• Journal of Information Processing Systems
• /
• v.19 no.3
• /
• pp.289-301
• /
• 2023

Due to the development and dissemination of modern technology, anyone can easily communicate using services such as social network service (SNS) through a personal computer (PC) or smartphone. The development of these technologies has caused many beneficial effects. At the same time, bad effects also occurred, one of which was the spam problem. Spam refers to unwanted or rejected information received by unspecified users. The continuous exposure of such information to service users creates inconvenience in the user's use of the service, and if filtering is not performed correctly, the quality of service deteriorates. Recently, spammers are creating more malicious spam by distorting the image of spam text so that optical character recognition (OCR)-based spam filters cannot easily detect it. Fortunately, the level of transformation of image spam circulated on social media is not serious yet. However, in the mail system, spammers (the person who sends spam) showed various modifications to the spam image for neutralizing OCR, and therefore, the same situation can happen with spam images on social media. Spammers have been shown to interfere with OCR reading through geometric transformations such as image distortion, noise addition, and blurring. Various techniques have been studied to filter image spam, but at the same time, methods of interfering with image spam identification using obfuscated images are also continuously developing. In this paper, we propose a deep learning-based spam image detection model to improve the existing OCR-based spam image detection performance and compensate for vulnerabilities. The proposed model extracts text features and image features from the image using four sub-models. First, the OCR-based text model extracts the text-related features, whether the image contains spam words, and the word embedding vector from the input image. Then, the convolution neural network-based image model extracts image obfuscation and image feature vectors from the input image. The extracted feature is determined whether it is a spam image by the final spam image classifier. As a result of evaluating the F1-score of the proposed model, the performance was about 14 points higher than the OCR-based spam image detection performance.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.6
• /
• pp.230-245
• /
• 2023

The importance of evaluating the safety of Automated Vehicles (AV) is increasing with the advances in autonomous driving technology. Accordingly, an evaluation scenario that defines in advance the situations AV may face while driving is being used to conduct efficient stability evaluation. On the other hand, the single scenarios currently used in conventional evaluations address limited situations within short segments. As a result, there are limitations in evaluating continuous situations that occur on real roads. Therefore, this study developed a set of multiple scenarios that allow for continuous evaluation across entire sections of roads with diverse geometric structures to assess the safety of AV. In particular, the conditions for connecting individual scenarios were defined, and a methodology was proposed for developing concrete multiple scenarios based on the scenario evaluation procedure of the PEGASUS project. Furthermore, a simulation was performed to validate the practicality of these multiple scenarios.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.1
• /
• pp.192-210
• /
• 2024

Most frequency-domain remote sensing image watermarking algorithms embed watermarks at random locations, which have negative impact on the watermark invisibility. In this study, we propose an adaptive watermarking scheme for remote sensing images that considers the information complexity to select where to embed watermarks to improve watermark invisibility without affecting algorithm robustness. The scheme converts remote sensing images from RGB to YCbCr color space, performs two-level DWT on luminance Y, and selects the high frequency coefficient of the low frequency component (HH^Y₂) as the watermark embedding domain. To achieve adaptive embedding, HH^Y₂ is divided into several 8*8 blocks, the entropy of each sub-block is calculated, and the block with the maximum entropy is chosen as the watermark embedding location. During embedding phase, the watermark image is also decomposed by two-level DWT, and the resulting high frequency coefficient (HH^W₂) is then embedded into the block with maximum entropy using α- blending. The experimental results show that the watermarked remote sensing images have high fidelity, indicating good invisibility. Under varying degrees of geometric, cropping, filtering, and noise attacks, the proposed watermarking can always extract high identifiable watermark images. Moreover, it is extremely stable and impervious to attack intensity interference.

• Journal of Korean Society of Steel Construction
• /
• v.20 no.5
• /
• pp.633-644
• /
• 2008

The structural framework design uses high-strength bolts and welding in column splices. However, for the column under high compression, the number of the required high-strength bolts can be excessive and the increase of welding results in difficulty of quality inspection, the transformation of the structural steels, and the increase of erection time. According to the AISC criteria, when columns have bearing plates, or they are finished to bear at splices, there shall be sufficient connections to hold all parts securely in place. The Korean standard sets the maximum 25% of the load as criteria. Using direct contact makes it possible to transfer all compressive force through it. The objective of this study is to examine the generally applied stress path mechanism of welded or bolted columns and to verify the bending moment and compression transfer mechanism of the column splice according to metal touch precision. For this study,22 specimens of various geometric shapes were constructed according to the change in the variables for each column splice type, which includes the splice method, gap width, gap axis, presence or absence of splice material, and connector type. The results show that the application of each splice can be improved through the examination of the stress path mechanism upon metal contact. Moreover, the revision of the relative local code on direct contact needs to be reviewed properly for the economics and efficiency of the splices.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.4
• /
• pp.403-408
• /
• 2003

