• Journal of KIISE:Software and Applications
• /
• v.33 no.11
• /
• pp.936-941
• /
• 2006

To apply object recognition techniques to real environment, illumination compensation method should be developed. As effective illumination compensation model, we focused our attention on Retinex model and illumination-Reflectance model, implemented them, and experimented on their performance. We implemented Retinex model with Single Scale Retinex, Multi-Scale Retinex, and Retinex Neural Network and Multi-Scale Retinex Neural Network, neural network model of Retinex model. Also, we implemented illumination-Reflectance model with reflectance image calculation by calculating an illumination image by low frequency filtering in frequency domain of Discrete Cosine Transform and Wavelet Transform, and Gaussian blurring. We compare their illumination compensation performance to facial images under nine illumination directions. We also compare their performance after post processing using Principal Component Analysis(PCA). As a result, illumination Reflectance model showed better performance and their overall performance was improved when illumination compensated images were post processed by PCA.

• The KIPS Transactions:PartB
• /
• v.17B no.3
• /
• pp.227-232
• /
• 2010

This paper proposes the real time lip reading method in the embedded environment. The embedded environment has the limited sources to use compared to existing PC environment, so it is hard to drive the lip reading system with existing PC environment in the embedded environment in real time. To solve the problem, this paper suggests detection methods of lip region, feature extraction of lips, and awareness methods of phonetic words suitable to the embedded environment. First, it detects the face region by using face color information to find out the accurate lip region and then detects the exact lip region by finding the position of both eyes from the detected face region and using the geometric relations. To detect strong features of lighting variables by the changing surroundings, histogram matching, lip folding, and RASTA filter were applied, and the properties extracted by using the principal component analysis(PCA) were used for recognition. The result of the test has shown the processing speed between 1.15 and 2.35 sec. according to vocalizations in the embedded environment of CPU 806Mhz, RAM 128MB specifications and obtained 77% of recognition as 139 among 180 words were recognized.

• Korean Journal of Soil Science and Fertilizer
• /
• v.44 no.3
• /
• pp.371-374
• /
• 2011

The objectives of the present study evaluated aquatic animals on the water in a rice field. Field investigation was carried out in conventional tillage without rice straw or green manure crop treatment (CTFS, check plot), no-tillage without cover crops (NTNT), no-tillage amended with rape (NTRA), no-tillage amended with rye (NTRY), no-tillage amended with hairyvetch (NTHV), and no-tillage amended with Chinese milk vetch (NTCM). Total dense population of aquatic animals in HTHV was significantly higher than the other plots (p<0.05) on May 30. Dense populations of Daphniidae and Culicidae on June 20 were lowest in CTFS compared to no-tillage plots (p<0.05). Furthermore, in principal component analysis (PCA), PC1 explained 44.9% of variance, whereas PC2 explained 26%, for a cumulative total of 70.9% and the PC1 of the PCA separated the samples from NT treatments and CFS (p<0.05).

• Journal of Korea Trade
• /
• v.25 no.5
• /
• pp.110-128
• /
• 2021

Purpose - The essential purpose of this study is to analyze the possibility of substitution of an individual job resulting from technological development represented by the 4th Industrial Resolution, considering the different effects of digital transformation on the labor market. Design/methodology - In order to estimate the substitution probability, this study used two data sets which the job characteristics data for individual occupations provided by KEIS and the information on occupational status of substitution provided by Frey and Osborne(2013). In total, 665 occupations were considered in this study. Of these, 80 occupations had data with labels of substitution status. The primary goal of estimation was to predict the degree of substitution for 607 of 665 occupations (excluding 58 with markers). It utilized three methods a principal component analysis, an unsupervised learning methodology of machine learning, and Ridge and Lasso from supervised learning methodology. After extracting significant variables based on the three methods, this study carried out logistics regression to estimate the probability of substitution for each occupation. Findings - The probability of substitution for other occupational groups did not significantly vary across individual models, and the rank order of the probabilities across occupational groups were similar across models. The mean of three methods of substitution probability was analyzed to be 45.3%. The highest value was obtained using the PCA method, and the lowest value was derived from the LASSO method. The average substitution probability of the trading industry was 45.1%, very similar to the overall average. Originality/value - This study has a significance in that it estimates the job substitution probability using various machine learning methods. The results of substitution probability estimation were compared by industry sector. In addition, This study attempts to compare between trade business and industry sector.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.283-294
• /
• 2022

The feature map used in the network for deep learning generally has larger data than the image and a higher compression rate than the image compression rate is required to transmit the feature map. This paper proposes a method for transmitting a pyramid feature map with high compression rate, which is used in a network with an FPN structure that has robustness to object size in deep learning-based image processing. In order to efficiently compress the pyramid feature map, this paper proposes a structure that predicts a pyramid feature map of a level that is not transmitted with pyramid feature map of some levels that transmitted through the proposed prediction network to efficiently compress the pyramid feature map and restores compression damage through the proposed reconstruction network. Suggested mAP, the performance of object detection for the COCO data set 2017 Train images of the proposed method, showed a performance improvement of 31.25% in BD-rate compared to the result of compressing the feature map through VTM12.0 in the rate-precision graph, and compared to the method of performing compression through PCA and DeepCABAC, the BD-rate improved by 57.79%.

