• Journal of KIISE
• /
• v.42 no.11
• /
• pp.1372-1379
• /
• 2015

This paper presents an analysis of feature extraction methods used for distinguishing the speech of patients with cleft palates and people with normal palates. This research is a basic study on the development of a software system for automatic recognition and restoration of speech disorders, in pursuit of improving the welfare of speech disabled persons. Monosyllable voice data for experiments were collected for three groups: normal speech, cleft palate speech, and simulated clef palate speech. The data consists of 14 basic Korean consonants, 5 complex consonants, and 7 vowels. Feature extractions are performed using three well-known methods: LPC, MFCC, and PLP. The pattern recognition process is executed using the acoustic model GMM. From our experiments, we concluded that the MFCC method is generally the most effective way to identify speech distortions. These results may contribute to the automatic detection and correction of the distorted speech of cleft palate patients, along with the development of an identification tool for levels of speech distortion.

• Journal of the Institute of Convergence Signal Processing
• /
• v.14 no.3
• /
• pp.162-168
• /
• 2013

This paper examines the implementation of automatic compensation modules for digital camera image when a person is closing his/her eyes. The modules detect the face and eye region and then recognize the eye state. If the image is taken when a person is closing his/her eyes, the function corrects the eye and produces the image by using the most satisfactory image of the eye state among the past frames stored in the buffer. In order to recognize the face and eye precisely, the pre-process of image correction is carried out using SURF algorithm and Homography method. For the detection of face and eye region, Haar-like feature algorithm is used. To decide whether the eye is open or not, similarity comparison method is used along with template matching of the eye region. The modules are tested in various facial environments and confirmed to effectively correct the images containing faces.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.4
• /
• pp.824-830
• /
• 2010

In order to prepare for increasing performance requirement for Differential Global Navigation Satellite System (DGNSS) services of International Maritime Organization (IMO) and International Association of Lighthouse Authorities (IALA), this paper focuses on design of network-based Automatic Identification System (AIS) reference station system that can perform the functionality of Differential Global Positioning System (DGPS) reference station in an AIS base station system. AIS base station receives the differential corrections from the DGPS reference station, and it is not a method for transmitting the received differential corrections to onboard AIS units, but it is a method for generating the optimized differential corrections for onboard AIS units in AIS coverage. Therefore this paper proposes an algorithm for generating the differential corrections at AIS reference station, and performs the performance assessment of the proposed algorithm based on DGPS correction data measured from a DGPS reference station. Finally this paper discusses the test results and efficiency of the proposed system.

• The KIPS Transactions:PartB
• /
• v.16B no.6
• /
• pp.497-502
• /
• 2009

In this paper, we introduce an automatic product feature extracting system that improves the efficiency of product review analysis. Our system consists of 2 parts: a review collection and correction part and a product feature extraction part. The former part collects reviews from internet shopping malls and revises spoken style or ungrammatical sentences. In the latter part, product features that mean items that can be used as evaluation criteria like 'size' and 'style' for a skirt are automatically extracted by utilizing term statistics in reviews and web documents on the Internet. We choose nouns in reviews as candidates for product features, and calculate degree of association between candidate nouns and products by combining inner association degree and outer association degree. Inner association degree is calculated from noun frequency in reviews and outer association degree is calculated from co-occurrence frequency of a candidate noun and a product name in web documents. In evaluation results, our extraction method showed an average recall of 90%, which is better than the results of previous approaches.

• Archives of Plastic Surgery
• /
• v.51 no.1
• /
• pp.30-35
• /
• 2024

Background Breast aesthetics evaluation often relies on subjective assessments, leading to the need for objective, automated tools. We developed the Seoul Breast Esthetic Scoring Tool (S-BEST), a photometric analysis software that utilizes a DenseNet-264 deep learning model to automatically evaluate breast landmarks and asymmetry indices. Methods S-BEST was trained on a dataset of frontal breast photographs annotated with 30 specific landmarks, divided into an 80-20 training-validation split. The software requires the distances of sternal notch to nipple or nipple-to-nipple as input and performs image preprocessing steps, including ratio correction and 8-bit normalization. Breast asymmetry indices and centimeter-based measurements are provided as the output. The accuracy of S-BEST was validated using a paired t-test and Bland-Altman plots, comparing its measurements to those obtained from physical examinations of 100 females diagnosed with breast cancer. Results S-BEST demonstrated high accuracy in automatic landmark localization, with most distances showing no statistically significant difference compared with physical measurements. However, the nipple to inframammary fold distance showed a significant bias, with a coefficient of determination ranging from 0.3787 to 0.4234 for the left and right sides, respectively. Conclusion S-BEST provides a fast, reliable, and automated approach for breast aesthetic evaluation based on 2D frontal photographs. While limited by its inability to capture volumetric attributes or multiple viewpoints, it serves as an accessible tool for both clinical and research applications.

