• 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.

• Journal of Platform Technology
• /
• v.11 no.5
• /
• pp.16-22
• /
• 2023

There is a growing interest in facial age estimation because many applications require age estimation techniques from facial images. In order to estimate the exact age of a face, a technique for extracting aging features from a face image and classifying the age according to the extracted features is required. Recently, the performance of various CNN-based deep learning models has been greatly improved in the image recognition field, and various CNN-based deep learning models are being used to improve performance in the field of facial age estimation. In this paper, age estimation performance was compared by learning facial features based on various CNN-based models such as AlexNet, VGG-16, VGG-19, ResNet-18, ResNet-34, ResNet-50, ResNet-101, ResNet-152. As a result of experiment, it was confirmed that the performance of the facial age estimation models using ResNet-34 was the best.

• Journal of Oral Medicine and Pain
• /
• v.38 no.3
• /
• pp.235-246
• /
• 2013

Age estimations by forensic odontology play a great role in personal identification. The purpose of this study was to analyze the characteristics of age estimation cases in Korea. Surveying clients who requested age estimation at the Department of Oral Medicine, Kyungpook National University Dental Hospital from March 2012 to March 2013. The results were as follows: 1. On gender distribution, females(57.14%) were more than males(42.86%). The elderly with 50's and over 60's were majorities(89.28%) of clients, and no clients were below 40's. Most of clients were equal to and lower than elementary school graduate(69.64%). 2. The most frequent reason for age discrepancy between registered age and alleged age was mistakes by family or relatives(80.36%). The purposes of age estimation were welfare(62.50%), social relationship problem(12.50%), to find right age(10.71%), and occupation(8.93%). 3. In order of route to visit at Department of Oral Medicine, they were via government office(48.21%), acquaintances(21.43%), mass media(14.29%), and clinic(10.71%). Clients had high degree of comprehension on age estimation with forensic odontology (scored 7.03 out of 10). The 2/3 of clients were satisfied with present fee for age estimation. 4. The percentage on the proximity of estimated age to alleged age was 69.81%. 4(11.43%) clients were approved on age correction by court.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.7
• /
• pp.3229-3232
• /
• 2012

In this study, cancer incidence data were assessed to provide various rates of five year age groups for a given year, lying between two census years. The individual exponential growth rate method is most useful in both population-based and non-population cased cancer registries in India to estimate the population by five yearly age groups and also find the rates of crude rates, age standard rates and cumulative rates. This method has been shown to endure from bias and often results sacrificing the overall growth rate and correction factor must be needful in five year age group population to maintain it. A second method, the difference distribution method is also able to maintain the overall growth rate and overcome the bias in estimation of five yearly age group populations. From this point of view these methods serving a new technique for population estimation by five yearly age groups for inter census years.

• Journal of the Korea Institute of Building Construction
• /
• v.7 no.1 s.23
• /
• pp.71-77
• /
• 2007

This paper is to investigate the effect of the curing temperature on strength development of concrete incorporating cement kiln dust(CKD) and blast furnace slag (BS) quantitatively. Estimation of the compressive strength of the concrete was conducted using the equivalent age equation and the rate constant model proposed by Carino. Correction of Carino model was studied to secure the accuracy of strength development estimation by introducing correction factors regarding rate constant and age. An increasing curing temperature results in an increase in strength at early age, but with the elapse of age, strength development at high curing temperature decreases compared with that at low curing temperature. Especially, the use of BS has a remarkable strength development at early age and even at later age, high strength is maintained due to accelerated pozzolanic activity resulting from high temperature. Whereas, at low curing temperature, the use of BS leads to a decrease in compressive strength. Accordingly, much attention should be paid to prevent strength loss at low temperature. Based on the strength development estimation using equivalent age equation, good agreements between measured strength and calculated strength are obtained.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.779-782
• /
• 2017

