• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.5
• /
• pp.360-366
• /
• 2022

This paper presents a AI model structure for restoring Korean traditional palace photographs, which remain only black-and-white photographs, to color photographs using Pix2Pix, one of the adversarial generative neural network techniques. Pix2Pix consists of a combination of a synthetic image generator model and a discriminator model that determines whether a synthetic image is real or fake. This paper deals with an artificial intelligence model by adjusting a receptive field of the discriminator, and analyzes the results by considering the characteristics of the ancient palace photograph. The receptive field of Pix2Pix, which is used to restore black-and-white photographs, was commonly used in a fixed size, but a fixed size of receptive field is not suitable for a photograph which consisting with various change in an image. This paper observed the result of changing the size of the existing fixed a receptive field to identify the proper size of the discriminator that could reflect the characteristics of ancient palaces. In this experiment, the receptive field of the discriminator was adjusted based on the prepared ancient palace photos. This paper measure a loss of the model according to the change in a receptive field of the discriminator and check the results of restored photos using a well trained AI model from experiments.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.6
• /
• pp.13-23
• /
• 2022

In this paper, we propose a detailed component image classification algorithm by fashion item for unstructured data retrieval in the fashion field. Due to the COVID-19 environment, AI-based online shopping malls are increasing recently. However, there is a limit to accurate unstructured data search with existing keyword search and personalized style recommendations based on user surfing behavior. In this study, pre-processing using Mask R-CNN was conducted using images crawled from online shopping sites and then classified components for each fashion item through CNN. We obtain the accuaracy for collar of the shirt's as 93.28%, the pattern of the shirt as 98.10%, the 3 classese fit of the jeans as 91.73%, And, we further obtained one for the 4 classes fit of jeans as 81.59% and the color of the jeans as 93.91%. At the results for the decorated items, we also obtained the accuract of the washing of the jeans as 91.20% and the demage of jeans accuaracy as 92.96%.

• Journal of Intelligence and Information Systems
• /
• v.18 no.1
• /
• pp.1-21
• /
• 2012

In recent years, mobile phone has experienced an extremely fast evolution. It is equipped with high-quality color displays, high resolution cameras, and real-time accelerated 3D graphics. In addition, some other features are includes GPS sensor and Digital Compass, etc. This evolution advent significantly helps the application developers to use the power of smart-phones, to create a rich environment that offers a wide range of services and exciting possibilities. To date mobile AR in outdoor research there are many popular location-based AR services, such Layar and Wikitude. These systems have big limitation the AR contents hardly overlaid on the real target. Another research is context-based AR services using image recognition and tracking. The AR contents are precisely overlaid on the real target. But the real-time performance is restricted by the retrieval time and hardly implement in large scale area. In our work, we exploit to combine advantages of location-based AR with context-based AR. The system can easily find out surrounding landmarks first and then do the recognition and tracking with them. The proposed system mainly consists of two major parts-landmark browsing module and annotation module. In landmark browsing module, user can view an augmented virtual information (information media), such as text, picture and video on their smart-phone viewfinder, when they pointing out their smart-phone to a certain building or landmark. For this, landmark recognition technique is applied in this work. SURF point-based features are used in the matching process due to their robustness. To ensure the image retrieval and matching processes is fast enough for real time tracking, we exploit the contextual device (GPS and digital compass) information. This is necessary to select the nearest and pointed orientation landmarks from the database. The queried image is only matched with this selected data. Therefore, the speed for matching will be significantly increased. Secondly is the annotation module. Instead of viewing only the augmented information media, user can create virtual annotation based on linked data. Having to know a full knowledge about the landmark, are not necessary required. They can simply look for the appropriate topic by searching it with a keyword in linked data. With this, it helps the system to find out target URI in order to generate correct AR contents. On the other hand, in order to recognize target landmarks, images of selected building or landmark are captured from different angle and distance. This procedure looks like a similar processing of building a connection between the real building and the virtual information existed in the Linked Open Data. In our experiments, search range in the database is reduced by clustering images into groups according to their coordinates. A Grid-base clustering method and user location information are used to restrict the retrieval range. Comparing the existed research using cluster and GPS information the retrieval time is around 70~80ms. Experiment results show our approach the retrieval time reduces to around 18~20ms in average. Therefore the totally processing time is reduced from 490~540ms to 438~480ms. The performance improvement will be more obvious when the database growing. It demonstrates the proposed system is efficient and robust in many cases.

