• 음성과학
• /
• 제14권1호
• /
• pp.37-62
• /
• 2007

The current study examines the role of post-lexical tonal patterns of a prosodic phrase in word segmentation. In a word spotting experiment, native Korean listeners were asked to spot a disyllabic or trisyllabic word from twelve syllable speech stream that was composed of three Accentual Phrases (AP). Words occurred with various post-lexical intonation patterns. The results showed that listeners spotted more words in phrase-initial than in phrase-medial position, suggesting that the AP-final H tone from the preceding AP helped listeners to segment the phrase-initial word in the target AP. Results also showed that listeners' error rates were significantly lower when words occurred with initial rising tonal pattern, which is the most frequent intonational pattern imposed upon multisyllabic words in Korean, than with non-rising patterns. This result was observed both in AP-initial and in AP-medial positions, regardless of the frequency and legality of overall AP tonal patterns. Tonal cues other than initial rising tone did not positively influence the error rate. These results not only indicate that rising tone in AP-initial and AP_final position is a reliable cue for word boundary detection for Korean listeners, but further suggest that phrasal intonation contours serve as a possible word boundary cue in languages without lexical prominence.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 춘계학술발표대회
• /
• pp.515-518
• /
• 2019

Semantic segmentation has remained as a challenging problem in the field of computer vision. Given the immense power of Convolution Neural Network (CNN) models, many complex problems have been solved in computer vision. Semantic segmentation is the challenge of classifying several pixels of an image into one category. With the help of convolution neural networks, we have witnessed prolific results over the time. We propose a convolutional neural network model which uses Fully CNN with deconvolutional pixel layers. The goal is to create a hierarchy of features while the fully convolutional model does the primary learning and later deconvolutional model visually segments the target image. The proposed approach creates a direct link among the several adjacent pixels in the resulting feature maps. It also preserves the spatial features such as corners and edges in images and hence adding more accuracy to the resulting outputs. We test our algorithm on Karlsruhe Institute of Technology and Toyota Technologies Institute (KITTI) street view data set. Our method achieves an mIoU accuracy of 92.04 %.

• 농촌지도와개발
• /
• 제28권1호
• /
• pp.13-23
• /
• 2021

This study aims to examine the market segmentation of rural healing tourists. A two-stage cluster method was used to segment the market of rural healing tourists, and the difference in satisfaction by segmented market was identified. In this study, a total of 433 cases were used for analysis. A total of four clusters of rural healing tourists were derived based on the purpose of visit and involvement with rural healing tourism. The names of each cluster were determined as 'high involvement, daily escape purpose type', 'high involvement, stress relief purpose type', 'low involvement, daily escape purpose type', and 'high involvement, exotic experience purpose type.' Each groups were found to have significant differences according to educational level, purpose of visit, companion, and expenditure. The satisfaction and the behavioral intention of rural healing tourists was highest in the group of 'high involvement, stress relief purpose type.' The results of this study suggest that the characteristics and satisfaction of rural healing tourists were differ according to the segmented group. This study suggests useful information for target marketing strategies for each segmented market according to the characteristics of rural healing tourists.

• 스마트미디어저널
• /
• 제11권11호
• /
• pp.40-48
• /
• 2022

본 논문에서는 인공지능교육의 어려움을 해결하기 위하여 인공지능 교육에 활용이 가능한 교육용 키트를 개발하였다. 이를 통하여 이론 중심에서 실무 위주의 경험을 학습하기 위한 CNN과 OpenCV를 이용하여 컴퓨터 비전 기술을 이용한 사람 인식(Object Detection and Person Detection in Computer Vision)과 특정 오브젝트를 학습시키고 인식시키는 사용자 이미지인식(Your Own Image Recognition), 사용자 객체 분류(Segmentation) 및 세분화(Classification Datasets), 학습된 타켓을 공격하는 IoT하드웨어 제어와 인공지능보드인 Jetson Nano GPIO를 제어함으로써 효과적인 인공지능 학습에 도움이 되는 교재를 개발하여 활용할 수 있도록 하였다.

• 아태비즈니스연구
• /
• 제14권1호
• /
• pp.411-426
• /
• 2023

Purpose - The purpose of this study was to explore and diagnose the characteristics and behavioural patterns of rural tourists after COVID-19 using decision tree analysis to classify and identify key segmentation groups. Design/methodology/approach - The CHAID algorithm was used as the analysis technique for the decision tree. The explanatory variables used in the analysis of each decision tree model were demographic variables and rural tourism usage behaviour and perception variables, and the target variables were the preferences of rural tourists' activities after COVID-19. From the Rural Tourism 2020 survey data, 614 samples with rural tourism experience were extracted and used in the analysis. Findings - The variables that significantly explained the preference for each type of rural tourism activity after COVID-19 were rural tourism safety perception, repeated visits to the region, rural tourism priority activity, rural tourism accommodation experience, gender, age group, marital status, occupation, and education level. Among them, rural tourism safety perception was the most important explanatory variable in each analysis model. Research implications or Originality - Overall, to promote rural tourism, it is necessary to enhance the safety image of rural tourism, strengthen loyalty programs for repeat visitors, and develop customized products that reflect the preferred trends of rural tourism.

