• 대한의용생체공학회:의공학회지
• /
• 제21권2호
• /
• pp.137-144
• /
• 2000

Clustered microcalcifications in X-ray mammograms are an important sign for the diagnosis of breast cancer. A shape-based method, which is based on the morphological features of clustered microcalcifications, is proposed for classifying clustered microcalcifications into benign or malignant categories. To verify the effectiveness of the proposed shape features, clinical mammograms were used to compare the classification performance of the proposed shape features with those of conventional textural features, such as the spatial gray-leve dependence method and the wavelet-based method. Image features extracted from these methods were used as inputs to a three-layer backpropagation neural network classifier. The classification performance of features extracted by each method was studied by using receiver operating-characteristics analysis. The proposed shape features were shown to be superior to the conventional textural features with respect to classification accuracy.

• Journal of Information Processing Systems
• /
• 제16권2호
• /
• pp.343-359
• /
• 2020

In this paper, a new algorithm is proposed for three-dimensional (3D) shape recognition using local features of model views and its sparse representation. The algorithm starts with the normalization of 3D models and the extraction of 2D views from uniformly distributed viewpoints. Consequently, the 2D views are stacked over each other to from view cubes. The algorithm employs the descriptors of 3D local features in the view cubes after applying Gabor filters in various directions as the initial features for 3D shape recognition. In the training stage, we store some 3D local features to build the prototype dictionary of local features. To extract an intermediate feature vector, we measure the similarity between the local descriptors of a shape model and the local features of the prototype dictionary. We represent the intermediate feature vectors of 3D models in the sparse domain to obtain the final descriptors of the models. Finally, support vector machine classifiers are used to recognize the 3D models. Experimental results using the Princeton Shape Benchmark database showed the average recognition rate of 89.7% using 20 views. We compared the proposed approach with state-of-the-art approaches and the results showed the effectiveness of the proposed algorithm.

• ETRI Journal
• /
• 제45권3호
• /
• pp.505-517
• /
• 2023

Color, texture, and shape act as important information for images in human recognition. For content-based image retrieval, many studies have combined color, texture, and shape features to improve the retrieval performance. However, there have not been many powerful methods for combining all color, texture, and shape features. This study proposes a content-based image retrieval method that uses the combined local and global features of color, texture, and shape. The color features are extracted from the color autocorrelogram; the texture features are extracted from the magnitude of a complete local binary pattern and the Gabor local correlation revealing local image characteristics; and the shape features are extracted from singular value decomposition that reflects global image characteristics. In this work, an experiment is performed to compare the proposed method with those that use our partial features and some existing techniques. The results show an average precision that is 19.60% higher than those of existing methods and 9.09% higher than those of recent ones. In conclusion, our proposed method is superior over other methods in terms of retrieval performance.

• 한국산업정보학회논문지
• /
• 제6권1호
• /
• pp.33-38
• /
• 2001

본 논문에서는 영상의 형태 특징을 이용한 영상 검색 시스템을 제안한다. 형태특징을 얻기 위해서 먼저 체인코드를 이용하여 경계선 추출을 추출하였다. 형태특징으로 객체의 경계선과 무게중심까지의 합, 표준편차 그리고 객체의 장축과 단축 비율 등을 추출하였다. 이러한 형태특징 정보를 이용하여 데이터 베이스에 저장된 영상과 질의 영상을 비교하여 유사도 순위에 따라 후보 영상들을 검색하였다. 본 실험의 결과 크기, 회전 이동 등의 변화에 둔감하였다. 약 170개의 폐곡선을 이루는 영상에 대한 검색 실험을 통하여 모양 정보에 대한 정확도를 측정하였다. 실험 결과 평균 Recall/Precision이 0.72/0.83를 보임으로써 제안된 방법이 유용함을 보였다.

• Journal of Biosystems Engineering
• /
• 제22권1호
• /
• pp.30-40
• /
• 1997

A computer vision system was built to automatically grade the leaf tobacco. A color image processing algorithm was developed to extract shape, color and texture features. An improved back propagation algorithm in an artificial neural network was applied to grade the Burley type dried leaf tobacco. The success rate of grading in three-grade classification(1, 3, 5) was higher than the rate of grading in six-grade classification(1, 2, 3, 4, 5, off), on the average success rate of both the twenty-five local pixel-set and the sixteen local pixel-set. And, the average grading success rate using both shape and color features was higher than the rate using shape, color and texture features. Thus, the texture feature obtained by the spatial gray level dependence method was found not to be important in grading leaf tobacco. Grading according to the shape, color and texture features obtained by machine vision system seemed to be inadequate for replacing manual grading of Burely type dried leaf tobacco.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2000년도 추계학술대회 논문집
• /
• pp.267-271
• /
• 2000

A part definition must not only provide shape information of a nominal part but also contain non-shape information such as tolerances, surface roughness and material attributes. Although machining features are useful for suitable shape information for process reasoning in the CAPP, they need to be integrated with tolerance information for effective process planning. We develop the tolerance modeler that efficiently integrates machining features with tolerance information for feature-based CAPP It is based on the association of machining features, tolerance features. and tolerances Tolerance features, where tolerances are assigned, are classified into two types; one is the face that is a topological entity on a solid model and the other is the functional geometry that is not referenced to topological entities. The functional geometry is represented by using machining features All the data for representing tolerance information with machining features are stored completely and unambiguously in the independent tolerance structure. The developed tolerance modeler is implemented as a module of a comprehensive feature-based CAPP system.

