• Journal of information and communication convergence engineering
• /
• v.11 no.1
• /
• pp.62-68
• /
• 2013

This paper proposes a method for identification of harmful video images based on the degree of harmfulness in the video content. To extract harmful candidate frames from the video effectively, we used a video color extraction method applying a projection map. The procedure for identifying the harmful video has five steps, first, extract the I-frames from the video and map them onto projection map. Next, calculate the similarity and select the potentially harmful, then identify the harmful images by comparing the similarity measurement value. The method estimates similarity between the extracted frames and normative images using the critical value of the projection map. Based on our experimental test, we propose how the harmful candidate frames are extracted and compared with normative images. The various experimental data proved that the image identification method based on the 2-dimensional projection map is superior to using the color histogram technique in harmful image detection performance.

• Journal of Korea Multimedia Society
• /
• v.24 no.12
• /
• pp.1624-1631
• /
• 2021

With the continued development of image processing technology, we live in a time when it is difficult to visually discriminate processed (or tampered) images from real images. However, as the risk of fake images being misused for crime increases, the importance of image forensic science for identifying fake images is emerging. Currently, various deep learning-based identifiers have been studied, but there are still many problems to be used in real situations. Due to the inherent characteristics of deep learning that strongly relies on given training data, it is very vulnerable to evaluating data that has never been viewed. Therefore, we try to find a way to improve generalization ability of deep learning-based fake image identifiers. First, images with various contents were added to the training dataset to resolve the over-fitting problem that the identifier can only classify real and fake images with specific contents but fails for those with other contents. Next, color spaces other than RGB were exploited. That is, fake image identification was attempted on color spaces not considered when creating fake images, such as HSV and YCbCr. Finally, dropout, which is commonly used for generalization of neural networks, was used. Through experimental results, it has been confirmed that the color space conversion to HSV is the best solution and its combination with the approach of increasing the training dataset significantly can greatly improve the accuracy and generalization ability of deep learning-based identifiers in identifying fake images that have never been seen before.

• Journal of The Korean Association For Science Education
• /
• v.14 no.2
• /
• pp.236-240
• /
• 1994

Recently computers are transforming our classroom by means of initiating and expanding teaching and learning. Lloyd (1989) indicates that computers show great promise in a way augmenting the classroom instructional process under the guidance of the teacher. In this paper computer program for mineral identification (called CPMI) is introduced. This program is is to provide a short list of 26 minerals. These mineras are classified using some properties for mineral identification that is color, streak, hardness, specific gravity, luster, and crystal form. Mineral properties can be divided into two groups for operating this program: (1) properties with numeric values, that is hardness and specific gravity; (2) properties whith a single word, that is color, streak, luster, and crystal form.

• Korean Institute of Interior Design Journal
• /
• no.31
• /
• pp.64-70
• /
• 2002

One of the main motivations of this research process is to develop an adaptable VR model whose color can be changed according to the emotional information of user. This paper addresses how to define color scheme and combine colors with harmony. The adaptable color of the VR model consists of three processes: emotional keyword identification, the color combination and the VR model adaptation processes. We have used the biorhythm to derive the emotional keyword which is used to find the color harmony scheme. The color harmony scheme provides information for the color combination of the VR model. Finally, we have obtained the VR model which color has been changed using the identified color schema.

• Journal of the Korean Society of Costume
• /
• v.49
• /
• pp.155-172
• /
• 1999

The purpose of this study was to investigate the effect of children's personality traits and parental child-rearing attitudes on clothing attitudes and color evaluation of preschool children. The subjects for this study consisted of 360 five-year-old children who were attending a preschool and their parents in Cheju Island Korea. Employed mothers had significantly higher score on love acceptance attitude than unemployed mothers did. Female children had more conservative attitude on clothing sex-role than male children did There were no significant gender differences in parental child-rearing attitudes. There were significant relationships between gender and preferred clothing colors. Male children were more likely to prefer blue red, green, and prussian blue for the colors of clothing than were female children while female children liked pink yellow and orange more than male children. Boys selected blue and girls selected pink as the most preferred clothing color. Overall preschool children chose red as the most preferred color black as the most disliked color. The children's sex identification by clothing color was highly consistent with the conservative attitude of adults for all colors. That is preschool children identified pink red and yellow with female color while prussian blue blue and green with male color. Clothing interest of boys was influenced by the mother's state of employment and academic trait. The boys high in academic trait and whose mothers did not have job were high in clothing interest. Clothing management of boys was influenced by emotionality and love acceptance rearing Ttitude. Clothing independednce of boys was influenced by authority control rearing attitude Clothing sex-role of boys was influenced by familism trait. The boys high in familism trait had open-hearted attitude in clothing sex-role. Clothing interest of girls was influenced by academic trait clothing management by sociality clothing independence by emotionality and clothing satisfaction by familism trait. Therefore the more positive personality children had the higher clothing interest and the more desirable clothing attitudes they had.

