• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.10
• /
• pp.323-332
• /
• 2022

As various services using AI technology are being developed, much attention is being paid to AI service production. Recently, AI technology is acknowledged as one of ICT services, a lot of research is being conducted for general-purpose AI service production. In this paper, I describe the research results in terms of systems for AI service production, focusing on the distribution and production of machine learning models, which are the final steps of general machine learning development procedures. Three different Ubuntu systems were built, and experiments were conducted on the system, using data from 2017 validation COCO dataset in combination of different AI models (RFCN, SSD-Mobilenet) and different communication methods (gRPC, REST) to request and perform AI services through Tensorflow serving. Through various experiments, it was found that the type of AI model has a greater influence on AI service inference time than AI machine communication method, and in the case of object detection AI service, the number and complexity of objects in the image are more affected than the file size of the image to be detected. In addition, it was confirmed that if the AI service is performed remotely rather than locally, even if it is a machine with good performance, it takes more time to infer the AI service than if it is performed locally. Through the results of this study, it is expected that system design suitable for service goals, AI model development, and efficient AI service production will be possible.

• Journal of the Korean Crystal Growth and Crystal Technology
• /
• v.32 no.1
• /
• pp.7-11
• /
• 2022

Recently, Hanmi Gemological Institute & Laboratory (HGI) had an opportunity to examine 5 transparent synthetic moissanite. The round brilliants ranged from 0.93 to 0.96 ct and had a colorless, pink, yellow, blue, and red color. Advanced testing results, including Fourier-transform infrared (FTIR) and Raman spectroscopy, identified all the specimens as synthetic moissanite. Under the microscope, all samples except the colorless were confirmed to be a synthetic moissanite coated with a colored film. EDXRF chemical analysis detected very weak X-ray fluorescence peak characteristics of Ca, Ti, and Co in the colored samples. These features were not detected in the colorless sample. Raman spectroscopy investigation was unable to detect the 1332 cm^-1 (produced by sp³ bonding of carbon atoms) or the ~1550 cm^-1 (produced by graphite-related sp² bonding) peak in the colorless sample. The SEM image of the colorless sample showed no indication of a coating. The TEM image of the colorless sample revealed the presence of a 3~8 nm thick layer on the moissanite. Moreover, from the corresponding STEM Z-contrast image combined with the energy-dispersive X-ray spectroscopy (EDX) line profiles and EDX elemental maps, this layer was estimated to be carbon, silicon and oxygen.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.30 no.2
• /
• pp.147-156
• /
• 2024

The sustainable management and enhancement of marine resources are becoming increasingly important issues worldwide. This study was conducted in response to these challenges, focusing on the development and performance comparison of fish detection and classification models as part of a deep learning-based technique for assessing the effectiveness of marine resource enhancement projects initiated by the Korea Fisheries Resources Agency. The aim was to select the optimal model by training various sizes of YOLOv8-Seg models on a fish image dataset and comparing each performance metric. The dataset used for model construction consisted of 36,749 images and label files of 12 different species of fish, with data diversity enhanced through the application of augmentation techniques during training. When training and validating five different YOLOv8-Seg models under identical conditions, the medium-sized YOLOv8m-Seg model showed high learning efficiency and excellent detection and classification performance, with the shortest training time of 13 h and 12 min, an of 0.933, and an inference speed of 9.6 ms. Considering the balance between each performance metric, this was deemed the most efficient model for meeting real-time processing requirements. The use of such real-time fish detection and classification models could enable effective surveys of marine resource enhancement projects, suggesting the need for ongoing performance improvements and further research.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.21 no.1
• /
• pp.45-51
• /
• 2003

Stereo bird's-eyes-view was prepared for 3-dimensional view of various forms of Jecheon city, and 3-dimensional simulation was applied to it so as to show it in moving pictures in spatial. In manufacturing stereo bird's-eyes-view, perspective technology was used in image-making technology, and the basic material images are prepared as fellows: used EOC Images from Arirang-1 satellite, created DEM whose error was optionally geometric corrected after drawn from the contour line of the map on a scale of l/5,000 manufactured by national geography institute as a national standard map, and classified road lines which were manufactured as a road layer vector file of a map on a scale of l/l,000 and then overlay it over the three dimensional image of target area. Especially for the connectivity with address system to be used in new address, an arterial road map on a scale of l/l,000 that had been manufactured to grant new address was used in maximum in road network structure data of city area in this study.