• 한국구조물진단유지관리공학회 논문집
• /
• 제25권5호
• /
• pp.135-140
• /
• 2021

본 연구에서는 일반강도 범위 콘크리트의 단면에서 골재 형상의 특성을 추출하고 이를 인공신경망과 이미지 프로세싱 기술에 적용하여 콘크리트의 압축강도를 예측하였다. 이를 위하여 면적, 둘레, 길이 등과 같은 일반적인 골재 형상 특성과 함께 골재의 거리-각도 특징을 수치적으로 표현하고 물성치 예측에 활용하였다. 그 결과, 콘크리트 압축강도에 영향을 미치는 주요변수를 사용하지 않고 단면의 골재 형상 특성만을 사용하여 압축강도 예측이 가능하였으며, 인공신경망 알고리즘 구축을 통해 예측 강도와 실제 강도의 상대오차 4.43% 이내의 범위에서 콘크리트 압축강도를 예측할 수 있었다. 본 연구에서 도출된 결과를 기반으로 골재의 거리-각도 특징을 활용하여 콘크리트의 유동성, 휨·인장강도 등 다양한 특성을 예측도 가능할 것으로 판단된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권12호
• /
• pp.3149-3165
• /
• 2013

Content based image retrieval is increasingly gaining popularity among image repository systems as images are a big source of digital communication and information sharing. Identification of image content is done through feature extraction which is the key operation for a successful content based image retrieval system. In this paper content based image retrieval system has been developed by adopting a strategy of combining multiple features of shape, color and relevance feedback. Shape is served as a primary operation to identify images whereas color and relevance feedback have been used as supporting features to make the system more efficient and accurate. Shape features are estimated through second derivative, least square polynomial and shapes coding methods. Color is estimated through max-min mean of neighborhood intensities. A new technique has been introduced for relevance feedback without bothering the user.

• 지능정보연구
• /
• 제18권3호
• /
• pp.1-12
• /
• 2012

길 옆이나 공원 또는 조경시설에는 많은 나무들을 포함하고 있다. 비록 많은 나무들이 쉽게 우리 주변에서 보이지만, 일반인들이 그 나무의 이름, 종류 및 정보들을 얻기가 힘든 경우도 있다. 나무의 이름이나 정보를 얻기 위하여 인터넷이나 서적을 이용하여 찾아 분류하여야 한다. 나무의 구성 요소는 잎, 꽃, 수피 등이 있는데, 일반적으로 나무의 잎을 이용하여 분류할 수 있다. 이는 잎이 형태, 잎맥 등의 정보를 포함하고 있기 때문이다. 잎의 형태는 나무의 종류를 결정하는데 중요한 역할을 하며, 또한 잎맥을 포함한 텍스쳐도 나무의 종류를 분류하는데 유용하게 사용된다. 본 논문에서는 형태와 텍스쳐를 조합한 특징들을 이용한 잎 분류 시스템에 대한 성능을 평가하였다. 형태 특징으로는 푸리에 기술자를 이용하였고, 텍스쳐 특징으로는 GLCM 또는 웨이브릿 기술자, 그리고 그들의 조합을 사용하였다. 그리고 사용된 데이터는 인터넷에서 용이하게 구할 수 있고, 분류 성능평가에 사용되는 Flavia 잎 데이터 셋을 사용하였다. 형태와 텍스쳐를 기반으로 하는 다양한 조합을 가진 분류 시스템의 성능을 인식률과 PR(precision-recall) 지수로 평가하고, 성능을 비교하였다. 성능평가 결과, 형태와 텍스쳐를 조합한 특징들을 갖는 시스템의 성능이 조합하지 않은 시스템의 성능보다 나아짐을 알 수 있었다.

• 한국실내디자인학회논문집
• /
• 제19권6호
• /
• pp.20-29
• /
• 2010

Art historians and critics have defined the style as common features appeared in a class of objects. Abstract common features from a set of objects have been used as a bench mark for date and location of original works. Commonalities in shapes are identified by relationships as well as physical properties from shape descriptions. This paper will focus on how the computer and human can recognize common shape properties from a class of shape objects to learn design knowledge. Shape representation using schema theory has been explored and possible inductive generalization from shape descriptions has been investigated. Also learned shape knowledge can be used. for new design process as design concept. Several design process such as parametric design, replacement design, analogy design etc. are used for these design processes. Works of Mario Botta and Louis Kahn are analyzed for explicitly clarifying the process from conceptual ideas to final designs. In this paper, theories of computer science, artificial intelligence, cognitive science and linguistics are employed as important bases.