• Journal of Software Engineering Society
• /
• v.29 no.1
• /
• pp.13-21
• /
• 2020

As CNN model is applied to various domains such as image classification and object detection, the performance of CNN model which is used to safety critical system like autonomous vehicles should be reliable. To evaluate that CNN model can sustain the performance in various environments, we developed an image data augmentation apparatus which generates images that is changed background. If an image which contains object is entered into the apparatus, it extracts an object image from the entered image and generate s composed images by synthesizing the object image with collected background images. A s a method to evaluate a CNN model, the apparatus generate s new test images from original test images, and we evaluate the CNN model by the new test image. As a case study, we generated new test images from Pascal VOC2007 and evaluated a YOLOv3 model with the new images. As a result, it was detected that mAP of new test images is almost 0.11 lower than mAP of the original test images.

• Journal of KIISE
• /
• v.44 no.9
• /
• pp.992-1004
• /
• 2017

To assess image quality accurately, an image quality assessment (IQA) metric is required to reflect the human visual system (HVS) properly. In other words, the structure, color, and contrast ratio of the image should be evaluated in consideration of various factors. In addition, as mobile embedded devices such as smartphone become popular, a fast computing speed is important. In this paper, the proposed IQA metric combines color similarity, gradient similarity, and phase similarity synergistically to satisfy the HVS and is designed by using optimized pooling and quantization for fast computation. The proposed IQA metric is compared against existing 13 methods using 4 kinds of evaluation methods. The experimental results show that the proposed IQA metric ranks the first on 3 evaluation methods and the first on the remaining method, next to VSI which is the most remarkable IQA metric. Its computing speed is on average about 20% faster than VSI's. In addition, we find that the proposed IQA metric has a bigger amount of correlation with the HVS than existing IQA metrics.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.05b
• /
• pp.206-209
• /
• 2003

생체인식 기술 중에서 지문-기반 인식은 많은 어플리케이션에 성공적으로 이용되어온 가장 오래된 방법이지만 지문 인식 시스템이 클라이언트/서버 형식으로 운영될 경우 지문 이미지를 획득하여 특징점을 추출하고 이를 서버로 전송하는 경우 보안 취약성이 존재한다. 취약성에는 여러 가지가 있을 수 있지만 본 연구와 관련된 부분은 지문 이미지 획득과 특징점 추출과정 그리고 추출된 특징점의 매칭 과정에 초점을 맞추고 있다. 본 논문에서는 지문 이미지의 영상 처리를 통한 특징점 추출 및 추출된 특징점을 변조하는 도구를 구현하여 기존의 지문인식 시스템들에 대한 매칭 알고리즘 취약성 평가를 검증할 수 있는 평가 도구를 설계 및 구현하였다. 매칭 알고리즘 취약성 평가는 평가를 위해 구현된 지문 인식 시스템에서 특징점을 추출하고, 추출된 특징점 중 단점을 이용하여 선택된 이미지 영역을 변조한다. 변조된 이미지는 평가 대상 시스템에서 재입력하여 평가를 수행한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.423-424
• /
• 2020

다양한 환경 변화에 따라 적용 가능한 최적의 위장무늬 개발의 필요성이 증대됨에 따라 위장무늬 성능 평가를 위한 포토시뮬레이션 기술 또한 주목받고 있으나 포토시뮬레이션 저작에 관한 연구는 미비하다. 본 논문에서는 작전환경 이미지 상 위장무늬 이미지의 배치 및 기 배치된 위장무늬의 탐지 시간을 측정하는 소프트웨어인 포토시뮬레이션 기술 개발에 대해 서술한다. 개발된 포토시뮬레이션은 작전환경 및 위장무늬 이미지 로드, 사용자 입력도구를 통한 대상 작전환경 이미지 상 위장무늬 이미지의 배치 및 저작, 저작 된 작전 환경 이미지 상 위장무늬 이미지를 모니터에 출력, 사용자 입력도구를 통한 작전환경 이미지 상 위장무늬 이미지의 탐지 및 탐지 시간 측정 기술을 포함한다. 결과에서는 개발 포토시뮬레이션 기술을 통한 위장무늬 이미지 배치 및 저작, 그리고 위장무늬 이미지의 평균 시간 측정 결과 예시를 보여준다.

• Journal of The Korean Association For Science Education
• /
• v.38 no.5
• /
• pp.753-763
• /
• 2018

The image of scientists that learners have has an important impact on science learning and on science-related career choices. The image of the scientist was mainly analyzed using the drawing analysis method. Drawing analysis has limitations on drawing, mainly analyzing the external image of scientist. Science teachers' images of scientists and their perception of science-related careers are important factors in students' science learning and science-related career choices. However, research on science teachers is lacking. Therefore, the purpose of this study is to investigate the usefulness of measurement tools by developing and applying a scientist image measurement tool through the semantic analysis method, and to discuss the educational implications of the research by investigating the image of scientists and science-related professions of secondary pre-service science teachers. The subjects of the study were 79 male and 55 female for a total of 134 students in the 2nd and 3rd grades majoring in science education at a teachers college. The results of the research show that the image measurement tool consisted of four components: 'ability,' 'evaluation,' 'activity,' and 'emotion,' in 24 items. As a result of applying the developed measurement tool to the secondary pre-service science teachers, the image of the 'evaluation,' 'ability,' and 'activity' elements of the scientist were high, but 'emotion' was low. There was no statistically significant difference according to gender. It is found that science-related career perceive them as 'hard,' 'professional,' 'smart,' and 'complex.' In particular, male students perceive themselves as 'hard and difficult' while female students perceive it as 'challenging and complicated'. Finally, we discussed the usefulness of using the image measurement tool of the scientists, the image of the scientists of the secondary pre-service science teachers, and the educational implications on science-related career.