• The KIPS Transactions:PartB
• /
• v.14B no.4
• /
• pp.311-320
• /
• 2007

This paper presents vision-based 3D facial expression animation technique and system which provide the robust 3D head pose estimation and real-time facial expression control. Many researches of 3D face animation have been done for the facial expression control itself rather than focusing on 3D head motion tracking. However, the head motion tracking is one of critical issues to be solved for developing realistic facial animation. In this research, we developed an integrated animation system that includes 3D head motion tracking and facial expression control at the same time. The proposed system consists of three major phases: face detection, 3D head motion tracking, and facial expression control. For face detection, with the non-parametric HT skin color model and template matching, we can detect the facial region efficiently from video frame. For 3D head motion tracking, we exploit the cylindrical head model that is projected to the initial head motion template. Given an initial reference template of the face image and the corresponding head motion, the cylindrical head model is created and the foil head motion is traced based on the optical flow method. For the facial expression cloning we utilize the feature-based method, The major facial feature points are detected by the geometry of information of the face with template matching and traced by optical flow. Since the locations of varying feature points are composed of head motion and facial expression information, the animation parameters which describe the variation of the facial features are acquired from geometrically transformed frontal head pose image. Finally, the facial expression cloning is done by two fitting process. The control points of the 3D model are varied applying the animation parameters to the face model, and the non-feature points around the control points are changed by use of Radial Basis Function(RBF). From the experiment, we can prove that the developed vision-based animation system can create realistic facial animation with robust head pose estimation and facial variation from input video image.

• Korea Science and Art Forum
• /
• v.19
• /
• pp.281-292
• /
• 2015

For this study, I conducted a survey investigating current situation, user preference, and field experiment. Hospitals utilizing digital sign systems at least five years were selected, which are connected with visual elements (layout, typo, color) used in waiting areas and elements of the systems (time, video time line). The results obtained from the field survey showed that digital sign systems used the color of typo and background contrasted to one another to increase explicitness and to ensure easy understanding of contents. In addition, the Gothic typo with relatively high legibility was adopted. Time and video timeline, which characterize digital sign systems, showed the advertising screens of the hospitals and the guidance of medical treatment at regular intervals. Moreover, survey results on user satisfaction showed that a majority of respondents indicated they had difficulty in understanding digital information conveyed from digital sign systems due to time setting for rotational speed or the small size of typo although most of the users had previous experience with digital sign systems. The highest proportion of respondents (n=86, 86%) answered that information related to medical departments was what they sought most frequently and that this kind of information should be importantly considered in digital sign systems. For the experiment, new samples with restructured contents of current digital sign systems were created and tested while keeping its design unchanged as well as applying these new samples. Study participants were in their 20s through 50s. When the size of typo was larger under the same conditions for all age groups, study participants found the desired information approximately 3.5 seconds faster. In addition, those in their 20-30s and 40-50s showed the time difference of 4.7 seconds for small typo and 6 seconds for large typo, which suggested that there was a difference by age in the amount of time taken in the experiment to find the desired information from the rotating digital sign system regardless of age and the size of typo.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.6 s.312
• /
• pp.20-27
• /
• 2006

Multi-level thresholding is a method that is widely used in image segmentation. However most of the existing methods are not suited to be directly used in applicable fields and moreover expanded until a step of image segmentation. This paper proposes region-based multi-level thresholding as an image segmentation method. At first we classify pixels of each color channel to two clusters by using EWFCM(Entropy-based Weighted Fuzzy C-Means) algorithm that is an improved FCM algorithm with spatial information between pixels. To obtain better segmentation results, a reduction of clusters is then performed by a region-based reclassification step based on a similarity between regions existing in a cluster and the other clusters. The clusters are created using the classification information of pixels according to color channel. We finally perform a region merging by Bayesian algorithm based on Kullback-Leibler distance between a region and the neighboring regions as a post-processing method as many regions still exist in image. Experiments show that region-based multi-level thresholding is superior to cluster-, pixel-based multi-level thresholding, and the existing mettled. And much better segmentation results are obtained by the post-processing method.

