• Science of Emotion and Sensibility
• /
• v.10 no.1
• /
• pp.113-125
• /
• 2007

The aim of the experimental studies described in this paper is to investigate the effects of the face/eye/mouth areas using dynamic facial expressions and static facial expressions on emotional recognition. Using seven-seconds-displays, experiment 1 for basic emotions and experiment 2 for complex emotions are executed. The results of two experiments supported that the effects of dynamic facial expressions are higher than static one on emotional recognition and indicated the higher emotional recognition effects of eye area on dynamic images than mouth area. These results suggest that dynamic properties should be considered in emotional study with facial expressions for not only basic emotions but also complex emotions. However, we should consider the properties of emotion because each emotion did not show the effects of dynamic image equally. Furthermore, this study let us know which facial area shows emotional states more correctly is according to the feature emotion.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.8
• /
• pp.31-37
• /
• 2021

In this paper, we propose a method to effectively search by automatically classifying scenes in which specific images such as pitching or swing appear in baseball game images using a CNN(Convolution Neural Network) model. In addition, we propose a video scene search system that links the classification results of specific motions and game records. In order to test the efficiency of the proposed system, an experiment was conducted to classify the Korean professional baseball game videos from 2018 to 2019 by specific scenes. In an experiment to classify pitching scenes in baseball game images, the accuracy was about 90% for each game. And in the video scene search experiment linking the game record by extracting the scoreboard included in the game video, the accuracy was about 80% for each game. It is expected that the results of this study can be used effectively to establish strategies for improving performance by systematically analyzing past game images in Korean professional baseball games.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.3D
• /
• pp.535-540
• /
• 2006

This paper presented an effective strategy to extract the buildings and to reconstruct 3-D buildings using high-resolution multispectral stereo satellite images. Proposed scheme contained three major steps: building enhancement and segmentation using both BDT (Background Discriminant Transformation) and ISODATA algorithm, conjugate building identification using the object matching with Hausdorff distance and color indexing, and 3-D building reconstruction using photogrammetric techniques. IKONOS multispectral stereo images were used to evaluate the scheme. As a result, the BDT technique was verified as an effective tool for enhancing building areas since BDT suppressed the dominance of background to enhance the building as a non-background. In building recognition, color information itself was not enough to identify the conjugate building pairs since most buildings are composed of similar materials such as concrete. When both Hausdorff distance for edge information and color indexing for color information were combined, most segmented buildings in the stereo images were correctly identified. Finally, 3-D building models were successfully generated using the space intersection by the forward RFM (Rational Function Model).

• Proceedings of the Korea Multimedia Society Conference
• /
• 1998.10a
• /
• pp.232-236
• /
• 1998

이미지가 전경과 배경으로 이루어져 있을 경우, 이미지에서 중요한 대부분의 정보는 전경의 영역에 집중하게 된다. 만약 이미지를 전경과 배경으로 구분할 수 있다면 영상 인식, 영상 합성, 영상 압축 등 여러 분야에 유용하게 활용할 수 있게 된다. 본 논문에서는 선명도 차이를 이용하여 이미지를 전경과 배경으로 분할하는 방법을 소개하고, 그 실험 결과를 보인다.

• Korean Journal of Remote Sensing
• /
• v.24 no.6
• /
• pp.631-639
• /
• 2008

This study presents an approach to synthesize hyperspectral images of lower resolution at a higher resolution using the high resolution images acquired from a sensor of commercial satellites. The proposed method was applied to the reconstruction of EO-1 Hyperion images using the images acquired from IKONOS sensor. Based on the FitPAN-Mod pansharpening technique (Lee, 2008b), the hyperspectral images of 30m resolution were reconstructed at 1m resolution of IKONOS panchromatic image. In this study, the synthesized hyperspectral images of 50 bands, whose wavelengths range in the wavelength of panchromatic sensor, were generated from the three stages of high resolution reconstruction using FitPAN-Mod. The experimental results show that the proposed method effectively integrates the spatial detail of the panchromatic modality as well as the spectral detail of the hyperspectral one into the synthesized image. It indicates the proposed method has a potential as a technique to produce alternative images for the images that would have been observed from a hyperspectral sensor at the high resolution of commercial satellite images.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.44 no.1
• /
• pp.125-132
• /
• 2024

