• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권1호
• /
• pp.288-301
• /
• 2017

In this paper, we propose an optimized algorithm for texture classification by computing a completed modeling of the local binary pattern (CLBP) instead of the traditional LBP of a scalable block size in an image. First, we show that the CLBP descriptor is a better representative than LBP by extracting more information from an image. Second, the CLBP features of scalable block size of an image has an adaptive capability in representing both gross and detailed features of an image and thus it is suitable for image texture classification. This paper successfully implements a machine learning scheme by applying the CLBP features of a scalable size to the Support Vector Machine (SVM) classifier. The proposed scheme has been evaluated on Outex and CUReT databases, and the evaluation result shows that the proposed approach achieves an improved recognition rate compared to the previous research results.

• 한국정보처리학회논문지
• /
• 제4권8호
• /
• pp.2017-2024
• /
• 1997

본 논문은 새로운 형태의 문서 통신 방식인 지적 커뮤니케이션 시스템(IICS : Intelligent Image Communication System)의 구현을 위하여 한글 문서를 대상으로 문서를 구성하는 문자의 서체와 문자의 크기 및 기울기를 인식하고 방법을 제안한다. 서체를 인식하기 위하여 문서에서 일정한 크기의 블럭을 추출하여 주파수 분석을 하였고, 단어의 외접 사각형의 수직 거리를 이용하여 문자의 크기를 인식하였다. 문자의 기울기를 인식하기 위하여 수직 방향의 투영 프로파일을 이용하였다. 서체 인식을 위한 인식기의 가변적인 히든 노드를 이용하여 오류 역전파 알고리즘으로 학습된 MLP(Multi-layer Perceptron)를 사용하였으며, 문자의 크기와 기울기를 분류하기 위하여 Mahalanobis distance를 이용하였다. 실험을 통하여 서체 분류는 10개의 서체에 대하여 평균 95.19%의 인식률을 얻었고, 문자의 크기 분류는 5가지의 문자 크기에 대하여 평균 97.34%의 인식률을 얻었으며, 문자의 기울기는 평균 89.09%의 인식률을 얻음으로써 제안된 방법의 유용성을 입증하였다.

• 한국초전도ㆍ저온공학회논문지
• /
• 제23권3호
• /
• pp.26-31
• /
• 2021

Advanced classification of Cs contaminated soil by using a magnetic force-assisted selection pipe was investigated. A selection pipe is a device that sort particles depending on their particle size, based on the relationship between buoyancy, drag, and gravity force acting on the particles. Radioactive cesium is concentrated in small-particle size soil components with a large specific surface area. Hence, the volume of the Cs contaminated soil can be reduced by recycling the large-particle size soil components with low radioactive concentration. One of the problems of the selection pipe was that the radioactive concentration of the stayed soil in the selection pipe exceeds 8000 Bq/kg, which is the standard value of recycling of Cs contaminated soil, due to low classification accuracy. In this study, magnetic fields were applied to the lab-scale selection pipe from upper side to improve the classification accuracy and to reduce the radioactive concentration of the stayed soil.

• Spatial Information Research
• /
• 제18권5호
• /
• pp.13-26
• /
• 2010

본 논문에서는 항공 라이다 데이터를 이용하여 지형의 유형을 분류하는 과정에서 지형의 특성에 따라 지형 분류의 판정 단위를 가변적으로 변화시키는 동적 가변 윈도우 기반 지형 분류 기법을 제안한다. 제안된 동적 가변 윈도우 기반 지형 분류 기법에서는 지형의 특성과 반복 패턴에 따라 지형 분류의 판정 단위를 가변적으로 결정하여 지형 분류에 소요되는 시간을 감소시키고자 하였다. 또한, 본 논문에서는 실험을 통하여 동적 가변 윈도우 기반 지형 분류 기법의 시간효율과 정확도를 분석하고 최적의 최대 판정 윈도우 크기를 제시하였다. 실험 결과에 따르면 제안된 동적 가변 윈도우 기반 지형 분류 기법은 고정 윈도우 크기를 이용하는 기법과 유사한 정도의 정확성을 유지하면서도 빠른 지형 분류가 가능한 것으로 판명되었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권7호
• /
• pp.2261-2280
• /
• 2014

