• 정보처리학회논문지B
• /
• 제10B권7호
• /
• pp.823-828
• /
• 2003

이 논문의 주요 목적은 내용을 기반으로 하는 이미지 검색에서 이미지 객체의 외형특징을 추출하는 방법을 제시하는 것이다. 대부분의 실질적인 객체들의 외형은 불규칙적이고, 이러한 객체를 수치화하기위한 일반적인 방법은 없다. 특히 전자 카타로그들은 상품들을 나타내는 많은 이미지를 포함하고 있다. 이 논문에서는 이미지 전체가 아닌 이미지내의 개별 객체들을 기반으로 특징을 추출하는 방법을 제시한다. 왜냐하면 제시된 방법은 한 이미지내에서 RLC lines을 사용하여 각 객체들의 외형을 기반으로하는 방법을 사용하기 때문이다. 실험결과는 일반적으로 가장 많이 사용하는 특징인 Texture와 비교를 했고 제시된 외형을 나타내는 변수들이 전자카타로그의 이미지 객체들을 뚜렷하게 나타냈고, 보다 정확하게 객체들을 분류하고 구별하였다.

• 대한방사선기술학회지:방사선기술과학
• /
• 제42권2호
• /
• pp.119-130
• /
• 2019

Positron emission tomography (PET) is widely used imaging modality for effective and accurate functional testing and medical diagnosis using radioactive isotopes. However, PET has difficulties in acquiring images with high image quality due to constraints such as the amount of radioactive isotopes injected into the patient, the detection time, the characteristics of the detector, and the patient's motion. In order to overcome this problem, we have succeeded to improve the image quality by using the dynamic image reconstruction method based on singular value decomposition. However, there is still some question about the characteristics of the proposed technique. In this study, the characteristics of reconstruction method based on singular value decomposition was estimated over computational simulation. As a result, we confirmed that the singular value decomposition based reconstruction technique distinguishes the images well when the signal - to - noise ratio of the input image is more than 20 decibels and the feature vector angle is more than 60 degrees. In addition, the proposed methode to estimate the characteristics of reconstruction technique can be applied to other spatio-temporal feature based dynamic image reconstruction techniques. The deduced conclusion of this study can be useful guideline to apply medical image into SVD based dynamic image reconstruction technique to improve the accuracy of medical diagnosis.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1991년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 22-24 Oct. 1991
• /
• pp.1192-1197
• /
• 1991

This paper describes a method of extracting the 3-D coordinates of feature points of an object from two images taken by one camera. The first image is from a CCD camera before approaching the object and the second image is from same camera after approaching the object along the optical axis. In the two images, the feature points appear at different position on the screen due to image enlargement. From the change of positions of feature points their world coordinates are calculated. In this paper, the correspondence problem is solved by image shrinking and correlation.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.2108-2111
• /
• 2003

This paper introduces a new local feature extraction method and image matching method for the localization and classification of targets. Proposed method is based on the block-by-block projection associated with directional pattern of blocks. Each pattern has its own eigen-vertors called as CEBs(Classified Eigen-Blocks). Also proposed block-based image matching method is robust to translation and occlusion. Performance of proposed feature extraction and matching method is verified by the face localization and FLIR-vehicle-image classification test.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 1999년도 춘계종합학술대회
• /
• pp.50-54
• /
• 1999

본 논문에서는 영상의 다양한 특징 정보 중에서 색상 특징과 모양 특징을 이용한 영상 검색 시스템을 제안한다. 색상 특징은 지역별 색상 분포 히스토그램을 추출하고, 각 지역의 히스토그램 중에 가장 큰 값을 가지는 4개의 값을 특징 정보로 이용한다. 모양 특징을 추출하기 위한 전처리 과정은 경계면 추출과정, 경계면에 대한 무게 중심 추출 과정, angular sampling 과정으로 구성되고, 무게 중심으로부터 경계면까지의 거리의 합, 표준 편차, 장축/단축 비율을 특징 정보로 이용한다. 각 질의 영상들의 특징 정보와 데이터베이스에 저장된 영상들의 특징 정보들 비교하여 유사도 순위에 따라 후보영상들이 검색된다. 200개의 폐곡선을 이루는 상표영상에 대한 검색 실험을 통하여 색상 정보와 모양 정보에 대한 정확도를 측정하였다. 실험 결과 평균 Recall/Precision이 0.72/0.83를 보임으로써 제안된 방법이 유용함을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권12호
• /
• pp.4835-4848
• /
• 2020