• Journal of the Korea Computer Graphics Society
• /
• v.20 no.1
• /
• pp.1-11
• /
• 2014

Patients with cerebral palsy or arthritis have deformities in lower limb which cause unstable gait or posture and pains. Surgeons perform a deformity correction osteotomy with surgical plan. But sometimes they find the unexpected angular or rotational deformation after surgery. The problems are that there is no method to predict the result of a surgical plan and also there are so many factors to must consider in surgical planning step such as clinical measurements, rotation angle, wedge angle, morphology of lower limb, etc. This paper presents new methods for planning the deformity correction osteotomy efficiently. There are two approaches based on the 3D mesh model and the accurate assessment of the patient's lower limb. One is the manual pre-simulation of surgery using forward kinematics. And the other is the automatic surgical planning using inverse kinematics and nonlinear optimization. Using these methods, we can predict and verify the results of various surgical treatments and also we can find a more effective surgical plan easily compared to conventional methods.

• Atmosphere
• /
• v.24 no.3
• /
• pp.433-444
• /
• 2014

Although the Radar-AWS Rainrate (RAR) calculation system operated by Korea Meteorological Administration estimated precipitation using 2-dimensional composite components of single polarization radars, this system has several limitations in estimating the precipitation accurately. To to overcome limitations of the RAR system, the Korea Meteorological Administration developed and operated the RMQ (Radar-based Multi-sensor Quantitative Precipitation Estimation) system, the improved version of NMQ (National Mosaic and Multi-sensor Quantitative Precipitation Estimation) system of NSSL (National Severe Storms Laboratory) for the Korean Peninsula. This study introduced the RMQ system domestically for the first time and verified the precipitation estimation performance of the RMQ system. The RMQ system consists of 4 main parts as the process of handling the single radar data, merging 3D reflectivity, QPE, and displaying result images. The first process (handling of the single radar data) has the pre-process of a radar data (transformation of data format and quality control), the production of a vertical profile of reflectivity and the correction of bright-band, and the conduction of hydrid scan reflectivity. The next process (merger of 3D reflectivity) produces the 3D composite reflectivity field after correcting the quality controlled single radar reflectivity. The QPE process classifies the precipitation types using multi-sensor information and estimates quantitative precipitation using several Z-R relationships which are proper for precipitation types. This process also corrects the precipitation using the AWS position with local gauge correction technique. The last process displays the final results transformed into images in the web-site. This study also estimated the accuracy of the RMQ system with five events in 2012 summer season and compared the results of the RAR (Radar-AWS Rainrate) and RMQ systems. The RMQ system ($2.36mm\;hr^{-1}$ in RMSE on average) is superior to the RAR system ($8.33mm\;hr^{-1}$ in RMSE) and improved by 73.25% in RMSE and 25.56% in correlation coefficient on average. The precipitation composite field images produced by the RMQ system are almost identical to the AWS (Automatic Weather Statioin) images. Therefore, the RMQ system has contributed to improve the accuracy of precipitation estimation using weather radars and operation of the RMQ system in the work field in future enables to cope with the extreme weather conditions actively.

• Geophysics and Geophysical Exploration
• /
• v.18 no.4
• /
• pp.181-196
• /
• 2015

A 3.5 kHz or chirp sub-bottom profiling survey is widely used in the marine geological and engineering purpose exploration. However, swells in the sea degrade the quality of the survey data. The horizontal continuity of profiler data can be enhanced and the quality can be improved by correcting the influence of the swell. Accurate detection of sea bottom location is important in correcting the swell effect. In this study, we tried to pick sea bottom locations by finding the position of crossing a threshold of the maximum value for the raw data and transformed data of envelope or energy ratio. However, in case of the low-quality data where the sea bottom signals are not clear due to sea wave noise, automatic sea bottom detection at the individual traces was not successful. We corrected the mispicks for the low quality data and obtained satisfactory results by picking a sea bottom within a range considering the previous average of sea bottom, and excluding unreliable big-difference picks. In case of trace by trace picking, fewest mispicks were found when using energy ratio data. In case of picking considering the previous average, the correction result was relatively satisfactory when using raw data.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2001.10a
• /
• pp.177-186
• /
• 2001

Based upon the previous experiences and typical oases of typhoon evasion fur ships as well as tile achievement in scientific research in this detrain, we developed the Intelligent Typhoon Evasion System for Ships. It consists of five subsystems, including electronic charts, ship movement management, typhoon information query and automatic plotting, real-time calculation of ship-typhoon situation, intelligent typhoon evasion decision making. With the synthetical application of analogy theory, synoptic chart, satellite cloud picture analysis, typhoon digital forecast and other relevant technologies, we leave established the typhoon evasion data bases. model bases and knowledge bases, which make it possible to automatically track the ships and typhoon paths. The system can realize ship-typhoon situation analysis, risk levee assessment, typhoon paths correction and course synoptic forecast, and intelligent typhoon evasion decision making.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.11 no.2
• /
• pp.13-19
• /
• 2011

By using beam-projectors, we can easily configure a big image system. In the process of installing beam-projectors, however manual steps are essentially needed to perform a calibration such that distortions can be minimized. In order to automatically perform the correction of distortion, in this paper we propose a new auto-calibration method for beam-projector, which is based on Zigbee and can be easily implemented by simple hardware and software. In the proposed scheme, we recognize the required image project area by using Zigbee-based sensor module, and then we can obtain the best beam projection even in the case that the screen is badly twisted.