• Journal of information and communication convergence engineering
• /
• 제9권6호
• /
• pp.666-670
• /
• 2011

In this paper, we propose a stable active contour based tracking method which utilizes the bimodal segmentation technique to obtain a background color diminished image frame. The proposed method overcomes the drawback of the Mansouri model which is liable to fall into a local minimum state when colors appear in the background that are similar to the target colors. The Mansouri model has been a foundation for active contour based tracking methods, since it is derived from a probability based interpretation. By stabilizing the model with the proposed speed function, the proposed model opens the way to extend probability based active contour tracking for practical applications.

• 전기학회논문지P
• /
• 제55권4호
• /
• pp.167-175
• /
• 2006

This paper presents a method to segment semiconductor wafer ID on poor quality images. The method is based on multiple templates and normalized gray-level correlation (NGC) method. If the lighting condition is not so good and hence, we can not control the image quality, target image to be inspected presents poor quality ID and it is not easy to identify and then recognize the ID characters. Conventional several method to segment the interesting ID regions fails on the bad quality images. In this paper, we propose a multiple template method, which uses combinational relation of multiple templates from model templates to match several characters of the inspection images. To find out the optimal solution of multiple template model in ID regions, we introduce newly-developed snake algorithm. Experimental results using images from real FA environment are presented.

• 복식문화연구
• /
• 제21권2호
• /
• pp.301-308
• /
• 2013

The purpose of this research is to classify fashion consumers based on their attitudes, goals and values of life. It is to understand what drives human behaviors as well as to learn the various directions people live in society using Bangkok people as the samples. Online and on-site questionnaire survey is employed. Questions are designed to focus on 7 aspects of life, ranging from private life, professional life, social life, politics, culture and information interaction, household business and finance, and consumption of products and services in the main market. The research results can be used to classify consumers' lifestyles into 20 major and numerous minor groups of lifestyle. Lifestyles of male and female samples are compared to investigate their different patterns and directions. Fashion trend diagram is used to analyze the overlapped lifestyles of mass consumers. The lifestyle segmentations would benefit to designer and fashion branding team in understanding their target group deeper inside the background of their behaviors.

• 제어로봇시스템학회논문지
• /
• 제10권8호
• /
• pp.726-733
• /
• 2004

This paper presents a method to segment object ID(identification) marks on poor quality images under uncontrolled lighting conditions of automated inspection process. The method is based on dynamic programming using multiple templates and normalized gray-level correlation (NGC) method. If the lighting condition is not good and hence, we can not control the image quality, target image to be inspected presents poor quality ID marks and it is not easy to identify and recognize the ID characters. Conventional several methods to segment the interesting ID mark regions fail on the bad quality images. In this paper, we propose a multiple template method, which uses combinational relation of multiple templates from model templates to match several characters of the inspection images. To increase the computation speed to segment the ID mark regions, we introduce the dynamic programming based algorithm. Experimental results using images from real factory automation(FA) environment are presented.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2022년도 제65차 동계학술대회논문집 30권1호
• /
• pp.41-44
• /
• 2022

Mean-Shift 영상 분할은 객체 검출을 위한 영상 전처리 방법으로써, 영상 처리 및 패턴 인식 분야에서 널리 사용되는 방법이다. 영상 분할은 영역 기반과 에지 기반 방식으로 나누어지며 대표적으로 FCM, Quickshift, Felzenszwalb, SLIC 알고리즘 등 이 있다. 언급한 영상 분할 방법들은 Mean-Shift 영상 분할에 비해서 빠른 속도로 실행시킬 수 있지만, 형태적 특징이 훼손되고 하나의 객체가 여러 세그멘테이션으로 분할된다는 단점을 가지고 있다. 본 논문에서는 소형 객체를 탐지하기 위한 고속화된 Mean-Shift 영상 분할과 객체의 형태적 특징을 이용하여 객체를 탐지하는 방법을 제안한다. 하드웨어 리소스가 제한된 신호처리기에 제안하는 알고리즘을 수행하기 위하여 Mean-Shift 영상 분할에서 필터링 과정을 고속화 하였고, 적외선 영상 내 영상 전처리 수행을 통해 잡음 제거 후 Mean-Shift 영상 분할 방법을 수행함으로써, 객체의 형태적 특징을 잘 살려서 영상 분할을 할 수 있도록 하였다. 또한 각 세그멘테이션의 크기, 너비, 높이, 밝기 정보와 형태적 특징점을 이용한 객체 탐지 방법을 제안한다.