• Journal of Biosystems Engineering
• /
• v.36 no.1
• /
• pp.40-47
• /
• 2011

Image analysis algorithm for the quality evaluation of ginseng seedling was investigated. The images of ginseng seedling were acquired with a color CCD camera and processed with the image analysis methods, such as binary conversion, labeling, and thinning. The processed images were used to calculate the length and weight of ginseng seedlings. The length and weight of the samples could be predicted with standard errors of 0.343 mm, and 0.0214 g respectively, $R^2$ values of 0.8738 and 0.9835 respectively. For the evaluation of the three quality grades of Gab, Eul, and abnormal ginseng seedlings, features from the processed images were extracted. The features combined with the ratio of the lengths and areas of the ginseng seedlings efficiently differentiate the abnormal shapes from the normal ones of the samples. The grade levels were evaluated with an efficient pattern recognition method of support vector machine analysis. The quality grade of ginseng seedling could be evaluated with an accuracy of 95% and 97% for training and validation, respectively. The result indicates that color image analysis with support vector machine algorithm has good potential to be used for the development of an automatic sorting system for ginseng seedling.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.10 no.1 s.20
• /
• pp.1-7
• /
• 2004

RADARSAT is one of many possible data sources that can play an important role in marine surveillance including ship detection because radar sensors have the two primary advantages: all-weather and day or night imaging. However, atmospheric effects on SAR imaging can not be bypassed and any remote sensing image has various geometric distortions, In this study, radiometric and geometric calibrations for RADARSAT/SAT data are tried using SGX products georeferenced as level 1. Even comparison of the near vs. far range sections of the same images requires such calibration Radiometric calibration is performed by compensating for effects of local illuminated area and incidence angle on the local backscatter, Conversion method of the pixel DNs to beta nought and sigma nought is also investigated. Finally, automatic geometric calibration based on the 4 pixels from the header file is compared to a marine chart. The errors for latitude and longitude directions are 300m and 260m, respectively. It can be concluded that the error extent is acceptable for an application to open sea and can be calibrated using a ground control point.

• Phonetics and Speech Sciences
• /
• v.7 no.3
• /
• pp.139-149
• /
• 2015

This paper aims to analyze pronunciation variations of loanwords produced by Korean and improve the performance of pronunciation modeling of loanwords in Korean by using syllable-based segmentation and phonological knowledge. The loanword text corpus used for our experiment consists of 14.5k words extracted from the frequently used words in set-top box, music, and point-of-interest (POI) domains. At first, pronunciations of loanwords in Korean are obtained by manual transcriptions, which are used as target pronunciations. The target pronunciations are compared with the standard pronunciation using confusion matrices for analysis of pronunciation variation patterns of loanwords. Based on the confusion matrices, three salient pronunciation variations of loanwords are identified such as tensification of fricative [s] and derounding of rounded vowel [ɥi] and [$w{\varepsilon}$]. In addition, a syllable-based segmentation method considering phonological knowledge is proposed for loanword pronunciation modeling. Performance of the baseline and the proposed method is measured using phone error rate (PER)/word error rate (WER) and F-score at various context spans. Experimental results show that the proposed method outperforms the baseline. We also observe that performance degrades when training and test sets come from different domains, which implies that loanword pronunciations are influenced by data domains. It is noteworthy that pronunciation modeling for loanwords is enhanced by reflecting phonological knowledge. The loanword pronunciation modeling in Korean proposed in this paper can be used for automatic speech recognition of application interface such as navigation systems and set-top boxes and for computer-assisted pronunciation training for Korean learners of English.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.1
• /
• pp.733-744
• /
• 2016

The legacy methods for converting a business model to a feature model make it difficult to support an automatic transformation due to a dependence on a domain analyzers' intuitions, which hinders the feature oriented development for the integration of feature modeling in business modeling. This paper proposes a method for converting a BPMN business model into a feature model based on syntax. To allow the conversion between the heterogeneous models from BPMN to the FM(Feature Model), it defines the grouping mechanism based activities' syntax, and then makes translation rules and a method based on the element (represent business function) and structure (relationships and process among elements), which are common constructs of their models. This method was applied to an online shopping mall system as a case study. With this mechanism, it will help develop a mechanical or automated structure transformation from the BPMN model to the FM.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.5
• /
• pp.267-278
• /
• 2017