OpenBR is a framework for researching new facial recognition methods, improving existing algorithms, interacting with commercial systems, measuring perceived performance, and deploying automated biometric systems. Designed to facilitate rapid algorithm prototyping, it features a mature core framework, flexible plug-in system, and open and closed source development support. The established algorithms can be used for specific forms such as face recognition, age estimation, and gender estimation. In this paper, we describe the framework of OpenBR and implement facial recognition, gender estimation, and age estimation using supported programs.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.9
• /
• pp.1224-1231
• /
• 2018

Automatic age estimation has been used in many social network applications, practical commercial applications, and human-computer interaction visual-surveillance biometrics. However, it has rarely been explored. In this paper, we propose an automatic age estimation system, which includes face detection and convolutional deep learning based on an inception module. The latter is a 22-layer-deep network that serves as the particular category of the inception design. To evaluate the proposed approach, we use 4,000 images of eight different age groups from the Adience age dataset. k-fold cross-validation (k = 5) is applied. A comparison of the performance of the proposed work and recent related methods is presented. The results show that the proposed method significantly outperforms existing methods in terms of the exact accuracy and off-by-one accuracy. The off-by-one accuracy is when the result is off by one adjacent age label to the above or below. For the exact accuracy, the age label of "60+" is classified with the highest accuracy of 76%.

• Journal of Korea Multimedia Society
• /
• v.12 no.3
• /
• pp.383-396
• /
• 2009

Bone age assessment has been widely used in pediatrics to identify endocrine problems of children. Since the number of trained doctors is far less than the demands, there has been numerous requests for automatic estimation of bone age. Therefore, in this paper, we propose an automatic bone age assessment method that utilizes pattern classification techniques. The proposed method consists of three modules; a finger segmentation module, a normalized shape model generation module and a bone age estimation module. The finger segmentation module segments fingers and epiphyseal regions by means of various image processing algorithms. The shape model abstraction module employ ASM to improves the accuracy of feature extraction for bone age estimation. In addition, SVM is used for estimation of bone age. Features for the estimation include the length of bone and the ratios of bone length. We evaluated the performance of the proposed method through statistical analysis by comparing the bone age assessment results by clinical experts and the proposed automatic method. Through the experimental results, the mean error of the assessment was 0.679 year, which was better than the average error acceptable in clinical practice.

• Anatomy and Cell Biology
• /
• v.56 no.1
• /
• pp.86-93
• /
• 2023

Age at death estimation has always been a crucial yet challenging part of identification process in forensic field. The use of human skeletons have long been explored using the principle of macro and micro-architecture change in correlation with increasing age. The clavicle is recommended as the best candidate for accurate age estimation because of its accessibility, time to maturation and minimal effect from weight. Our study applies pre-trained convolutional neural network in order to achieve the most accurate and cost effective age estimation model using clavicular bone. The total of 988 clavicles of Thai population with known age and sex were radiographed using Kodak 9000 Extra-oral Imaging System. The radiographs then went through preprocessing protocol which include region of interest selection and quality assessment. Additional samples were generated using generative adversarial network. The total clavicular images used in this study were 3,999 which were then separated into training and test set, and the test set were subsequently categorized into 7 age groups. GoogLeNet was modified at two layers and fine tuned the parameters. The highest validation accuracy was 89.02% but the test set achieved only 30% accuracy. Our results show that the use of medial clavicular radiographs has a potential in the field of age at death estimation, thus, further study is recommended.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2001.05a
• /
• pp.397-402
• /
• 2001

Microstructural characteristics such as hydrates and porosity greatly influence the development of concrete strength. In this study, a strength estimation model for early-age concrete considerig, the microstructural characteristics was proposed, which considers the effects of both an increment of degree of hydration and capillary porosity on a strength increment. Hydration modeling and compressive strength test with curing temperature and curing ages were carried out. By comparing test results with estimated strength, it is found that the strength estimation model can estimate compressive strength of early-age concrete with curing ages and curing temperature within a margin of error.