• International Journal of Computer Science & Network Security
• /
• v.23 no.3
• /
• pp.187-192
• /
• 2023

With development of information technology and necessity for high security, using different identification methods has become very important. Each biometric feature has its own advantages and disadvantages and choosing each of them depends on our usage. Retinal scanning is a bio scale method for identification. The retina is composed of vessels and optical disk. The vessels distribution pattern is one the remarkable retinal identification methods. In this paper, a new approach is presented for identification via retinal images using LBP and hog methods. In the proposed method, it will be tried to separate the retinal vessels accurately via machine vision techniques which will have good sustainability in rotation and size change. HOG-based or LBP-based methods or their combination can be used for separation and also HSV color space can be used too. Having extracted the features, the similarity criteria can be used for identification. The implementation of proposed method and its comparison with one of the newly-presented methods in this area shows better performance of the proposed method.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.7
• /
• pp.1040-1046
• /
• 2015

This paper introduces GP(Genetic Programming) based color detection model for an object detection of humanoid robot vision. Existing color detection methods have used linear/nonlinear transformation of RGB color-model. However, most of cases have difficulties to classify colors satisfactory because of interference of among color channels and susceptibility for illumination variation. Especially, they are outstanding in degraded images from robot vision. To solve these problems, we propose illumination robust and non-parametric multi-colors detection model using evolution of GP. The proposed method is compared to the existing color-models for various environments in robot vision for real humanoid Nao.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.7
• /
• pp.1031-1039
• /
• 2015

Present guided missiles are equipped with infrared seeker to find the infrared sources radiating from target plane and then chase, which results in an improvement of the hitting success rate when in striking target objects. To interrupt the chases from the guided missile, the target plane spreads the flare, avoiding the missile attracts. Our research is to develop a 2-color infrared identification technique to discern the flare and real thermal source from target plane. Considering flare radiation properties and EM atmosphere transmission rates, two channels were selected, in which main channel (MC) was in a range of 3.7 μm∼4.8 μm and auxiliary channel (AC) in 1.7 μm∼2.3 μm. A 2500K heat source was used for an artificial flare source, while a 570K heat source was utilized for airplane infrared source in experimental testing. Two infrared sensors detectable only at each chanel were employed in order to measure the voltage ratio from two channels, identifying the flare and real target plane via comparison the voltage ratio. Several experimental conditions were imported in order to prove that our proposed 2-color infrared identification technique is very efficient way to discern heat sources from aircraft and flare, demonstrating that our proposed technique is very promising means for our force’s InfraRed Counter Counter Measure (IRCCM) in order to countermeasure opposite force’s InfraRed Counter Measures (IRCM).

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2005.11a
• /
• pp.153-156
• /
• 2005

Skin region detection in images is an important process in many computer vision applications targeting humans such as hand gesture recognition and face identification. It usually starts at a pixel-level, and involves a pre-process of color spae transformation followed by a classification process. A color space transformation is assumed to increase separability between skin classes and other classes, to increase similarity among different skin tones, and to bring a robust performance under varying imaging conditions, without any complicated analysis. In this paper, we examine if the color space transformation actually brings those benefits to the problem of skin region detection on a set of human hand images with different postures, backgrounds, people, and illuminations. Our experimental results indicate that color space transfomation affects the skin detection performance. Although the performance depends on camera and surround conditions, normalized [R, G, B] color space may be a good choice in general.

• The Korea Journal of Herbology
• /
• v.34 no.3
• /
• pp.19-30
• /
• 2019

Objectives : This study is to propose the identification keys based on stereoscopic examination of 8 seed herbs in 2 categories (Phyllolobobii Semen (PS) with 4 Astragali Semen (AS), and 2 Lepidii seu Descurainiae Semen (LDS) with 1 Drabae Semen (DS)) which have difficulties in discrimination with visual observation. Methods : We reviewed the description of original plants and their medicinal parts from the literature. The original plants were collected, identified, confirmed as specimens, and compared to the samples distributed in the market. The first identification was made by visual observation, and insufficient points were supplemented by stereoscopic observation. Identification criteria were set by considering morphological characteristics of authentic herbs, percentage of adulterants, and distinction between authentic herbs and adulterants. Results : The original plants of PS and AS could be distinguished by upright or lying form of stem, color of flowers, number of leaflets, and presence of hair of fruits. LDS and DS could be distinguished by leaf arrangement on stem: radical or cauline, whole plants size, leaf division, color of flowers, and shape of fruits. The herbal medicines of PS and AS could be distinguished by seed surface pattern, size, and hardness. LDS and DS could be distinguished by size, shape, viscosity when chewed, and degree of mucous layer formation when soaked in water. Conclusions : This study suggests the identification keys of original plants and herbal medicines. Especially, since fine seed herbs are difficult to distinguish by visual observation, the stereoscope should be applied to the discrimination.