• Korean Journal of Plant Taxonomy
• /
• v.49 no.4
• /
• pp.300-318
• /
• 2019

Many infraspecific taxa within Lespedeza maximowiczii and hybrids with related species have been described, but taxonomic verification remains controversial. We examined the morphological traits of hybrids (L. chiisanensis and L. patentibicolor) and infraspecific taxa (var. tomentella, elongata, and tricolor) and analyzed their genetic structures using microsatellite loci. Flower and leaflet shapes in var. tomentella and elongata were within the range of variation of those in var. maximowiczii, and individuals in the two former varieties were grouped into var. maximowiczii. Lespedeza maximowiczii var. tricolor was similar to L. buergeri in terms of the structure and flower color, whereas the leaflet and bracteole shapes of var. tricolor were similar to those of var. maximowiczii. Based on the genetic structure (K = 3), var. tricolor had a mixed lineage with L. maximowiczii and L. buergeri. In addition, these formed a distinct lineage at K = 5. For two hybrids, the flower and leaflet structure in L. chiisanensis did not differ from those in L. maximowiczii, whereas the flowers of L. patentibicolor were within the range of variation of L. bicolor. In addition, L. chiisanensis and L. patentibicolor were assigned to L. maximowiczii and L. bicolor, respectively, based on the genetic structure. We treated var. tomentella and elongata as a forma, f. friebeana, because L. friebeana preceded var. tomentella, whereas var. tricolor was treated as a distinct species, L. tricolor. Lespedeza chiisanensis was recognized as a synonym of L. maximowiczii. Lespedeza patentibicolor was considered to be L. bicolor.

• Korean Journal of Plant Taxonomy
• /
• v.47 no.1
• /
• pp.27-45
• /
• 2017

A taxonomic study of the genus Hosta (Lilliaceae) in Korea was conducted based on morphological characteristics. Hosta clausa varieties share several characteristics (rhizomes with underground stolons, smooth scapes, and purple anthers). Hosta clausa var. normalis has an open perianth, long pistils, and fertile fruit. H. clausa var. clausa can be distinguished from H. clausa var. normalis by its closed perianth and sterile fruit. H. clausa var. geumgangensis has sterile fruit, green petioles, short pistils, and short narrow perianth tubes. H. clausa var. ensata has very narrow, sword-shaped leaves. It can be included in H. clausa var. normalis, which has a large degree of variation in leaf and petiole shape. H. jonesii has smooth scapes, yellow anthers, and bell-shaped flowers. It can be distinguished from the related species H. tsushimensis found on the Tushima islands in Japan by its wide perianth tube. H. yingeri is distinguished by its funnel-shaped flowers, 3 long and 3 short stamens, and smooth scape; the related species H. laevigata has 6 equally-sized stamens, narrowly lanceolate leaves, and wavy leaf margins. Because H. laevigata is not found in its type locality Isl. Heugsando, its taxonomic position must be determined at a later time. H. minor shares several characteristics (scapes with ridges and yellow-colored anthers) with the related taxa H. venusta. However, H. venusta is changed to H. minor var. venusta because it has overlapping characteristics in plant size, number of flowers, leaf size, and leaf shape. Consequently, the genus Hosta in Korea is classified into 5 species, 3 varieties, and 6 forms.

• Tunnel and Underground Space
• /
• v.30 no.5
• /
• pp.462-472
• /
• 2020

Rock classification is fundamental discipline of exploring geological and geotechnical features in a site, which, however, may not be easy works because of high diversity of rock shape and color according to its origin, geological history and so on. With the great success of convolutional neural networks (CNN) in many different image-based classification tasks, there has been increasing interest in taking advantage of CNN to classify geological material. In this study, a feasibility of the deep CNN is investigated for automatically and accurately identifying rock types, focusing on the condition of various shapes and colors even in the same rock type. It can be further developed to a mobile application for assisting geologist in classifying rocks in fieldwork. The structure of CNN model used in this study is based on a deep residual neural network (ResNet), which is an ultra-deep CNN using in object detection and classification. The proposed CNN was trained on 10 typical rock types with an overall accuracy of 84% on the test set. The result demonstrates that the proposed approach is not only able to classify rock type using images, but also represents an improvement as taking highly diverse rock image dataset as input.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.11a
• /
• pp.97-100
• /
• 2006

사상의학은 한의학의 독특하고 뛰어난 의료 체계이나 체질 감별에 객관성이 확보되지 않아 원래의 가치를 인정 받지 못하고 있다. 이를 위해 본 연구에서는 용모사기론을 기반으로 안면 형태학적 특징 분석을 통한 진단시스템을 만드는 것을 목표로 하고 있다. 이를 통해 정확하고 편리하게 체질을 분류 할수 있는 방법을 제시하고 정확한 사상체질 분류 진단기기의 개발을 위한 정면 얼굴과 측면 얼굴에서의 주요 영역을 추출하는 방법을 제안하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.05a
• /
• pp.141-144
• /
• 2008

