• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.6
• /
• pp.1111-1123
• /
• 2023

In recent years, as generative models have developed, research that threatens them has also been actively conducted. We propose a new membership inference attack against text-to-image model. Existing membership inference attacks on Text-to-Image models produced a single image as captions of query images. On the other hand, this paper uses personalized embedding in query images through Textual Inversion. And we propose a membership inference attack that effectively generates multiple images as a method of generating Adversarial Prompt. In addition, the membership inference attack is tested for the first time on the Stable Diffusion model, which is attracting attention among the Text-to-Image models, and achieve an accuracy of up to 1.00.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.33 no.2
• /
• pp.18-22
• /
• 2010

The purpose of this study was to investigated correlation between personal aggression and skin conductance level during watching attack image. Twenty three male ($21.4\pm1.8$ years) college students participated in this experiment. A personal aggression of each subject measured by questionnaire. The experimental procedure consisted of four phases, i.e., rest state (15 min), control image 1 (2 min. 14 sec), aggression image (50 sec), and control image 2 (2 min. 14 sec). Control image 1 and 2 consisted of sea, mountain, and valley scenary. Aggression image used scenes of the violence movie. Skin Conductance Level (SCL) of electrothermal activity was measured during watching the images. The SCL was greater during aggression image than during control image 1 and 2. A negative correlation was found between aggressive personality and change rate of SCL during watching aggression image compared to control image 1. This results suggests that aggression image was accompanied by the higher activation of Sympathetic Nervous System (SNS). Also, the higher aggression scores, an increasing rate of SNS activation was become smaller during watching aggression image.

• Tribology and Lubricants
• /
• v.23 no.6
• /
• pp.301-305
• /
• 2007

The wear particle analysis has been known as very effective method to foreknow and decide a moving situation and a damage of machine parts by using the digital computer image processing. But it was not laid down and trusted to calculate shape parameters of wear particle and wear volume. In order to apply image processing method in the foreknowledge and decision of lubricated condition, it needs to verify the reliability of the calculated data by the image processing and to lay down the number of images and the amount of wear particle in one image. In this study, the lubricated friction experiment was carried out in order to establish the optimum image capture with the SM45C specimen under experiment condition. The wear particle data were calculated differently according to the number of image and the amount of wear particle in one image.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1140-1145
• /
• 2003

Image normalization is one of the important areas in pattern recognition. Also, log-polar images are useful in the sense that their image data size is reduced dramatically comparing with conventional images and it is possible to develop faster pattern recognition algorithms. Especially, the log-polar image is very similar with the structure of human eyes. However, there are almost no researches on pattern recognition using the log-polar images while a number of researches on visual tracking have been executed. We propose an image normalization technique of log-polar images using momentums applicable for affine-invariant pattern recognition. We handle basic distortions of an image including translation, rotation, scaling, and skew of a log-polar image. The algorithm is experimented in a PC-based real-time vision system successfully.

• Journal of Korea Multimedia Society
• /
• v.21 no.2
• /
• pp.158-165
• /
• 2018

Since a large amount of multimedia image has dramatically increased, it is important to search semantically relevant image. Thus, several semantic image annotation methods using RDF(Resource Description Framework) model in mobile environment are introduced. Earlier studies on annotating image semantically focused on both the image tag and the context-aware information such as temporal and spatial data. However, in order to fully express their semantics of image, we need more annotations which are described in RDF model. In this paper, we propose an annotation method inferencing with RDFS entailment rules and user defined rules. Our approach implemented in Moment system shows that it can more fully represent the semantics of image with more annotation triples.

• Journal of the Korean Graphic Arts Communication Society
• /
• v.22 no.2
• /
• pp.163-178
• /
• 2004

In this study, the CIE RGB color space which was one of the most popular device-dependent application program in digital image processing was adopted to make the profile with the device information. The profile was applied to the digital image of a JPEG file format. The result was compared with the color reproduction of another digital image of a JPEG file format, which was made in the e-sRGB color space that had the color spaces allocated to each reproduced color of an image and device-independent colors. In this way it was investigated which color space was more appropriate for digital image processing for web printing and if the e-sRGB color space was good as a color management tool that didn't depend on a device in processing a digital image for web printing.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2012.05a
• /
• pp.40-42
• /
• 2012

Colorization is a method using computer to add color to a black and white image automatically. The input is a grayscale image and some representative pixels (RPs). The RPs contain the color information for the image, and it indicates each region's color information. Colorization-based coding is a novel way for lossy image compression, it decodes a color image to get grayscale image and extracts RPs from the image. Because RPs decides the region's color and we also want small data size for image compression, form this viewpoint the paper proposes a way to get better and fewer RPs based on watershed segmentation. According to the segmentation result we also improve the original chrominance blending colorization method to save decode time and get better reconstruct image.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1244-1248
• /
• 2005

In this paper, we propose fuzzy c-means (FCM) to solve recognition errors in invariant range image, multi-pose face recognition. Scale, center and pose error problems were solved using geometric transformation. Range image face data was digitized into range image data by using the laser range finder that does not depend on the ambient light source. Then, the digitized range image face data is used as a model to generate multi-pose data. Each pose data size was reduced by linear reduction into the database. The reduced range image face data was transformed to the gradient face model for facial feature image extraction and also for matching using the fuzzy membership adjusted by fuzzy c-means. The proposed method was tested using facial range images from 40 people with normal facial expressions. The output of the detection and recognition system has to be accurate to about 93 percent. Simultaneously, the system must be robust enough to overcome typical image-acquisition problems such as noise, vertical rotated face and range resolution.

• Culinary science and hospitality research
• /
• v.14 no.4
• /
• pp.398-414
• /
• 2008

The purpose of this study is to analyze the effect of restaurant atmosphere on its image and customers' emotional responses and behavior. The results of this study indicated that perceived restaurant atmospheres had a significant effect on customers' emotional responses, and these emotional responses greatly influenced the image of a restaurant. Especially, the ambient and cleanliness factors of restaurant atmosphere influenced a restaurant image, and the positive image from those factors had a significant effect on customer behavior. The design and human factors of restaurant atmosphere influenced customer behavior, and the positive image from those factors had a significant effect on customer behavior. Finally, it was verified that the restaurant atmospheric factors affected its image and customers' emotional responses and behavior. Moreover, the better the restaurant atmospheric factors(design, ambient, cleanliness, humanity) are, the better customers' emotional responses and image are, thereby increasing customers' revisiting and word-of-mouth intention.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.36 no.9
• /
• pp.952-965
• /
• 2012

This study verifies the constituents of the professional image by a quantitative method that follows previous qualitative work to clarify the conceptual structure of the professional image for appearance management in the workplace. This study used on-line and off-line data from a positive sampling that involved 1,056 male and female workers engaged in 10 occupational classes. The results of the study were as follows: First, the constituents of a professional image include openness, leadership, harmonious relationship, and financial power, all of which demonstrated a high interrelationship. Second, there are significant differences in favorable factors according to the occupational category. It is important to strategically manage the professional image in consideration of effective image factors and related appearance attributes.