• 전자공학회논문지S
• /
• 제34S권10호
• /
• pp.104-111
• /
• 1997

It is known as a difficult problem to recognize text-background mixed documents. In this paper a new string extraction algorithm, using mathematical morphology for the document consisting of text and overlapped periodic background pattern, is proposed. The algorithm consists of pattern periodicity feature extraction and background removal. The extracted pattern periodicity feature is used to determine the shape of structuring elements for morphological pre- and post-processing to remove background. The effectiveness of the proposed algorithm over the existing one is also verified through the experiments with various test documents.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제9권3호
• /
• pp.172-177
• /
• 2009

In this paper, a new morphology-based homomorphic filtering technique is presented to enhance features in medical images. The homomorphic filtering is performed based on the morphological sub-bands, in which an image is morphologically decomposed. An evolutionary design is carried to find an optimal gain and structuring element of each sub-band. As a search algorithm, Differential Evolution scheme is utilized. Simulations show that the proposed filter improves the contrast of the interest feature in medical images.

• 한국정보통신학회논문지
• /
• 제8권3호
• /
• pp.714-720
• /
• 2004

얼굴검출 작업에서 다양한 형태를 가지는 후보영역을 정사하기 위한 기하학적 연산과정이 수반된다. 본 논문에서는 컬러영상에서 색도 분포 특성을 이용함으로써 얼굴가림과 방향에 영향을 받지 않고 얼굴 유효특징점을 검출할 수 있는 알고리즘을 제안한다. 제안한 알고리즘은 얼굴의 특징점 주변에서 Cb와 Cr이 일관적인 색도차를 가진다는 점에 착안한 것으로써, 기본 색도차 영상인 Eye맵 마스크에서 특징점을 효과적으로 강조시킬 수 있는 평균-그레이 모폴로지 연산을 수행한다. 실험을 통해, 제안한 방법이 가변적 형태의 후보영역에 대해서도 강인하게 얼굴의 유효특징점을 검출할 수 있음을 확인할 수 있었다.

• 융합신호처리학회논문지
• /
• 제2권4호
• /
• pp.22-30
• /
• 2001

본 논문은 유방질환 중에서 유관(duct )에 발생하는 유방종양을 Benign, DCIS(ductal carcinoma in situ) NOS (invasive ductal carcinoma)로 분류하기 위해 3가지 분류기 (classifier) 를 생성한 후, 비교 분석하였다. 분류기 생성에서 가장 중요한 단계인 특징 추출 단계에서 세포핵의 기하학적 특징을 형태학적 특징을 추출하여 분류기를 생성하고 염색질 패턴의 내부적 변화를 나타내는 질감 특징을 추출하여 2가지 배율(100/400배)에서 2개의 분류기를 생성하였다. 400배 배율의 유방질환 영상에서 세포핵을 추출하여 핵의 형태학적 특징값인 핵의 면적, 둘레. 가로, 세로(장. 단축) 의 길이, 원형성의 비율을 구한 후 이 특징값들을 조합하여 판별분석에 의해 분류기를 생생하고, 분류 정확도를 검증하였다. 100배 배율과 400배의 배율의 유방질환 영상에서 1, 2, 3, 4 단계(level)의 wavelet 변환를 적용한 후, 분할된 서브밴드에서 GLCM(Gray Level Co-occurrence Matrix)을 이용하여 질감 특징(entropy Energy, Contrast, Homogeneity)를 추출하고, 이 특징값들을 조합하여 판변 분석에 의해 분류기를 생성한 후 분류 정확도를 검증하였다. 이 세 분류기를 비교 분석 하였을때 현민경 100배 배율의 영상을 3단계 wavelet 변환을 적용하고 질감 특징을 추출하여 생성한 분류기가 다른 두 분류기보다 유방 질환 Benign, DCIS; NOS를 분류하는데 더 나은 결과를 보였다.

• 대한의용생체공학회:의공학회지
• /
• 제42권5호
• /
• pp.232-240
• /
• 2021

Heterogeneity in cancer is the major obstacle for precision medicine and has become a critical issue in the field of a cancer diagnosis. Many attempts were made to disentangle the complexity by molecular classification. However, multi-dimensional information from dynamic responses of cancer poses fundamental limitations on biomolecular marker-based conventional approaches. Cell morphology, which reflects the physiological state of the cell, can be used to track the temporal behavior of cancer cells conveniently. Here, we first present a hybrid learning-based platform that extracts cell morphology in a time-dependent manner using a deep convolutional neural network to incorporate multivariate data. Feature selection from more than 200 morphological features is conducted, which filters out less significant variables to enhance interpretation. Our platform then performs unsupervised clustering to unveil dynamic behavior patterns hidden from a high-dimensional dataset. As a result, we visualize morphology state-space by two-dimensional embedding as well as representative morphology clusters and trajectories. This cell morphology profiling strategy by hybrid learning enables simplification of the heterogeneous population of cancer.

