external environment changes by applying deep learning-based learning. To improve the accuracy of the proposed algorithm, an improved CNN network structure and learning method are described, and the performance of the algorithm is also evaluated. In this study, in order to improve the learning method based on CNN composed of 6 layers of hidden layers, a network using GoogLeNet's inception module was constructed. As a result of the experiment, the age estimation accuracy of 5,328 images for the performance test of the age estimation method is about 85%, and the gender estimation accuracy is about 98%. It is expected that real-time age recognition will be possible beyond feature extraction of face images if studies on the construction of a larger data set, pre-processing methods, and various network structures and activation functions have been made to classify the age classes that are further subdivided according to age.

• Journal of Oral Medicine and Pain
• /
• v.6 no.1
• /
• pp.101-110
• /
• 1981

For the purpose of an estimation of age based on the changes in the human dental cavity caused by increase in age, 1,208 extracted teeth in the parts from central incisors and lateral incisors and lateral incisors to second premolars of upper and lower, right and left side were evaluated and analized all of surface index of pulp cavity. The results are as follows : 1. The surface index of pulp caxities of upper and lower, central and lateral incisors, and tend to decrease regularly as the age increase. So above teeth are more applicable to age estimation than canine and premolars. 2 For the purpose of age estimation by surface index of pulp cavity of central and lateral incisor, linear equations are as follows. Upper central incisor: X=(16.301-Y)/0.12 Upper lateral incisor: X=(16.620-Y)/0.11 Lower central incisor: X=(20.963-Y)/0.16 X=Age Y=Surface index of pulp cavity Correlation coefficient between chronologic age and estimated age is 0.699 3.The least error(3.3 yrs of age)reveals in 41-45 age group, which shows the highest possibility of estimation of age. The highest error(4.1 yrs of age)reveals in 61-65 age group and 56-60 age group.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.7
• /
• pp.2480-2495
• /
• 2014

This paper describes a hierarchical method for image-based age estimation that combines age group classification and age value estimation. The proposed method uses a coarse-to-fine strategy with different appearance features to describe facial shape and texture. Considering the damage to continuity between neighboring groups caused by fixed divisions during age group classification, a dynamic grouping technique is employed to allow non-fixed groups. Based on the given group, an ordinal hyperplane ranking (OHRank) model is employed to transform age estimation into a series of binary enquiry problems that can take advantage of the intrinsic correlation and ordinal information of age. A set of experiments on FG-NET are presented and the results demonstrate the validity of our solution.

• Journal of Platform Technology
• /
• v.10 no.3
• /
• pp.44-50
• /
• 2022

Research on facial age estimation is being actively conducted because it is used in various application fields. Facial images taken in various environments often have occlusions, and there is a problem in that performance of age estimation is degraded. Therefore, we propose age estimation method by creating an occluded part using image extrapolation technology to improve the age estimation performance of an occluded face image. In order to confirm the effect of occlusion in the image on the age estimation performance, an image with occlusion is generated using a mask image. The occluded part of facial image is restored using SpiralNet, which is one of the image extrapolation techniques, and it is a method to create an occluded part while crossing the edge of an image. Experimental results show that age estimation performance of occluded facial image is significantly degraded. It was confirmed that the age estimation performance is improved when using a face image with reconstructed occlusions using SpiralNet by experiments.

• Journal of Korea Multimedia Society
• /
• v.25 no.1
• /
• pp.39-51
• /
• 2022

Image-based gender classification and age estimation of human are classic problems in computer vision. Most of researches in this field focus just only one task of either gender classification or age estimation and most of the reported methods for each task focus on accuracy performance and are not computationally light. Thus, running both tasks together simultaneously on low cost mobile or embedded systems with limited cpu processing speed and memory capacity are practically prohibited. In this paper, we propose a novel light-weight gender classification and age estimation method based on ensemble multitasking deep learning with light-weight processing neural network architecture, which processes both gender classification and age estimation simultaneously and in real-time even for embedded systems. Through experiments over various well-known datasets, it is shown that the proposed method performs comparably to the state-of-the-art gender classification and/or age estimation methods with respect to accuracy and runs fast enough (average 14fps) on a Jestson Nano embedded board.

• Proceedings of the Earthquake Engineering Society of Korea Conference
• /
• 2001.04a
• /
• pp.74-80
• /
• 2001

The estimation of recurrence interval for fault activity and earthquake is an important input parameter for seismic hazard assessment. In this study, the methods of recurrences interval estimation were reviewed and tentative calculation was performed for age dating data which have uncertainty. Age dating data come from previous studies of Ulsan fault system which is a well developed lineament in the southeastern part of korean Peninsula. Age dating for fault gouges, parent rocks, Quaternary sediments and veins were carried out by several researchers through various methods. Recurrence interval for fault activity was estimated on the basis of the age dating data of minor fault gouge and sediments during past 3Ma. The estimated recurrence interval was about 430-500 ka. Exact estimation of recurrence interval for fault activity need to compile more geological data and fault characteristics such as fault length, amount of displacement, slip rate and accurate fault movement age. In the future, the methods and results of fault recurrence interval estimation should be considered for establishing the criteria for domestic active fault definition.

• ETRI Journal
• /
• v.39 no.5
• /
• pp.643-651
• /
• 2017

Human age estimation is one of the key factors in the field of Human-Robot Interaction/Human-Computer Interaction (HRI/HCI). Owing to the development of deep-learning technologies, age recognition has recently been attempted. In general, however, deep learning techniques require a large-scale database, and for age learning with variations, a conventional database is insufficient. For this reason, we propose an age estimation method using artificially generated data. Image data are artificially generated through 3D information, thus solving the problem of shortage of training data, and helping with the training of the deep-learning technique. Augmentation using 3D has advantages over 2D because it creates new images with more information. We use a deep architecture as a pre-trained model, and improve the estimation capacity using artificially augmented training images. The deep architecture can outperform traditional estimation methods, and the improved method showed increased reliability. We have achieved state-of-the-art performance using the proposed method in the Morph-II dataset and have proven that the proposed method can be used effectively using the Adience dataset.