• Journal of Biosystems Engineering
• /
• v.40 no.1
• /
• pp.89-93
• /
• 2015

Purpose: Machine vision-based image processing methods can be useful for estimating the fresh weight of plants. This study analyzes the ability of two different image processing methods, i.e., morphological and pixel-value analysis methods, to measure the fresh weight of lettuce grown in a closed hydroponic system. Methods: Polynomial calibration models are developed to relate the number of pixels in images of leaf areas determined by the image processing methods to actual fresh weights of lettuce measured with a digital scale. The study analyzes the ability of the machine vision- based calibration models to predict the fresh weights of lettuce. Results: The coefficients of determination (> 0.93) and standard error of prediction (SEP) values (< 5 g) generated by the two developed models imply that the image processing methods could accurately estimate the fresh weight of each lettuce plant during its growing stage. Conclusions: The results demonstrate that the growing status of a lettuce plant can be estimated using leaf images and regression equations. This shows that a machine vision system installed on a plant growing bed can potentially be used to determine optimal harvest timings for efficient plant growth management.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.10
• /
• pp.25-33
• /
• 2012

In this paper, we propose a rule-based model to correct errors in a speech recognition result in the mobile device environment. The proposed model considers the mobile device environment with limited resources such as processing time and memory, as follows. In order to minimize the error correction processing time, the proposed model removes some processing steps such as morphological analysis and the composition and decomposition of syllable. Also, the proposed model utilizes the longest match rule selection method to generate one error correction candidate per point, assumed that an error occurs. For the purpose of deploying memory resource, the proposed model uses neither the Eojeol dictionary nor the morphological analyzer, and stores a combined rule list without any classification. Considering the modification and maintenance of the proposed model, the error correction rules are automatically extracted from a training corpus. Experimental results show that the proposed model improves 5.27% on the precision and 5.60% on the recall based on Eojoel unit for the speech recognition result.

• Korea-Australia Rheology Journal
• /
• v.19 no.3
• /
• pp.125-131
• /
• 2007

Biodegradable polymeric blends are expected to be widely used by industry due to their environmental friendliness and comparable mechanical and thermal properties. Poly (lactic acid) (PLA) and poly (butylene succinate) (PBS) are such biodegradable polymers which aim to replace commodity polymers in future applications. Since cost and brittleness of PLA is quite high, it is not economically feasible to use it alone for day to day use as a packaging material without blending. In this study, blends of PLA and PBS with various compositions were prepared by using a laboratory-scale twin-screw extruder at $180^{\circ}C$. Morphological, thermal, rheological and mechanical properties were investigated on the samples obtained by compression molding to explore suitability of these compositions for packaging applications. Morphology of the blends was investigated by scanning electron microscopy (SEM). Morphology showed a clear phase difference trend depending on blend composition. Modulated differential scanning calorimetry (MDSC) thermograms of the blends indicated that the glass transition temperature ($T_g$) of PLA did not change much with the addition of PBS, but analysis showed that for PLA/PBS blend of up to 80/20 composition there is partial miscibility between the two polymers. The tensile strength and modulus were measured by the Instron Universal Testing Machine. Tensile strength, modulus and percentage (%) elongation at break of the blends decreased with PBS content. However, tensile strength and modulus values of PLA/PBS blend for up to 80/20 composition nearly follow the mixing rule. Rheological results also show miscibility between the two polymers for PBS composition less than 20% by weight. PBS reduced the brittleness of PLA, thus making it a contender to replace plastics for packaging applications. This work found a partial miscibility between PBS and PLA by investigating thermal, mechanical and morphological properties.

• MALSORI
• /
• no.46
• /
• pp.51-64
• /
• 2003

In order to produce high quality synthesized speech, it is very important to get an accurate grapheme-to-phoneme conversion and prosody model from texts using natural language processing. Robust preprocessing for non-Korean characters should also be required. In this paper, we analyzed Korean texts using a morphological analyzer, part-of-speech tagger and syntactic chunker. We present a new grapheme-to-phoneme conversion method for Korean using a hybrid method with a phonetic pattern dictionary and CCV (consonant vowel) LTS (letter to sound) rules, for unlimited vocabulary Korean TTS. We constructed a prosody model using a probabilistic method and decision tree-based method. The probabilistic method atone usually suffers from performance degradation due to inherent data sparseness problems. So we adopted tree-based error correction to overcome these training data limitations.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.6
• /
• pp.1552-1562
• /
• 1998