Optical satellite images are being used for national security and collection of information, and their utilization is increasing. However, it acquires low-quality images that are not suitable for the user's requirement due to weather conditions and time constraints. In this paper, a deep learning-based conversion of image and colorization model referring to high-resolution SAR images was created to simulate the occluded area with clouds of optical satellite images. The model was experimented according to the type of algorithm applied and input data, and each simulated images was compared and analyzed. In particular, the amount of pixel value information between the input black-and-white image and the SAR image was similarly constructed to overcome the problem caused by the relatively lack of color information. As a result of the experiment, the histogram distribution of the simulated image learned with the Gray-scale image and the high-resolution SAR image was relatively similar to the original image. In addition, the RMSE value was about 6.9827 and the PSNR value was about 31.3960 calculated for quantitative analysis.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04b
• /
• pp.622-624
• /
• 2002

본 논문에서는 선택적 주의에 기반한 잡영 영상에서의 목표물 탐지 방법에 대해 기술한다. 특히 제안하는 방법은 목표물에 대한 아무런 지식을 사용하지 않고, 단지 입력되는 영상의 상향식 단서만을 사용하여 목표물을 탐지해냄으로써 여러 다양한 분야에 일반적으로 사용될 수 있다. 제안하는 시스템에서는 몇 가지 기본 특징들이 입력된 영상에서 바로 추출되며, 이러한 특징들이 서로 통합되어 가는 과정에서 목표물 탐지에 유용하지 않은 정보는 자연스럽게 걸러지며, 유용한 정보는 추가되고 부각되어진다. 간단한 영상부터 복잡한 자연영상에 이르는 다양한 잡영 영상을 대상으로 실험하여 제안하는 시스템의 성능을 평가하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2013.06a
• /
• pp.348-350
• /
• 2013

본 논문에서는 깊이영상의 특징을 이용하여 깊이영상에 보다 적합한 움직임 예측방법에 대한 방식을 제안한다. 기존 컬러영상 기반으로 제안되었던 대부분의 움직임 예측 방법들이 깊이영상에 적용할 경우 local minimum 에 빠지게 되어 이에 따른 압축 성능 저하가 있음을 확인하였다. 본 논문에서는 이러한 문제점들이 깊이영상의 오브젝트 경계 영역에서 나타나게 됨을 분석하며, 이러한 문제점을 해결하기 위해 깊이영상의 경계 영역에 대해 feature matching 방식을 이용한 full search 방식을 제안한다. 실험적인 결과는 제안방식이 기존 full search 방식과 비교하여 성능은 비슷하게 유지한 채 복잡도를 크게 개선할 수 있음을 보여준다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 1998.04a
• /
• pp.154-159
• /
• 1998

최근의 전자도서관에서 문서영상 데이터베이스를 구축하여 사용자에게 원하는 정보의 원문을 그대로 서비스하고 있는데, 주로 200 dpi 문서영상에 대해 TIFF 영상포맷에서의 ITU-T T.6 압축방법을 사용하고 있다. 본 연구에서는, 문서영상 데이터베이스의 확장성, 지속성, 효율성 등을 고려하여, 문서 영상의 스캐닝 해상도의 600 dpi가 적당하며, 압축방법은 JBIG이 타당함을 제시하였다. 아울러, 모니터 및 프린터 기반 서비스의 특성을 분석하여 서비스 해상도를 차별화하는 방법인 단계별 서비스 방안을 제시함으로써 JBIG의 단점인 과다한 복구시간 문제를 해결하였다. 대표적인 문서영상들에 대한 실험을 통해, JBIG의 높은 압축율 및 제시된 단계별 서비스 방안의 타당성을 확인하였다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 1998.04a
• /
• pp.34-39
• /
• 1998

영상검색을 위해 Wavelet 변환을 사용한 특징추출 접근방법은 영상들을 압축과 동시에 인덱스 할 수 있어서 영상 데이터베이스 저장과 관리의 복잡성이 상당히 감소될 수 있다. 본 연구는 각 영상의 Hue값에 대해 위치 정보의 주파수 정보를 가지는 Wavelet 변환의 성질을 이용하여 2단계 Wavelet 변환 후 생성된 저대역 부밴드에서 칼라 특징을 추출하고 나머지 부밴드에서 질감 특징을 추출하여 영상 데이터베이스의 검색에 이용한다. 200개 영상을 사용하여 실험한 결과, 제안된 방법은 recall과 precision에서 약 97%, 81%의 검색 효율을 보였다.