• Journal of KIISE:Databases
• /
• v.32 no.4
• /
• pp.362-371
• /
• 2005

Similarity indexing and searching are well known to be difficult in high-dimensional applications such as multimedia databases. Especially, they become more difficult when multiple features have to be indexed together. In this paper, we propose a novel indexing method called the GB-index that is designed to efficiently handle complex similarity queries as well as relevance feedback in high-dimensional image databases. In order to provide the flexibility in controlling multiple features and query objects, the GB-index treats each dimension independently The efficiency of the GB-index is realized by specialized bitmap indexing that represents all objects in a database as a set of bitmaps. Main contributions of the GB-index are three-fold: (1) It provides a novel way to index high-dimensional data; (2) It efficiently handles complex similarity queries; and (3) Disjunctive queries driven by relevance feedback are efficiently treated. Empirical results demonstrate that the GB-index achieves great speedups over the sequential scan and the VA-file.

• Journal of the Korea Computer Graphics Society
• /
• v.19 no.4
• /
• pp.1-11
• /
• 2013

In this paper, we represented the HTML5 webpage in 3D space for the 3D stereoscopic display by using CSS3 stylesheet; browser-based declarative contents, and proposed CSS Stereo 3DTV Profile. First, we suggested various webpage separation methods for reconstructing webpages in the 3D space effectively. Next, we suggested 3D view volume setting method by using extended CSS3 modules. And then, pre-processor converts sample contents which is written extended CSS stylesheet into the present CSS stylesheet for displaying in the webkit based browser. For the resulting stereoscopic images, we developed a rendering engine emulator which is implemented in JavaScript for simple display in the web browser, which produced dual images from virtual left and right-eyed cameras. And we have checked the sample contents displayed on the 3DTV.

• Journal of Digital Convergence
• /
• v.13 no.10
• /
• pp.483-490
• /
• 2015

The purpose of this study was to systematically organize the information for the regional resources from the agricultural management entities of convergence industry in Chungcheongnam-do. The target was the Sixth Agricultural Industry Association in Chungcheongnam-do; total 70 kinds of resources were investigated. The content was organized by name of regional source, introduction, photo, company and product information, feature of product, introduction of experience program, and etc., containing the value and meaning of products in stories of the regional sources and images. The material was organized in order of grains, fruits and vegetables, marine products, livestock, Korean sauces Kimchi, fermented broth concentrates, beverages tea, and other. It was saved as pdf file to distribute to the members; it may be utilized for online promotion, product promotion in exhibition festival sales promotion, posts for bulletin board hall, and etc. but also for promotional material in overseas marketing after translating to each language.

• Journal of Digital Contents Society
• /
• v.11 no.3
• /
• pp.393-398
• /
• 2010

Composite and compact devices equipped with the functionality of digital still image acquisition, such as cellular phones and MP3 players are widely available to common users. In addition, the application of digital still images is becoming common among security and digital recording devices. The amount of still images, that are maintained or shared in personal storage or massive storage provided by various web services, are rapidly increasing. These still images are bound with file names or identifiers that are provided arbitrarily by users or that are generated from device specific naming method. However, those identifiers are vulnerable for unexpected changing or eliminating so that it becomes a problem in still image search or management. In this paper, we propose a method for still image identifier generation that is created from the still image internal information.

• The Journal of the Korea Contents Association
• /
• v.11 no.12
• /
• pp.560-569
• /
• 2011

In this paper, we propose a text processing method for Hindi characters, Devanagari scripts, in the Android. The key points of the text processing are to device automata, which define the combining rules of alphabets into a set of syllables, and to implement a font rendering engine, which retrieves and displays the glyph images corresponding to specific characters. In general, an automaton depends on the type and the number of characters. For the soft-keyboard, we designed the automata with 14 consonants and 34 vowels based on Unicode. Finally, a combined syllable is converted into a glyph index using the mapping table, used as a handle to load its glyph image. According to the multi-lingual framework of Freetype font engine, Dvanagari scripts can be supported in the system level by appending the implementation of our method to the font engine as the Hindi module. The proposed method is verified through a simple message system.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.9
• /
• pp.5434-5439
• /
• 2014

The surface management of metals was performed with a tool microscope or surface roughness measurement instruments. These methods were not efficient for checking the surface status of the die in the production field. For this reason, an analysis system or measurement system to monitor the wear, defects and surface status as a die ages is required. This study, developed surface analysis software for automatic analysis and standardization of a die or processed products. Software was designed to measure the basic features, such as circles, dots, and lines. The captured images were rendered as three-dimensional representations so that the depth of the grooves on the die and segmental profiles could be estimated. As a result of experimental analysis, the surface roughness was measured with an accuracy more than 93.2%, and the maximum deviation in the surface roughness for the brightness of the lighting was within $3{\mu}m$. The confidence in the device's precision was assured. These results show quality control through efficient surface analysis.