• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.1
• /
• pp.75-80
• /
• 2021

Artificial intelligence is becoming an important part of our lives providing incredible benefits. In this respect, facial expression recognition has been one of the hot topics among computer vision researchers in recent decades. Classifying small dataset of low resolution images requires the development of a new small scale deep CNN model. To do this, we propose a method suitable for small datasets. Compared to the traditional deep CNN models, this model uses only a fraction of the memory in terms of total learnable weights, but it shows very similar results for the FER2013 and FERPlus datasets.

• Korea Trade Review
• /
• v.43 no.6
• /
• pp.193-214
• /
• 2018

The role of social value in public institutions has recently been emphasized. The purpose of this paper is to present key performance indicators(KPIs) and a development model for the realization of social value for port authorities. KPIs that could be quantitatively measured are presented with the five social value assessment indicators of the government management evaluation system for public institutions. Through the analysis of vision, mission and social value promotion strategies and stakeholders for each port authority, the concept of a customer-specific social value model is presented.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.183-185
• /
• 2021

Detecting bacteria in blood could be an important research area in medicine and computer vision. In this paper, we propose a method for detecting bacteria in blood from 366 darkfield microscopy images acquired at Kaggle. Generate a training dataset through preprocessing and data augmentation using image processing techniques, and define a deep learning model for learning it. As a result of the experiment, it was confirmed that the proposed deep learning model effectively detects red blood cells and bacteria in darkfield microscopy images. In this paper, we learned using a relatively simple model, but it seems that more accurate results can be obtained by using a deeper model.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.278-284
• /
• 2009

Multimodal data to have several modalities such as videos, images, sounds and texts for one contents is increasing. Since this type of data has ill-defined format, it is not easy to represent the crossmodal information for them explicitly. So, we proposed new method to extract and analyze vision-language crossmodal association information using the documentaries video data about the nature. We collected pairs of images and captions from 3 genres of documentaries such as jungle, ocean and universe, and extracted a set of visual words and that of text words from them. We found out that two modal data have semantic association on crossmodal association information from this analysis.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.05a
• /
• pp.309-310
• /
• 2006

This paper is about the development of surface inspection of bearing inner and outer race using machine vision. Before this system is developed, most inspections are performed by workers' naked eye. To improve both the inconvenience and incorrectness, another new tester is introduced. This system has the three sections mainly. First one is the mechanism section which transfers bearing manufactured from previous process line to the testing process in plant. Another is the inspection system which is composed of two parts: computer vision and measurement system using laser diode which inspects the defects of the bearing inner or outer race. The other is the pneumatic cylinder part controlled by Programmable Logic Controller(PLC). The system which is developed shows favorable results, and that has the advantage of convenience and correctness compared to previous system.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.3
• /
• pp.151-159
• /
• 2006

In this paper. we Present an estimation method of a face pose by using two camera images. First, it finds corresponding facial feature points of eyebrow, eye and lip from two images After that, it computes three dimensional location of the facial feature points by using the triangulation method of stereo vision techniques. Next. it makes a triangle by using the extracted facial feature points and computes the surface normal vector of the triangle. The surface normal of the triangle represents the direction of the face. We applied the computed face pose to display a 3D face model. The experimental results show that the proposed method extracts correct face pose.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.04a
• /
• pp.439-442
• /
• 2010

본 논문에서는 비전 기반의 실시간 대기오염 모니터링 시스템을 제안한다. 제안된 시스템은 먼저 실시간으로 제공되는 동영상을 분석하여 차종 별 대수와 평균속도 등의 교통 파라미터를 실시간으로 추출하고, 이를 바탕으로 대기 중의 CO, NO2등의 밀도를 추정하여 시간대별 대기 오염도를 모니터링 한다. 이를 위해 제안된 시스템은 배경모델을 이용한 차량 추출, 차종 별 윤곽선 및 크기 정보를 이용하여 템플릿 기반으로 차종을 인식하고 이를 추적하여 대수 및 속도를 인식한다. 제안된 시스템의 평가를 위해 교통이 밀집된 공간에 설치하여 테스트하였고, 실제 결과와 비교한 결과, 차량 속도에서 정확도 83.3%, 차종인식에서 정확도 86.98%를 보였다. 이러한 실험 결과는 제안된 시스템이 다양한 지역에서 실시간 대기오염물질 배출량을 산정하는데 적용될 수 있음을 보여주었다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.222-224
• /
• 2022

Deep learning-based computer vision applications in the field of object segmentation take a transfer learning method using hyperparameters and models pretrained and distributed by STOA techniques to improve performance. Custom datasets used in this process require a lot of resources, such as time and labeling, in labeling tasks to generate Ground Truth information. In this paper, we present an automatic labeling construction method using object segmentation techniques so that resources such as time and labeling can be used less to build custom datasets used in deep learning neural networks.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.9 no.5
• /
• pp.213-224
• /
• 2009

This paper presents a new algorithm for estimating a driver's physical condition using real-time vision system and performs experimentation for real facial image data. The system relies on a face recognition to robustly track the center points and sizes of person's two pupils, and two side edge points of the mouth. The face recognition constitutes the color statistics by YUV color space together with geometrical model of a typical face. The system can classify the rotation in all viewing directions, to detect eye/mouth occlusion, eye blinking and eye closure, and to recover the three dimensional gaze of the eyes. These are utilized to determine the carelessness and drowsiness of the driver. Finally, experimental results have demonstrated the validity and the applicability of the proposed method for the estimation of a driver's physical condition.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.11
• /
• pp.273-280
• /
• 2020

Automatic Static Analysis Tools help developers to quickly find potential defects in source code with less effort. However, the tools reports a large number of false positive warnings which do not have to fix. In our study, we proposed an artificial neural network-based warning classification method using topic models of source code blocks. We collect revisions for fixing bugs from software change management (SCM) system and extract code blocks modified by developers. In deep learning stage, topic distribution values of the code blocks and the binary data that present the warning removal in the blocks are used as input and target data in an simple artificial neural network, respectively. In our experimental results, our warning classification model based on neural network shows very high performance to predict label of warnings such as true or false positive.