• Proceedings of the Korea Contents Association Conference
• /
• 2015.05a
• /
• pp.303-304
• /
• 2015

최근 차량을 이용한 범죄가 점점 증가하고 있고, 그로인해 범죄 차량의 식별 또한 많은 사람들의 관심을 받고 있다. 본 논문에서는 차량 식별을 위해 방범용 CCTV 영상을 이용한다. 차량 방범을 위한 CCTV 이미지 속에서 얻을 수 있는 차량 내 정보는 크게 번호판, 모델, 크기, 색상 등 여러 가지가 있는데, 본 논문에서는 그중 하나인 색상을 인식하는 방법에 대하여 제안한다. 기존에는 여러 가지 색상공간을 이용하여 추출하는 방법을 많이 사용했는데, 단순히 색상공간만으로는 무채색의 차량 추출이 어렵다. 이를 보완하기 위해 HSI 색상공간과 히스토그램의 분산을 분석하는 방법을 제안한다. 이를 이용하여 차량을 보다 정확한 색상별로 검색하는 것이 가능하며, 또한 차량 외의 다른 물체들의 색상 인식에도 응용 가능하다.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.6 s.44
• /
• pp.79-86
• /
• 2006

Classification technology is essential for fast retrieval in large multi-media database. This paper proposes a combining GA(Genetic Algorithm) and SVM(Support Vector Machine) model to fast retrieval. We used color and texture as feature vectors. We improved the retrieval accuracy by using proposed model which retrieves an optimal feature vector set in extracted feature vector sets. The first performance test was executed for the performance of color, texture and the feature vector combined with color and texture. The second performance test, was executed for performance of SVM and proposed algorithm. The results of the experiment, using the feature vector combined color and texture showed a good Performance than a single feature vector and the proposed algorithm using hybrid method also showed a good performance than SVM algorithm.

• Proceedings of the KSAR Conference
• /
• 2002.06a
• /
• pp.30-30
• /
• 2002

본 연구는 돼지 액상정액의 품질을 간편하게 육안적으로 식별하기 위한 방법을 개발하기 위하여 채취된 정액을 페놀레드(0.5%)가 첨가된 BTS보존액에 정액과 회석액비율을 1:1로 희석하여 1-2시간 17℃까지 냉각시킨 후 최종정자수가 3×10/sup 9/ sperm/80㎖ 되도록 최종 추가조정 희석한 후 17℃에서 1, 3 및 5일 동안 보관한 정액의 활력과 pH를 조사하고 페놀레드 색상변화를 Figure 1과 같이 pH 6.2-8.0까지의 색상을 10등급으로 나누고 pH 7.0 수준을 표준색상으로 하여 색상 변화를 조사한 결과는 다음과 같다. 돼지 액상정액을 17℃에서 1, 3 및 5일 동안 각각 보관하였을 때 정자 활력은 71.9%, 59.8% 및 53.9%였으며, 이 때 pH 는 각각 6.89, 6.84 및 7.06으로 적정 색상을 나타내었다. (중략)

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.10
• /
• pp.93-99
• /
• 2009

The color harmony in video was no way to know for giving pleasure. By identifying these color harmony, it gives order, clarity, similarity, contrast, etc. Therefore, to identify the color balance is very important. Color Harmony identify the color is whether the harmony by color harmony theory of Munsell, Ostwald, Firren, Moon & Spenser, Itten, Chevreul, and Judd etc. One of these methods, we identify color harmonies of 2 colors, 3 colors, 4 colors, 5 colors and 6 colors using Itten's color balance. Identification is using by Canny edge extraction, labeling and clustering, and color extraction and harmony etc. By identifying this color harmonies, we have laid the foundation of emotional database construction and emotional recognition.

• Proceedings of the KIEE Conference
• /
• 2003.11c
• /
• pp.747-749
• /
• 2003

인간은 시각기관을 통해 영상을 읽어 들이고, 그 데이터로부터 대상 물체의 여러 정보를 취득한다. 물체가 놓여져 있는 빛 환경 하에서 반사, 굴절, 흡수, 투과 및 간섭 등과 같은 매우 복잡한 빛 작용의 결과인 영상이 눈에 입력된다. 이 여러 정보 가운데 깊이와 색상 정보는 매우 중요한 인간의 시각 식별 인지 능력이다. 이 논문은 깊이와 색상의 상관관계를 실험을 통해 규명하고자 하였다. 색상 변화는 grey tone으로 한정하였다. 깊이와 색상을 각각 독립변수로 설정한 실험 조건 하에서 디지털 영상신호 데이터를 취득, 분석하였다. 색상을 상수로 처리한 다음, 깊이를 변수로 등간격으로 변화시켜 실험한 후, 변수를 바꾸어 깊이를 상수로 놓고 색상을 다단계로 변화시켜 영상 데이터를 취득하였다. 빛의 조사(照射) 작도는 90도로 일정하게 두어 그림자 효과를 배제하였다. 디지털 영상 입력 과정에서 포함되기 쉬운 노이즈와 떨림, 초점 흐림 등을 전처리로 처리한 후 색도 변화를 분석하였다. 분석 결과, 이미지 속에 내재된 깊이와 색상 정보의 상호 이중적 구조 형태로의 존재를 규명하였다.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_3
• /
• pp.1415-1425
• /
• 2018