A general meaning of caricaturing is that a representation, especially pictorial or literary, in which the subject's distinctive features or peculiarities are deliberately exaggerated to produce a comic or grotesque effect. In other words, a caricature is defined as a rough sketch(dessin) which is made by detecting features from human face and exaggerating or warping those. There have been developed many methods which can make a caricature image from human face using computer. In this paper, we propose a new caricaturing system. The system uses a real-time image or supplied image as an input image and deals with it on four processing steps and then creates a caricatured image finally. The four Processing steps are like that. The first step is detecting a face from input image. The second step is extracting special coordinate values as facial geometric information. The third step is deforming the face image using local warping method and the coordinate values acquired in the second step. In fourth step, the system transforms the deformed image into the better improved edge image using a fuzzy Sobel method and then creates a caricatured image finally. In this paper , we can realize a caricaturing system which is simpler than any other exiting systems in ways that create a caricatured image and does not need complex algorithms using many image processing methods like image recognition, transformation and edge detection.

• International Journal of Costume and Fashion
• /
• v.13 no.1
• /
• pp.23-34
• /
• 2013

The purpose of this study is to better understand the development and characteristics of knitwear fashion design by examining the transformation process of the modern knits. The subjects of the study are Missoni, Sonia Rykiel, and Azzedine Alaia, designers who are world-renowned knit designers, and the expressive techniques in their designs will be evaluated. The study also intends to analyze the aesthetic value of each designer's style through their product's silhouette, colors, and knitting techniques. On the basis of the analysis, we hope to research the factors in the designing process that will allow knits, which were made for practical purposes, to be valued as a luxury fashion item, and with the results, show the potential for knits in expanding its domain in fashion to become a more luxurious, creative fashion item. The characteristic comparison of the designers is as follows: First, in the case of colors, Missoni shows its distinct identity through a balance of splashy colors as well as nature-inspired color composition and balance. And, only with color use, is also able to express perspective, form composition, and rhythm. Sonia Rykiel designs are composed of black backgrounds with strong primary colors that are contrasted with one-point or stripes to express a light, urban image. Alaia emphasizes femininity by the use of black and white colors, which show modernity, in combination with neutral skin-toned colors, such as beige and gray. So, in other words, Missoni and Sonia Rykiel mixed colors for visual interconnectivity, while Alaia expressed femininity through the use of an achromatic color. Second, in the case of knitting techniques, Missoni uses the jacquard technique to make complex patterns that show balance of colors and patterns such as zigzag, stripe, geometries, and titan check, which are geometric, abstract, and symmetric. Sonia Rykiel who uses stripes as her trademark, most often utilizes the intarsia technique, which is expressed through one-point. Alaia combines diverse techniques, such as the Skashi weaving, by using computerized knitting. Third, as for silhouettes, Missoni eliminated exaggerated details in order to emphasize the flashy colors and delicate patterns and weavings of its designs, and this resulted in simplistic and relaxed silhouettes. Sonia Rykiel took advantage of the elasticity that the knit offers to get a tight silhouette, and in turn, emphasized the female sensuality. Alaia used curvilinear cuts that emphasized the womanly curves and gained an image considered soft and feminine.

• Korean Institute of Interior Design Journal
• /
• v.16 no.2 s.61
• /
• pp.262-269
• /
• 2007

The blur phenomenon obscuring the boundary between the field of designers and that of users may be the key paradigm in the 21st century. However, we observed a number of chair design cases that could be considered as the results of blur pheonomenon in the furniture design field from mid 1960s. The backgrounds include the repulsion against the uniform functionalism, deliberation on the life in the future and the development of plastic materials and their processing methods. Under such backgrounds, the designers pursued the new and futuristic furniture design. In that process, what is about the "freedom" that the consumers as well as the designers should have in using the furniture was the important concept. This concept enabled the creation of chair design inducing the participation of consumers. They created various kinds of shapes, functions and structures that the consumers became interested in as if they had fun with toy blocks by mainly using the new material "plastic". In a formative aspect, the entire shape is classified into the organic shape and geometric shape. The unit types are divided into two kinds; type that the unit of simple shape is repeated only with size difference and irregular combination type of the units comprised of more than two shapes. In the functional aspect, some cases showed the transformation and expansion of the function more variously. Other cases changed the function of chairs to tables, cabinets, or objects. In the structural aspect, on the basis of the method assembling each unit, one method is to assemble using the hardware and the other is to assemble only with intrinsic units of chair. The chair design created by the blur phenomenon between the designers and the users as described above causes the blur phenomenon between the furniture and the space where the furniture is installed. Accordingly, it is expanding the furniture design sphere including the case that the furniture is not selected as the rifle article depending on the characteristics of interior space but it becomes the element leading the characteristics of space. This study aims to estimate the change of interior space and the furniture that my cause the blur phenomenon by examining the cases above appropriate for the paradigm of the 21st century. Furthermore, this study will enable the discussion oil the directions of future furniture design based on its results.

• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.353-360
• /
• 2006

This paper presents a robust algorithm for segmenting a vehicle license plate area from a road image. We consider the features of license plates in three aspects : 1) edges due to the characters in the plate, 2) colors in the plate, and 3) geometric properties of the plate. In the preprocessing step, we compute the thresholds based on each feature to decide whether a pixel is inside a plate or not. A statistical approach is applied to the sample images to compute the thresholds. For a given road image, our algorithm binarizes it by using the thresholds. Then, we select three candidate regions to be a plate by searching the binary image with a moving window. The plate area is selected among the candidates with simple heuristics. This algorithm robustly detects the plate against the transformation or the difference of color intensity of the plate in the input image. Moreover, the preprocessing step requires only a small number of sample images for the statistical processing. The experimental results show that the algorithm has 97.8% of successful segmentation of the plate from 228 input images. Our prototype implementation shows average processing time of 0.676 seconds per image for a set of $1280{\times}960$ images, executed on a 3GHz Pentium4 PC with 512M byte memory.

• Journal of Broadcast Engineering
• /
• v.17 no.2
• /
• pp.305-315
• /
• 2012

Color correction between two or multiple images is very crucial for the development of subsequent algorithms and stereoscopic 3D camera system. Even though various color correction methods are proposed recently, there are few methods for measuring the performance of these methods. In addition, when two images have view variation by camera positions, previous methods for the performance measurement may not be appropriate. In this paper, we propose a method of measuring color difference between corresponding images for color correction. This method finds matching points that have the same colors between two scenes to consider the view variation by correspondence searches. Then, we calculate statistics from neighbor regions of these matching points to measure color difference. From this approach, we can consider misalignment of corresponding points contrary to conventional geometric transformation by a single homography. To handle the case that matching points cannot cover the whole regions, we calculate statistics of color difference from the whole image regions. Finally, the color difference is computed by the weighted summation between correspondence based and the whole region based approaches. This weight is determined by calculating the ratio of occupying regions by correspondence based color comparison.

• Journal of the Korean Society of Costume
• /
• v.32
• /
• pp.163-182
• /
• 1997

The purpose of this study was intended to analyze artistic formativeness represented in the modern fashion design materials. Nowadays the modern fashion design materials is characterized by variety. The fashion materials the most important of fashion is called a softwear in textile industry and emerged as a new field. Fashion design also escaped from the tra-ditional restraint and extended to pursue lib-eral clothes and the designer's creative inten-tion has resulted in conceptual and conven-tional alteration as a new mode of plastic ex-preseeion. As a results of analysis of the formative fea-ture of Art style represented in the modern fashion design materials. First Surrealism had been searching for a new way of confronting a social and rtistic environment that was stifling and repugnant to them. Accordingly the wide applicaytion of the various object due to the thought of Sur-realism through the modern fashion materials brought the diversification and individua-lization of the modern fashion design. Second Pop Art that is made modern mech-anic culture and commercialism brought the great transformation in the history of Art out of the existing style and the sense of ex-pression. And the plastic characteristics of Pop Art that has a gravity as modern fashion materials on a them of the elements of popular consumer's society. That is the common and cheap objects were introduced into fashion materials itself or pat-tern. Third Minimalism is a trend in art att-empting to seek essence of the object by presenting simple and disciplined expressions by minimal formative means. The features of external form are simplicity clarity unrelated composition and symmetrical structure. Mini-malism was a quest for basic elements repre-senting the fundamental esthetic values of art. The minimal expression in modern fashion materials mean fabrics with simple surface and is contained using simple geometric pattern or utilizing textiles without any patterns. Fourth Eroticism is a kind of psychological revolution in the development of human civilization and is deeply rooted in the cultural tradition of myth religion customs and art. So Eroticism must be distinguished from a mere animal reproduction. These erotic char-acteristics were holded the meanings of sexu-ality through the modern fashion materials. Especially it was expressed the sexual part of body was nakedly showed through trans-parent materials or semitransparent like metalic and opaque materials. Recently the various kinds of new materials such as paper vinyle plastic metal as well as human body were applied to new fashion de-sign. First of all the new materials will give modern fashion designers stimuli and inspi-ration. It can also express values of moderners to despise materialism and uniformed modern society and to recover humanity and self-actualization.