• Journal of the Korea Computer Industry Society
• /
• v.5 no.9
• /
• pp.1101-1110
• /
• 2004

In the first quarter of 2004, there were about 1 billion 348 million mobile phone users worldwide with a penetration rate of only 29%. Korea ranks among the highest in the use of mobile communication, having over 36 million mobile phone subscribers with a mobile phone penetration rate of 75% as of May 2004. Since the introduction of wireless Internet service in May 1999, the number of subscribers rose to 34.5 million with 95.3% of the total mobile phone subscribers using wireless Internet services in May 2004, largely due to continued investments by telecommunication service providers, improvement of mobile handsets (color and digital camera phones) and implementation of policies on mobile number portability. In the Korean wireless Internet market, there are many user complaints since the service providers are competing with each other through TV commercial sales and phone discounts rather than improving their call quality, services and billing systems. therefore there is a growing need to improve the billing systems through means such as the implementation of reasonable payment plans according to consumer use, development of a wireless Internet billing system that can predict the number of users and establishment of pricing standards for controlled data (head, tail, etc...) as well as menu information by testing the texts. multimedia, video and other types of content provided by the three major mobile communication companies. The purpose of this study is to promote wireless Internet services and protect user rights by proposing a reasonable way to improve the billing systems for wireless Internet services after conducting a comparative analysis of file size and billing data of each of the service providers through a verification test on a packet billing system for wireless Internet services.

• Journal of Korean Society of Transportation
• /
• v.22 no.4 s.75
• /
• pp.97-106
• /
• 2004

It is a Known fact that driving through long tunnel increases possibility of traffic accident because of psychological feeling of insecurity and dispersion of drivers' concentration since driving in narrow and limited space for a longtime. It, therefore, results in raising transportation and environment problems, such as traffic accident difficult to be properly dealt with and ventilation. This study aims at proposing a method of augmenting driving amenity by improving the internal lighting facilities in the tunnel. The study is conducted by investigating internal landscapes of tunnels by lighting colors, which are currently being operated. The Color Planning System (CPS), developed by SHARP Co. Ltd, is exploited for selecting adjective that express the sensitivity image on lighting colors. The CPS is an example that applies to sensitivity of human body for products design development. The CPS takes the following process to define the color : 1) expressing "Pvoduct's Image" as "A Word (adjective)" and 2) referring "A Word" to "Image Scale", and 3) determining the color through this "Image Panel". The study is processed by making a questionnaire using the semantic differential (SD) scale, grasping the consciousness structure of experimental persons through the Factor Analysis, and building a model in which dependent variable is "Degree of Preference" about internal landscape in tunnel using LISREL(LInear Structural RELations).

• Journal of Korea Multimedia Society
• /
• v.15 no.10
• /
• pp.1196-1204
• /
• 2012

In this paper, a series of algorithms are proposed for controlling different kinds of multimedia contents and realizing interact between human and computer by using single input device. Human gesture recognition based on NUI is presented firstly in my paper. Since the image information we get it from camera is not sensitive for further processing, we transform it to YCbCr color space, and then morphological processing algorithm is used to delete unuseful noise. Boundary Energy and depth information is extracted for hand detection. After we receive the image of hand detection, PCA algorithm is used to recognize hand posture, difference image and moment method are used to detect hand centroid and extract trajectory of hand movement. 8 direction codes are defined for quantifying gesture trajectory, so the symbol value will be affirmed. Furthermore, HMM algorithm is used for hand gesture recognition based on the symbol value. According to series of methods we presented, we can control multimedia contents by using human gesture recognition. Through large numbers of experiments, the algorithms we presented have satisfying performance, hand detection rate is up to 94.25%, gesture recognition rate exceed 92.6%, hand posture recognition rate can achieve 85.86%, and face detection rate is up to 89.58%. According to these experiment results, we can control many kinds of multimedia contents on computer effectively, such as video player, MP3, e-book and so on.

• Journal of Korea Multimedia Society
• /
• v.10 no.7
• /
• pp.846-855
• /
• 2007

Significant feature extraction in cancer cell image analysis is an important process for grading cell carcinoma. In this study, we propose a method for 3D quantitative analysis of cell nuclei based upon digital image cytometry. First, we acquired volumetric renal cell carcinoma data for each grade using confocal laser scanning microscopy and segmented cell nuclei employing color features based upon a supervised teaming scheme. For 3D visualization, we used a contour-based method for surface rendering and a 3D texture mapping method for volume rendering. We then defined and extracted the 3D morphological features of cell nuclei. To evaluate what quantitative features of 3D analysis could contribute to diagnostic information, we analyzed the statistical significance of the extracted 3D features in each grade using an analysis of variance (ANOVA). Finally, we compared the 2D with the 3D features of cell nuclei and analyzed the correlations between them. We found statistically significant correlations between nuclear grade and 3D morphological features. The proposed method has potential for use as fundamental research in developing a new nuclear grading system for accurate diagnosis and prediction of prognosis.