• Safety and Health at Work
• /
• v.15 no.1
• /
• pp.42-52
• /
• 2024

Background: The lack of headforms that accurately reflect the head characteristics of Koreans and the demographic composition of the Korean population can lead to inadequate FFR testing and reduced effectiveness of FFRs. Method: Direct measurements of 5,110 individuals and 3D measurements of 2,044 individuals, aged between 9 and 69 years, were sampled from the data pool of Size Korea surveys based on the age and gender ratios of the Korean resident demographics. Seven head dimensions were selected based on the ISO 16976-2, availability of Size Korea measurements, and their relevance to the fit performance of FFRs. A principal component analysis (PCA) was performed using the direct measurements to extract the main factors explaining the head characteristics and then the main factors were standardized and remapped to 3D measurements, creating five size categories representing Korean head shapes. Lastly, representative 3D headforms were constructed by averaging five head shapes for each size category. Results: The study identified two main factors explaining Korean head characteristics by the PCA procedure specified in ISO 16976-2 and developed five representative headforms reflecting the anthropometric features of Korean heads: medium, small, large, short & wide, and long & narrow. Conclusion: This study developed representative headforms tailored to the Korean population for conducting total inward leakage (TIL) tests on filtering facepiece respirators (FFRs). The representative headforms can be used for TIL testing by employing robotic headforms to enhance the performance of FFRs for the Korean target population.

• Journal of Navigation and Port Research
• /
• v.27 no.3
• /
• pp.335-343
• /
• 2003

Currently serious conflicts of interests are arisen for the use of coastal area in Korea. However, there no mediation program, mediators' consistent policies and reasonable laws to resolve conflict of interests which may be arisen when developing coastal area. The objective of this study is to lay the evaluation criteria for the formalized objective evaluation among disputants of coastal conflicts for the better understanding and characterizing of coastal conflicts in Korea. In order to do so, this study has adopted for the extraction of the evaluation factors to describe the present conditions of conflicts in the selected study area(Sihwa lake), to analyze the problems, and then to explore alternative approaches for resolving the conflicts. As research methodologies, we have depended upon literature review and field survey methods. As field survey methods, we employed structured questionnaires for the various samples from the experts of research institutes, professors, representatives of NGOs and citizens. Survey results suggested that 5 representative elements comprising 35 detailed elements could be identified. Based on these results, this study was able to identify and classify the evaluation factors and help to resolve coastal conflicts in Korea.

• Journal of KIISE:Software and Applications
• /
• v.28 no.2
• /
• pp.192-200
• /
• 2001

본 논문은 조명 변화, 표정 변화, 부분적인 오클루전이 있는 얼굴 영상에 강인하고 적은 메모리양과 계산량을 갖는 효율적인 얼굴 인식 방법을 제안한다. SKKUface(Sungkyunkwan University face)라 명명한 이 방법은 먼저 훈련 영상에 PCA(principal component analysis)를 적용하여 차원을 줄일 때 구해지는 특징 벡터 공간에서 조명 변화, 얼굴 표정 변화 등에 해당되는 공간이 최대한 제외된 새로운 특징 벡터 공간을 생성한다. 이러한 특징 벡터 공간은 얼굴의 고유특징만을 주로 포함하는 벡터 공간이므로 이러한 벡터 공간에 Fisher linear discriminant를 적용하면 클래스간의 더욱 효과적인 분리가 이루어져 인식률을 획기적으로 향상시킨다. 또한, SKKUface 방법은 클래스간 분산(between-class covariance) 행렬과 클래스내 분산(within-class covariance) 행렬을 계산할 때 문제가 되는 메모리양과 계산 시간을 획기적으로 줄이는 방법을 제안하여 적용하였다. 제안된 SKKUface 방법의 얼굴 인식 성능을 평가하기 위하여 YALE, SKKU, ORL(Olivetti Research Laboratory) 얼굴 데이타베이스를 가지고 기존의 얼굴 인식 방법으로 널리 알려진 Eigenface 방법, Fisherface 방법과 함께 인식률을 비교 평가하였다. 실험 결과, 제안된 SKKUface 방법이 조명 변화, 부분적인 오클루전이 있는 얼굴 영상에 대해서 Eigenface 방법과 Fisherface 방법에 비해 인식률이 상당히 우수함을 알 수 있었다.

• Korean Journal of Agricultural Science
• /
• v.36 no.2
• /
• pp.219-224
• /
• 2009

Two functional modified-butterfats (MF668 and MF866) were synthesized with two blends (6:6:8 and 8:6:6, w/w%) of anhydrous butterfat (ABF), palm stearin (PS) and flaxseed oil (FSO, omega-3) via lipase-catalyzed interesterification reaction. Their flavor characteristic was investigated using electronic nose and SPME-GC/MS analysis. Each flavor pattern of ABF, FSO, MF668 and MF866 was significantly discriminated with first principal component score of 95.16% in PCA plot. In functional modified-butterfats analyzed with SPME-GC/MS, various volatile compounds such as aldehydes, ketones, acids, and alkanes were detected.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 1997.04a
• /
• pp.99-102
• /
• 1997

An electronic nose system is an instrument designed far mimicking human olfactory system. It consists generally of gas (odor) sensor array corresponding to olfactory receptors of human nose and artificial neural network pattern recognition technique based on human biological odor sensing mechanism. Considerable attempts to develop the electronic nose system have been made far applications in the fields of floods, drinks, cosmetics, environment monitoring, etc. A portable electronic nose system has been fabricated by using oxide semiconductor gas sensor array and pattern recognition technique such as principal component analysis (PCA) and back propagation artificial neural network The sensor array consists of six thick film gas sensors whose sensing layers are Pd-doped WO$_3$ Pt-doped SnO$_2$ TiO$_2$-Sb$_2$O$_3$-Pd-doped SnO$_2$ TiO$_2$-Sb$_2$O$_{5}$-Pd-doped SnO$_2$+Pd filter layer, A1$_2$O$_3$-doped ZnO and PdCl$_2$-doped SnO$_2$. As an application the system has been used to identify CO/HC car exhausting gases and the identification has been successfully demonstrated.d.