Recently, network traffic has become more complex and diverse due to the emergence of new applications and services. Therefore, the importance of application-level traffic classification is increasing rapidly, and it has become a very popular research area. Although a lot of methods for traffic classification have been introduced in literature, they have some limitations to achieve an acceptable level of performance in real-time application-level traffic classification. In this paper, we propose a novel application-level traffic classification method using payload size sequence (PSS) signature. The proposed method generates unique PSS signatures for each application using packet order, direction and payload size of the first N packets in a flow, and uses them to classify application traffic. The evaluation shows that this method can classify application traffic easily and quickly with high accuracy rates, over 99.97%. Furthermore, the method can also classify application traffic that uses the same application protocol or is encrypted.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2010년도 한국컴퓨터종합학술대회논문집 Vol.37 No.1(C)
• /
• pp.447-451
• /
• 2010

In this paper, we propose a simple but effective algorithm to increase the speed of Emphysema region classification. Emphysema region classification method based on CT image consumes a lot of time because of the large number of subregions due to the large size of CT image. Some of the sub-regions contain no Emphysema and the classification of these regions is worthless. To speed up the classification process, we create an algorithm to select Emphysema region candidates and only use these candidates in the Emphysema region classification instead of all of the sub-regions. First, the lung region is detected. Then we threshold the lung region and only select the dark pixels because Emphysema only appeared in the dark area of the CT image. Then the thresholded pixels are clustered into a region that called the Emphysema pre-detected region or Emphysema region candidate. This region is then divided into sub-region for the Emphysema region classification. The experimental result shows that Emphysema region classification using predetected Emphysema region decreases the size of lung region which will result in about 84.51% of time reduction in Emphysema region classification.

• 복식
• /
• 제57권10호
• /
• pp.50-59
• /
• 2007

This study has been conducted to classify elderly men's feet with the three-dimensional body scanner data of Size Korea. It was intended to assist the manufacturing of the shoes that can appropriately perform the functions of feet, by providing the specific information about the shapes of elderly men's feet that are altered as a result of aging and shoe-wearing for a long time. The findings are as follows. 1. The investigations into the average and standard deviation of the measurements and index values for the elderly men's feet showed a large personal difference in the items of length and circumference. 2. The factors constituting the elderly men's feet were observed to be the size of foot width(Factor 1), the central angle of feet and the extension of toes(Factor 2), the size of ankle(Factor 3), the positions of lateral malleolus and pternion(Factor 4), and the position and size of medial malleolus(Factor 5). 3. The cluster analysis for the classification of elderly men's feet produced three types of them.

• 자원리싸이클링
• /
• 제10권6호
• /
• pp.29-34
• /
• 2001

석탄회 분말을 다중자연낙하법에 의한 공기분급에 의하여 미립 및 조립의 분말로 정제 및 분급한 후 각각의 분말을 사용하여 뮬라이트 및 제올라이트를 합성하였다 평균 입경이 $6.5mu$m인 미립 석탄회에$ A12$ $O_3$를 첨가한 후 145$0^{\circ}C$ 이상의 온도에서 소성하여 뮬라이트 상의 소결체를 얻었다. 평균 입경 $56.3\mu$m인 조립 석탄회를 사용하여 3.5 M NaOH수용액과 $120^{\circ}C$에서 수열 반응시켜 phillipsite형 제올라이트를 합성하였다. 이와 같은 방법으로 모든 입도의 석탄회 분말을 무기재료의 합성에 이용할 수 있었다.

• 한국정밀공학회지
• /
• 제26권2호
• /
• pp.118-125
• /
• 2009

This paper reports the size classification of nanoparticles as well as electrical tuning techniques for the cut-off diameter and collection efficiency. Classifying particles < 100 nm in diameter is quite a technical challenge using a virtual impactor with the cut-off diameter being determined geometrically. However, the proposed virtual impactor can classify particles <100 nm and tune the cut-off diameter by electrically accelerating the particles. The cut-off diameter of the proposed device was tuned from 15 to 50nm.

• 전자공학회논문지B
• /
• 제33B권10호
• /
• pp.120-129
• /
• 1996

This paper presents an efficient block segmentation and classification using the edge information of the document image. We extract four prominent features form the edge gradient and orientaton, all of which, and thereby the block clssifications, are insensitive to the background noise and the brightness variation of of the image. Using these four features, we can efficiently classify a document image into the seven categrories of blocks of small-size letters, large-size letters, tables, equations, flow-charts, graphs, and photographs, the first five of which are text blocks which are character-recognizable, and the last two are non-character blocks. By introducing the clumn interval and text line intervals of the document in the determination of th erun length of CRLA (constrained run length algorithm), we can obtain an efficient block segmentation with reduced memory size. The simulation results show that the proposed algorithm can rigidly segment and classify the blocks of the documents into the above mentioned seven categories and classification performance is high enough for all the categories except for the graphs with too much variations.