본 논문에서는 세포영상을 분할하고 분류하는 알고리즘을 제안한다. 우선, 배경으로부터 세포를 분할한 후, 학습데이터로부터 얻은 Compactness, Smoothness, Moments와 같은 형태학적 특징을 추출한다. 전경세포들이 분할된 후에, 보다 정밀한 세포분석을 위해서 군집세포(Overlapped Cell)와 독립세포(Isolated Cell)를 분류 할 수 있는 알고리즘의 개발이 필수적이다. 이를 위해서 본 논문에서는 베이지안 네트워크와 각 노드에 대한 3개의 확률밀도함수를 사용하여 각 세포 영역을 분류한다. 분류된 군집세포영역은 향후 정확한 세포 분석을 위해서 군집세포가 포함하는 독립세포의 수만큼 마커를 찾고, Watershed 알고리즘과 병합과정을 거쳐 하나의 독립세포를 분리하게 된다. 현미경으로부터 얻은 세포영상에 대한 실험 결과는 이전 논문들에서 제안한 방법들과 비교했을 때, 각 군집세포의 독립세포로의 분리 이전에 세포영역에 대한 분류과정을 먼저 수행하였기 때문에 분할 성능이 크게 향상되었음을 확인할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.718-721
• /
• 2023

이미지 내 글꼴을 파악하는 것은 디자인 자료 제작, 저작권 확인 등 다양한 곳에서 중요한 문제이다. 하지만 이미지 내 한글 글꼴을 자동으로 식별하는 시스템은 아직 존재하지 않으며, 수동으로 한글 글꼴을 파악하는 것은 시간과 정확도 측면에서 매우 비효율적이다. 따라서 본 논문에서는 이미지 내 한글 글꼴을 자동으로 인식하는 시스템을 개발한다. 본 논문에서 개발한 시스템은 크게 두 가지 기법을 사용한다: (1) 한글의 기하학적인 특성을 활용하여 글자 단위로 텍스트를 인식하며, (2) 단어가 아닌 글자 단위로 글꼴을 분류하고 각 글자에 대한 글꼴 분류 결과를 종합하여 최종적인 글꼴 분류 결과를 얻는다. 10가지 한글 글꼴이 나타나는 직접 제작한 이미지를 사용하여 시스템의 성능을 평가한 결과 제안 방법은 비교 방법에 비해 더욱 정확히 한글 글꼴을 분류함을 확인하였다.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.316-319
• /
• 2021

우리는 과학기술 분야 논문 내 문장에 대해 논문의 의미 구조를 반영하는 수사학적 태그를 자동으로 부착하기 위한 분류 모델을 구축한다. 문장의 태그가 이전 문장의 태그와 상관관계를 갖는 특징을 반영하여 이전 문장을 추가 자질로 사용한다. 이전 문장을 추가 자질로 모델에 입력하기 위해 5 가지 결합 방법에 대한 실험을 진행한다. 실험 결과 각 문장에 대해 독립된 인코더를 사용하고 인코더의 결과 벡터를 concatenation 연산으로 조합하여 분류를 수행하는 것이 가장 높은 성능을 보이는 것을 확인하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.6 s.44
• /
• pp.1-8
• /
• 2006

Many researchers have been studied for the automatic chromosome karyotype classification and analysis. For the automatic classify the each chromosome which is the image in microscope, it is necessary to process the sub-procedure, ie. image pre-processing, implementing karyotype classifier. The image pre-processing proceeded the each chromosome separation, the noise exception and the feature parameter extraction. The extracted morphological feature parameter were the centromeric index(C.I.), the relative length ratio(R.L.), and the relative area ratio(R.A.). In this paper, the fuzzy classifier was implemented for the human chromosome karyotype classification. The extracted morphological feature parameter were used in the input parameter of fuzzy classifier. We studied about the selection of the membership function for the optimal fuzzy classifier in each chromosome groups.

• The KIPS Transactions:PartB
• /
• v.14B no.3 s.113
• /
• pp.153-162
• /
• 2007

Sasang medicine is peculiar medicine that constitution of a human classify four types and differ treatment method by physical constitution. In this way the most important thing is very difficult problem that classification of Sasang constitution and discriminate correctly. Therefore, in this paper targets diagnosis medical appliances development of hybrid form that can behave constitution classification and sees among for this paper to propose about method to grasp characteristic that is morphology about eye, nose, ear and mouth be based on appearance and manner of speaking. In this paper, classified and verified this for Sasang constitution through the QSCC II program at 1 step and present method that more exactly and conveniently analyzing measure each physical constitution feature by survey about eye, nose, ear and mouth at 2 steps. Also, extraction and analyze and verified main area of physical constitution classification based on front face and side face at 3 steps. Such propose method to extraction the principal face region based on face color from front face and side face for correct physical constitution classification diagnosis appliance development through experiment consideration and verification process.

• Journal of the Institute of Convergence Signal Processing
• /
• v.2 no.4
• /
• pp.22-30
• /
• 2001

In this paper we propose three classification algorithms to classify breast tumors that occur in duct into Benign, DCIS(ductal carcinoma in situ) NOS(invasive ductal carcinoma) The general approach for a creating classifier is composed of 2 steps: feature extraction and classification Above all feature extraction for a good classifier is very significance, because the classification performance depends on the extracted features, Therefore in the feature extraction step, we extracted morphology features describing the size of nuclei and texture features The internal structures of the tumor are reflected from wavelet transformed images with 10$\times$ and 40$\times$ magnification. Pariticulary to find the correlation between correct classification rates and wavelet depths we applied 1, 2, 3 and 4-level wavelet transforms to the images and extracted texture feature from the transformed images The morphology features used are area, perimeter, width of X axis width of Y axis and circularity The texture features used are entropy energy contrast and homogeneity. In the classification step, we created three classifiers from each of extracted features using discriminant analysis The first classifier was made by morphology features. The second and the third classifiers were made by texture features of wavelet transformed images with 10$\times$ and 40$\times$ magnification. Finally we analyzed and compared the correct classification rate of the three classifiers. In this study, we found that the best classifier was made by texture features of 3-level wavelet transformed images.