• Analytical Science and Technology
• /
• v.20 no.5
• /
• pp.434-441
• /
• 2007

The aim of this paper is to investigate composition of fatty acids in sweat on purpose of latent fingerprint detectant developing and crime evidence searching. Fingerprint from 5 male donors (aged 29-50 years) were collected. We identified fatty acid components on sweat using methylester mixture (37species) as standard fatty acid and analyzed them by GC-FID. As donor was aged, the level of total fat was found to decrease markedly (aged 20-30 years: 56.4-72.0 %, aged 50 years : 32.4-45.4 %). We identifided 28 species fatty acid, primarilly C16:0(palmitic acid), C16:1 (palmitoleic acid), C18:1n9c(oleic acid), C18:0 (stearic acid), C14:0 (tetradecanoic acid) and all sweats were found to contain C12:0 (lauric acid), C15:0 (pentadecanoic acid), C18:2n6c (linoleic acid), C18:2n6t (linolelaidic acid), C20:0 (arachidic acid), C24:0/C20:5n3 (lignoceric acid/eicosapentaenoic acid), but with differing frequencies and at varying levels. C14:1 (myristoleic acid), C15:1 (pentadecenoic acid), C21:0 (heneicosanoic acid), C22:1n9 (erucic acid) were often observed in sample. Ratio of saturated and unsaturated fatty acid was from 0.94:1 to 2.6:1. And decrease of total fatty acids components caused by loss of saturated fatty acid and monounsaturated fatty acid. In case of sweat amino acids, we detected serine ($0-31.9{\mu}L/mL$), threonine ($0-26.2{\mu}L/mL$), glycine ($0-18.9{\mu}L/mL$) and 20-30 years old, highly protein intake ratio individuals increased (10 times) than 50 years old. We observed greatly individual characterization of amino acid compounds in sweat.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.317-326
• /
• 2024

Biometric recognition is a technology that determines whether a person is identified by extracting information on a person's biometric and behavioral characteristics with a specific device. Cyber threats such as forgery, duplication, and hacking of biometric characteristics are increasing in the field of biometrics. In response, the security system is strengthened and complex, and it is becoming difficult for individuals to use. To this end, multiple biometric models are being studied. Existing studies have suggested feature fusion methods, but comparisons between feature fusion methods are insufficient. Therefore, in this paper, we compared and evaluated the fusion method of multiple biometric models using fingerprint, face, and iris images. VGG-16, ResNet-50, EfficientNet-B1, EfficientNet-B4, EfficientNet-B7, and Inception-v3 were used for feature extraction, and the fusion methods of 'Sensor-Level', 'Feature-Level', 'Score-Level', and 'Rank-Level' were compared and evaluated for feature fusion. As a result of the comparative evaluation, the EfficientNet-B7 model showed 98.51% accuracy and high stability in the 'Feature-Level' fusion method. However, because the EfficietnNet-B7 model is large in size, model lightweight studies are needed for biocharacteristic fusion.

• Journal of Intelligence and Information Systems
• /
• v.12 no.1
• /
• pp.1-15
• /
• 2006

In Korea, a resident registration card has various personal information such as a present address, a resident registration number, a face picture and a fingerprint. A plastic-type resident card currently used is easy to forge or alter and tricks of forgery grow to be high-degree as time goes on. So, whether a resident card is forged or not is difficult to judge by only an examination with the naked eye. This paper proposed an automatic recognition method of a resident card which recognizes a resident registration number by using a refined ART2-based RBF network newly proposed and authenticates a face picture by a template image matching method. The proposed method, first, extracts areas including a resident registration number and the date of issue from a resident card image by applying Sobel masking, median filtering and horizontal smearing operations to the image in turn. To improve the extraction of individual codes from extracted areas, the original image is binarized by using a high-frequency passing filter and CDM masking is applied to the binaried image fur making image information of individual codes better. Lastly, individual codes, which are targets of recognition, are extracted by applying 4-directional contour tracking algorithm to extracted areas in the binarized image. And this paper proposed a refined ART2-based RBF network to recognize individual codes, which applies ART2 as the loaming structure of the middle layer and dynamicaly adjusts a teaming rate in the teaming of the middle and the output layers by using a fuzzy control method to improve the performance of teaming. Also, for the precise judgement of forgey of a resident card, the proposed method supports a face authentication by using a face template database and a template image matching method. For performance evaluation of the proposed method, this paper maked metamorphoses of an original image of resident card such as a forgey of face picture, an addition of noise, variations of contrast variations of intensity and image blurring, and applied these images with original images to experiments. The results of experiment showed that the proposed method is excellent in the recognition of individual codes and the face authentication fur the automatic recognition of a resident card.

• Journal of Korean Society for Geospatial Information Science
• /
• v.22 no.3
• /
• pp.57-69
• /
• 2014

As of 2013, Korean population density is 505 persons per $1km^2$ and is ranked 3rd place in the most densely populated countries exception of city-states. It shows clearly the population is concentrated in the city area. To fulfil this urban concentration population demand, the enlargement and complexation of buildings, subway and other underground spaces connection tendency has been intensified, and it is need to construct the indoor spatial information DB as well as the accurate indoor surveying DB to promote people's safety and social welfare. In this study, Sadang station and Incheon National Airport were aimed for the construction of Wi-Fi AP location DB and RadioMap DB by collecting the indoor AP raw datas by using mobile device and those collected results were ran through the process of verification, supplementation, and analyzation. To evaluate the performance of constructed DB, 10 points in Incheon Airport- 3rd flr in block A, and 9 points in Sadang station-B1 were selected and calculated the estimated points and ran evaluation experiment using survey positioning error, which is distance between real position and the estimated position. The result shows that Incheon international airport's average and standard deviation was separately 17.81m, 17.79m and Sadang station's average and standard deviation was separately 22.64m, 23.74m. In Sadang station's case, the areas near the exit has low performance of surveying position due to fewer visible AP points than other areas. As total datas were examined except those position, it was verified that the user's location was mapping close position in surveying positioning by using constructed DB. It means that constructed DB contains correct Wi-Fi AP locations and radio wave patterns in object region, so it is considered that the indoor spatial information service based on constructed DB would be available.