형태소 분석(Morphological Analysis)과 같은 언어학적 처리에 의존하는 기존의 한국어 문헌에 대한 자동색인 기법들은 품사의 애매모호함이나 복합명사의 처리 등으로 부담(overhead)이 크다. 또한 불용어 처리에 사용되는 불용어 리스트가 대상 문헌의 주제 분야별로 따로 구축되어야 하며 그 크기가 방대하다는 문제점이 있다. 이러한 문제점들을 해결하기 위해, 본 논문에서는 각 문헌의 텍스트에 대해 복합명사 처리나 애매모호함에 대한 엄격한 분석을 수행하지 않는 간단한 형태의 형태소 분석을 수행하여 단순명사들을 추출한다. 그런 후 이들 단순명사들을 이용하여 유한 오토마타(Finite Automata)를 구성하고, 구성된 유한 오토마타와 각 명사의 단어빈도(Term Frequency)에 의해 각 색인어 후보들의 중요도를 계산하는 자동색인 기법을 제안한다. 그 결과 품사의 애매모호함에 대한 처리나 복합명사의 처리에따른 부담을 줄일 수 있었으며, 선정된 색인어들과 수작업으로 선정한 색인어들의 비교 실험에 의해 제안한 자동색인 기법의 성능을 검증하였다.

• Tribology and Lubricants
• /
• v.12 no.3
• /
• pp.72-78
• /
• 1996

This paper was undertaken to analyze the morphology of wear debris generated from lubricated moving machine surfaces by image processing. The lubricati, ng wear test was performed under different experimental conditions using the wear test device made in our laboratory and wear test specimen of the pin on disk type wear rubbed in paraffme series base oil, by varying applied load, sliding distance. The four parameters (50% volumetric diameter, aspect, roundness and reflectivity) to describe the morphology have been developed and outlined in the paper. A system using such techniques promises to obviate the need for subjective, human interpretation of particle morphology in machine condition monitoring, thus to overcome many of the difficulties with current methods and to facilitate wider use of wear particle analysis in machine condition monitoring.

• Annual Conference on Human and Language Technology
• /
• 2013.10a
• /
• pp.9-12
• /
• 2013

본 논문에서는 한국어 형태소 분할 및 품사 태깅 방법을 위한 결합 모델로 Semi-CRF와 Linear-chain CRF에 대한 초기 비교 실험을 수행한다. Linear-chain방법은 출력 레이블을 형태소 분할 정보와 품사 태그를 조합함으로써 결합을 시도하는 방식이고, Semi-CRF는 출력의 구조가 분할과 태깅 정보를 동시에 포함하도록 표현함으로써, 디코딩 과정에서 분할과 태깅을 동시에 수행하는 방법이다. Sejong품사 부착말뭉치에서 비교결과 Linear-chain방법이 Semi-CRF방법보다 우수한 성능을 보여주었다.

• Annual Conference on Human and Language Technology
• /
• 2013.10a
• /
• pp.13-17
• /
• 2013

본 논문은 CRF기반 한국어 형태소 분석 및 품사 태깅 과정에서 발생하는 미등록 복합형태소를 분해하기 위한 단순하고 효과적인 방법을 제안한다. 제안 방법은 1) 복합형태소를 내용형태소와 복합기능형태소로 분리하는 단계, 2) 복합기능형태소를 분해하는 두 단계로 구성된다. 실험 결과, 제안 알고리즘은 Sejong데이터에 대해, 기존의 lattice HMM 대비 높은 복합형태소 분해 정확률 및 두드러진 속도 개선을 보여준다.

• Annual Conference on Human and Language Technology
• /
• 2013.10a
• /
• pp.3-8
• /
• 2013

본 논문에서는 래티스상의 구조적 분류에 기반한 한국어 형태소 분석 및 품사 태깅을 수행하는 방법을 제안한다. 제안하는 방법은 입력문이 주어질 때 어휘 사전을 참조하여, 형태소를 노드로 취하고 인접형태 소간의 에지를 갖도록 래티스를 구성하며, 구성된 래티스상 가장 점수가 높은 경로상에 있는 형태소들을 분석 결과로 제시하는 방법이다. 실험 결과, ETRI 품사 부착 코퍼스에서 기존의 1차 linear-chain CRF에 기반한 방법보다 높은 어절 정확률 그리고 문장 정확률을 얻었다.

• Journal of the Semiconductor & Display Technology
• /
• v.13 no.4
• /
• pp.49-54
• /
• 2014

This paper proposes a new color segmentation method of vehicle license plates in the RGB color space. Firstly, the proposed method shifts the histogram of an input image rightwards and then stretches the image of the histogram slide. Secondly, the method separates each of the three RGB color components and performs the adaptive threshold processing with the three components, respectively. Finally, it combines the three components under the condition of making up a segment color and removes noises with the morphological processing. The proposed method is implemented using C language in an embedded Linux system for a high-speed real-time image processing. Experiments were conducted by using real vehicle images. The results show that the proposed algorithm is successful for most vehicle images. However, the method fails in some vehicles when the body and the license plate have the same color.