• 한국윤활학회:학술대회논문집
• /
• 한국윤활학회 1998년도 제27회 춘계학술대회
• /
• pp.314-320
• /
• 1998

Wear debris morphology is closely related to the wear mode and mechanism occured. Image recognition of wear debris is, therefore, a powerful tool in wear monitoring. But it has usually required expert's experience and the results could be too subjective. Development of automatic tools for wear debris recognition is needed to solve this problem. In this work, an algorithm for automatic wear debris recognition was suggested and implemented by PC base software. The presented method defined a characteristic 3-dimensional feature space where typical types of wear debris were separately located by the knowledge-based system and compared the similarity of object wear debris concerned. The 3-dimensional feature space was obtained from multiple feature vectors by using a multi-dimensional scaling technique. The results showed that the presented automatic wear debris recognition was satisfactory in many cases application.

• Tribology and Lubricants
• /
• 제15권2호
• /
• pp.206-211
• /
• 1999

Wear debris morphology is closely related to the wear mode and mechanism occured. Image recognition of wear debris is, therefore, a powerful tool in wear monitoring. But it has usually required expert's experience and the results could be too subjective. Development of automatic tools for wear debris recognition is needed to solve this problem. In this work, an algorithm for automatic wear debris recognition was suggested and implemented by PC base software. The presented method defined a characteristic 3-dimensional feature space where typical types of wear debris were separately located by the knowledge-based system and compared the similarity of object wear debris concerned. The 3-dimensional feature space was obtained from multiple feature vectors by using a multi-dimensional scaling technique. The results showed that the presented automatic wear debris recognition was satisfactory in many cases application.

• 한국군사과학기술학회지
• /
• 제11권4호
• /
• pp.124-132
• /
• 2008

In this paper, a dynamical filter called the Highest Probability Data Association Filter(HPDAF) improved by adding target feature information is proposed for robust target detection and tracking in clutter. IIR contains 2-dimensional kinematic coordinate, intensity, and feature information. In data association of the HPDAF for track initiation, feature information is utilized in addition to coordinate and intensity information. The performance of the proposed HPDA algorithm is tested and compared with the conventional HPDAF algorithm for track initiation by a series of Monte Carlo simulation runs for a 3-dimensional missile-target engagement. scenario.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 The Third Asian Fuzzy Systems Symposium
• /
• pp.745-749
• /
• 1998

Mathematical morphology (MM) has been introduced as a powerful tool for studying the geometrical properties of images, MM is a good approach to digital image processing , which is based on the shape feature. The MM operators such as dilation, erosion, closing and opening have been applied successfully to image noise reduction. The MM filters can easily filter the noise when the noise factors are known. However it is very difficult to reduce the noise when images are ambiguous, because the boundary between the noise and object is vague. In this paper, we propose a new method to reduce noise from ambiguous images by using Fuzzy Mathematical Morphology (FMM) operators. Performance evaluation via simulations show that the FMM filters efficiently reduce the image noise. Furthermore, the FMM filters show a good performance compared with the conventional filters.

• 한국자원식물학회:학술대회논문집
• /
• 한국자원식물학회 2019년도 춘계학술대회
• /
• pp.78-78
• /
• 2019

Gnaphalium L. is a small herbaceous genus comprising up to 80 species in worldwide (Asia, North to South America, Africa, and Oceania). This genus is highly polymorphic which embrace uncommon broad morphological boundary, and thus further studies were needed to proper taxonomic delimitations for the genus and its relatives. Gnaphalium uliginosum L. was usually found in moist sites such as margins of lake, pond, reservoir, stream banks and paddy field. This squat plant is solely known species in Korean Gnaphalium. During the revisionary study of the tribe Gnaphalieae (Asteraceae) in Korea, however, we found several materials in domestic herbaria (e.g., SNU, KWNU) that identified as G. uliginosum or Gamochaeta pensylvanica (Willd.) Cabrera collected from central to northern Korea, but clearly differ to the morphology of G. uliginosum. The external morphology of the materials is seemingly the only feature at odds with G. uliginosum. However, its morphological characters such as tall erected stems (ca. 30cm), hairs on seeds and whitish tomentose hairs on the whole plants are easily distinguished from G. uliginosum, and rather it looks like G. tranzschelii Kirp. Although the name G. tranzschelii have been treated as synonym of G. uliginosum by several authors, its distinct morphology might be sufficient to separate to two independent taxa. Generally, the morphological polymorphisms and hybridization of G. uliginosum complicate the taxonomy of the species, and thus further investigation for their habitat, distribution and morphology were needed to their taxonomic entity.