As the same letter can be pronounced differently depending on word contexts, one should refer to a lexicon in order to pronounce a word correctly. Phonetic alphabets that lexicons adopt as well as pronunciations that lexicons describe for the same word can be different from lexicon to lexicon. In this paper, we use a sequence-to-sequence model that is widely used in deep learning research area in order to convert automatically from one pronunciation to another. The 12 seq2seq models are implemented based on pronunciation training data collected from 4 different lexicons. The exact accuracy of the models ranges from 74.5% to 89.6%. The aim of this study is the following two things. One is to comprehend a property of phonetic alphabets and pronunciations used in various lexicons. The other is to understand characteristics of seq2seq models by analyzing an error.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.6
• /
• pp.1431-1439
• /
• 2017

In the security field, log analysis is important to detect malware or abnormal behavior. Recently, image visualization techniques for malware dectection becomes to a major part of security. These techniques can also be used in online games. Users can leave a game when they felt bad experience from game bot, automatic hunting programs, malicious code, etc. This churning can damage online game's profit and longevity of service if game operators cannot detect this kind of events in time. In this paper, we propose a new technique of PNG image conversion based churn prediction to improve the efficiency of data analysis for the first. By using this log compression technique, we can reduce the size of log files by 52,849 times smaller and increase the analysis speed without features analysis. Second, we apply data mining technique to predict user's churn with a real dataset from Blade & Soul developed by NCSoft. As a result, we can identify potential churners with a high accuracy of 97%.

• Journal of Power Electronics
• /
• v.17 no.6
• /
• pp.1587-1599
• /
• 2017

This paper proposes a real-time implementation of an optimal operation of a double stage grid connected wind power system incorporating an active power filter (APF). The system is used to supply the nonlinear loads with harmonics and reactive power compensation. On the generator side, a new adaptive neuro fuzzy inference system (ANFIS) based maximum power point tracking (MPPT) control is proposed to track the maximum wind power point regardless of wind speed fluctuations. Whereas on the grid side, a modified predictive current control (PCC) algorithm is used to control the APF, and allow to ensure both compensating harmonic currents and injecting the generated power into the grid. Also a type 2 fuzzy logic controller is used to control the DC-link capacitor in order to improve the dynamic response of the APF, and to ensure a well-smoothed DC-Link capacitor voltage. The gained benefits from these proposed control algorithms are the main contribution in this work. The proposed control scheme is implemented on a small-scale wind energy conversion system (WECS) controlled by a dSPACE 1104 card. Experimental results show that the proposed T2FLC maintains the DC-Link capacitor voltage within the limit for injecting the power into the grid. In addition, the PCC of the APF guarantees a flexible settlement of real power exchanges from the WECS to the grid with a high power factor operation.

• Journal of the Korea Convergence Society
• /
• v.12 no.10
• /
• pp.1-8
• /
• 2021

In online meetings and classes using webcams, the chromakey technique is a very necessary part to produce content. We proposed a technology that enables background synthesis without using a cloth for chromakey. The proposed method consists of three steps: an HSI image conversion step, a step of detecting a region changed from a background, and a step of replacing the background region with a chromakey and applying it. In the input video, the block average image of each frame is calculated, and the difference between the block average image of the background image and the block average image of the input image is used to detect the change area. The developed chromakey effect technology uses a technique of acquiring a background image without an object from a single camera and extracting only an object by distinguishing the moving object and the background. The proposed method is not only capable of processing even if the background has a variety of colors, but also has the seamless processing of the boundary lines of objects.

• Journal of Aerospace System Engineering
• /
• v.16 no.5
• /
• pp.70-77
• /
• 2022

This paper proposes database generation and management system for small-pixelized airborne target recognition. The proposed system has five main features: 1) image extraction from in-flight test video frames, 2) automatic image archiving, 3) image data labeling and Meta data annotation, 4) virtual image data generation based on color channel convert conversion and seamless cloning and 5) HOG/LBP-based tiny-pixelized target augmented image data. The proposed framework is Python-based PyQt5 and has an interface that includes OpenCV. Using video files collected from flight tests, an image dataset for airborne target recognition on generates by using the proposed system and system input.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.225-228
• /
• 2022

The method of calculating the architectural design cost of the Korean Society of Architecture Policy considers the time spent during the design period. Therefore, faster design times can reduce design costs. As a result of a survey of students majoring in architecture, they felt tiredness from repeated floor plan drawings and difficulties in that there were many things to consider when floor plan drawing. In this paper, we implement a program that can automatically convert sketches into standardized floor plans during the architectural design process and a web app for user convenience. In the proposed method, when a user registers a sketch image through a web app, the program separates the space in the drawing through geometric shapes detection. Based on the dimensions and spatial information shown in the sketch, the outer and inner walls are displayed and the appropriate furniture is placed in the space. Through the proposed method, the design cost can be expected to be reduced by reducing the time of the drawing process in the architectural design stage, and 95.2% of architectural students expressed their intention to use the program.