• Archives of design research
• /
• v.11 no.3
• /
• pp.199-206
• /
• 1998

Though development of semantic ratings of color image which is objective, concrete and reflecting our realities is urgent, researches on the area has not been active. To develop concepts and methods on semantic ratings of color image, study subjects, sampling, stimulating tools, analysis methods, and evaluation scale were critically reviewed on the literatures on color image. Planning color of costume commodity requires research on various themes and expanding study subjects into a variety of social strata. According to the context of study, stimulating tools should be selected prudenly, and analysis methods should be scrutinized. Factor analysis was used frequently as analysis method to extract factors associated with color image.

• Journal of The Korean Association For Science Education
• /
• v.37 no.6
• /
• pp.1051-1061
• /
• 2017

An image is a comprehensive result that you have experienced about an object and means the image that you have on the surface of your consciousness. The image of the subject has an important influence on learning the subject. The image analysis of the subjects that the learners have will be good data to decide the direction of teaching and learning. The purpose of this study is to develop and apply measurement tools for physics image and discuss its educational implications. The research method is to develop the measurement tools for the physics image by semantic analysis method and apply it to the secondary pre-service physics teacher. The subjects of the study were 39 first graders, 31 second graders, 37 third graders, and 38 fourth graders at the University of Education, a total of 145 students, 82 of whom were male and 63 were female. The study results show that the image measurement tools for physics consisted of 25 items from five elements: 'interest,' 'feeling,' 'scope,' 'evaluation,' and 'viewpoint.' There were statistically significant differences between the male and female students in applying the measurement tools developed for the physics image of secondary pre-service physics teachers. Male students showed significantly higher statistical significance than female students in the 'interest' and 'feeling' elements of measurement tools for the physics image. In the 'scope' element of measurement tools for the physics image the second grade was statistically higher than the fourth grade. Finally, we discussed educational implications for image analysis of physics and the usefulness of using measurement tools in physics image.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.06a
• /
• pp.489-496
• /
• 2001

본 연구에서는 기업의 경영이념이나 특성 등을 시각적 이미지로 표현하는 CI(Corporate Identity) 심벌마크의 설계 및 평가를 위해 Hybrid 감성공학기법을 적용하였다. 먼저, CI 심벌마크에 내재된 기업의 시각적 이미지를 분석하기 위하여 SD평가를 실시하였으며 CI 심벌마크의 디자인 요소와 기업이미지와의 상관관계를 분석하기 위하여 정통적인 감성공학적 접근방식에 해당하는 순향성 감성공학기법을 적용하였다. 최종적으로는 CI 심벌마크의 디자인 요소로부터 기업이미지에 대한 고객의 감성을 자동으로 평가할 수 있는 시스템을 개발하기 위하여 역향성 감성공학기법을 적용하였다. 구축된 시스템은 CI 심벌마크의 설계를 지원함으로써 설계에 소요되는 시간과 비용을 효과적으로 줄일 수 있는 유용한 도구로 장차 이용되리라 기대된다.

• Journal of Bio-Environment Control
• /
• v.33 no.2
• /
• pp.120-128
• /
• 2024

Since ChatGPT was released in 2022, the generative artificial intelligence (AI) industry has seen massive growth and is expected to bring significant innovations to cognitive tasks. AI-based image generation, in particular, is leading major changes in the digital world. This study investigates the technical foundations of Midjourney, Stable Diffusion, and Firefly-three notable AI image generation tools-and compares their effectiveness by examining the images they produce. The results show that these AI tools can generate realistic images of tomatoes, strawberries, paprikas, and cucumbers, typical crops grown in greenhouse. Especially, Firefly stood out for its ability to produce very realistic images of greenhouse-grown crops. However, all tools struggled to fully capture the environmental context of greenhouses where these crops grow. The process of refining prompts and using reference images has proven effective in accurately generating images of strawberry fruits and their cultivation systems. In the case of generating cucumber images, the AI tools produced images very close to real ones, with no significant differences found in their evaluation scores. This study demonstrates how AI-based image generation technology can be applied in agriculture, suggesting a bright future for its use in this field.

• Proceedings of the Korea Contents Association Conference
• /
• 2014.11a
• /
• pp.383-384
• /
• 2014

본 연구는 모바일 환경에서 활용 가능한 해석된 빗속의 사람 결과 이미지를 활용한 스트레스 평가도구 개발을 위해, 결과 이미지를 사용자에게 대비하여 제시하고 사용자의 선택 결과를 분석하여 스트레스 수준을 평가하기 위한 방법론의 타당성을 분석하였다. '빗속의 사람' 검사는 대상자가 직접 그림을 그려야 하나, 모바일 환경에서는 구현과 해석이 어려워 이미 그려진 그림을 선택하도록 설계하였다. 이를 위해 '빗속의 사람' 검사의 결과 이미지가 스트레스 상태를 선별할 때 유용한지를 밝히고자 하였다. 서울 및 경기지역의 20~50대 이하 여성 101명이 본 연구에 참여하였다. 이들을 대상으로 '빗속의 사람' 검사와 스트레스 검사를 동시에 실시하였다. '빗속의 사람' 검사 결과와 스트레스 검사 결과는 검사해석방법에 따라 스트레스를 3단계로 분류하였다. 분류된 3단계의 결과는 서로 유의한 상관관계가 있어 유용하게 활용 가능함을 확인하였다.