Kompsat-5 is the first Earth Observation Satellite which is equipped with an SAR in Korea. SAR images are generated by receiving signals reflected from an object by microwaves emitted from a SAR antenna. Because the wavelengths of microwaves are longer than the size of particles in the atmosphere, it can penetrate clouds and fog, and high-resolution images can be obtained without distinction between day and night. However, there is no color information in SAR images. To overcome these limitations of SAR images, colorization of SAR images using Cycle GAN, a deep learning model developed for domain translation, was conducted. Training of Cycle GAN is unstable due to the unsupervised learning based on unpaired dataset. Therefore, we proposed MS Cycle GAN applying multi-scale discriminator to solve the training instability of Cycle GAN and to improve the performance of colorization in this paper. To compare colorization performance of MS Cycle GAN and Cycle GAN, generated images by both models were compared qualitatively and quantitatively. Training Cycle GAN with multi-scale discriminator shows the losses of generators and discriminators are significantly reduced compared to the conventional Cycle GAN, and we identified that generated images by MS Cycle GAN are well-matched with the characteristics of regions such as leaves, rivers, and land.

• Proceedings of the Korea Contents Association Conference
• /
• 2010.05a
• /
• pp.542-544
• /
• 2010

본 논문은 유전 알고리즘과 신경망 알고리즘을 결합하여 내용기반 영상 식별을 하는 연구 방법을 제시한다. 특징벡터로는 색상 정보와 질감 정보를 사용하였다. 추출된 특징벡터의 집합을 제안한 모델을 통해 최적의 유효 특징벡터의 집합을 찾아 영상을 식별하고자 한다.

• Journal of Internet Computing and Services
• /
• v.24 no.5
• /
• pp.29-35
• /
• 2023

CCTV is used for various purposes such as crime prevention, public safety reinforcement, and traffic management. However, as the range and resolution of the camera improve, there is a risk of exposing personal information in the video. Therefore, there is a need for new technologies that can identify individuals while protecting personal information in images. In this paper, we propose histogram-based singular value decomposition for object identification and tracking. The proposed method distinguishes different objects present in the image using color information of the object. For object recognition, YOLO and DeepSORT are used to detect and extract people present in the image. Color values are extracted with a black-and-white histogram using location information of the detected person. Singular value decomposition is used to extract and use only meaningful information among the extracted color values. When using singular value decomposition, the accuracy of object color extraction is increased by using the average of the upper singular value in the result. Color information extracted using singular value decomposition is compared with colors present in other images, and the same person present in different images is detected. Euclidean distance is used for color information comparison, and Top-N is used for accuracy evaluation. As a result of the evaluation, when detecting the same person using a black-and-white histogram and singular value decomposition, it recorded a maximum of 100% to a minimum of 74%.

• Journal of the Korea Computer Graphics Society
• /
• v.16 no.1
• /
• pp.1-7
• /
• 2010

With the widespread use of vision-based surveillance systems, the capability for person identification is now an essential component. However, the CCTV cameras used in surveillance systems tend to produce relatively low-resolution images, making it difficult to use face recognition techniques for person identification. Therefore, an algorithm is proposed for person identification in CCTV camera images based on the clothing. Whenever a person is authenticated at the main entrance of a building, the clothing feature of that person is extracted and added to the database. Using a given image, the clothing area is detected using background subtraction and skin color detection techniques. The clothing feature vector is then composed of textural and color features of the clothing region, where the textural feature is extracted based on a local edge histogram, while the color feature is extracted using octree-based quantization of a color map. When given a query image, the person can then be identified by finding the most similar clothing feature from the database, where the Euclidean distance is used as the similarity measure. Experimental results show an 80% success rate for person identification with the proposed algorithm, and only a 43% success rate when using face recognition.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.7
• /
• pp.753-758
• /
• 2010

In this paper we propose an efficient marker tracking system that exploits IR and web cameras. The proposed method solves the marker swap problem and allows for fast and responsive marker tracking. We use color information gathered from the IR reflector to assign a unique identification to each marker. We can locate each marker withthe IR camera and also identify the marker uniquely by using color information provided by the web camera. The experiment results show that marker swapping can be eliminated effectively. Furthermore, our approach allows for faster and more responsive marker tracking.