The recent expansion of the digital content market is increasing the technical demand for various facial image transformations within the virtual environment. The recent image translation technology enables changes between various domains. However, current image-to-image translation techniques do not provide stable performance through unsupervised learning, especially for shape learning in the face transition field. This is because the face is a highly sensitive feature, and the quality of the resulting image is significantly affected, especially if the transitions in the eyes, nose, and mouth are not effectively performed. We herein propose a new unsupervised method that can transform an in-wild face image into another face style through radical transformation. Specifically, the proposed method applies two face-specific feature loss functions for a generative adversarial network. The proposed technique shows that stable domain conversion to other domains is possible while maintaining the image characteristics in the eyes, nose, and mouth.

• Journal of Electrical Engineering and Technology
• /
• 제13권5호
• /
• pp.2099-2106
• /
• 2018

This study presents a novel approach of discriminative feature vectors based on manifold learning using nonlinear dimension reduction (DR) technique to improve loss function, and combine with the Adversarial examples to regularize the object function for image classification. The traditional convolutional neural networks (CNN) with many new regularization approach has been successfully used for image classification tasks, and it achieved good results, hence it costs a lot of Calculated spacing and timing. Significantly, distrinct from traditional CNN, we discriminate the feature vectors for objects without empirically-tuned parameter, these Discriminative features intend to remain the lower-dimensional relationship corresponding high-dimension manifold after projecting the image feature vectors from high-dimension to lower-dimension, and we optimize the constrains of the preserving local features based on manifold, which narrow the mapped feature information from the same class and push different class away. Using Adversarial examples, improved loss function with additional regularization term intends to boost the Robustness and generalization of neural network. experimental results indicate that the approach based on discriminative feature of manifold learning is not only valid, but also more efficient in image classification tasks. Furthermore, the proposed approach achieves competitive classification performances for three benchmark datasets : MNIST, CIFAR-10, SVHN.

• 한국컴퓨터정보학회논문지
• /
• 제24권1호
• /
• pp.85-92
• /
• 2019

In this paper, we propose a efficient feature point extraction method that can solve the problem of performance degradation by introducing a preprocessing process when extracting feature points by utilizing the characteristics of 360-degree realistic media. 360-degree realistic media is composed of images produced by two or more cameras and this image combining process is accomplished by extracting feature points at the edges of each image and combining them into one image if they cover the same area. In this production process, however, the stitching process where images are combined into one piece can lead to the distortion of non-seamlessness. Since the realistic media of 4K-class image has higher resolution than that of a general image, the feature point extraction and matching process takes much more time than general media cases.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2001년도 추계학술대회 학술발표 논문집
• /
• pp.203-207
• /
• 2001

In this Paper, we propose the neural network based emotion recognition method for intelligently recognizing the human's emotion using CCD color image. To do this, we first acquire the color image from the CCD camera, and then propose the method for recognizing the expression to be represented the structural correlation of man's feature Points(eyebrows, eye, nose, mouse) It is central technology that the Process of extract, separate and recognize correct data in the image. for representation is expressed by structural corelation of human's feature Points In the Proposed method, human's emotion is divided into four emotion (surprise, anger, happiness, sadness). Had separated complexion area using color-difference of color space by method that have separated background and human's face toughly to change such as external illumination in this paper. For this, we propose an algorithm to extract four feature Points from the face image acquired by the color CCD camera and find normalization face picture and some feature vectors from those. And then we apply back-prapagation algorithm to the secondary feature vector. Finally, we show the Practical application possibility of the proposed method.

• 한국정보처리학회논문지
• /
• 제5권11호
• /
• pp.2776-2785
• /
• 1998

내용 기반 영상 검색 기술은 전자 미술관과 박물관, 상표와 저작권, 영상 저장 및 전송 시스템과 같은 대용량의 멀티미디어 데이터베이스를 구축하고 유지하는데 필수적인 요소이다. 따라서 내용 기반 검색에 대한 연구가 최근 몇 년 동안 큰 관심을 모으고 있다. 본 논문에서는 영상 검색을 위한 특징으로서 칼라 정보와 모양 정보를 동시에 고려하는 복합적인 특징 벡터를 사용한 검색 기법을 제안하였다. 칼라 정보 획득을 위해서는 지역 칼라 분포 특성을 고려하여, 영상을 이루는 각 부영역별 화소들의 대수적 모멘트를 이용하여 각 특징 산출하였다. 모양 정보를 획득하기 위해서는 향상된 불변 모멘트를 사용함으로써 연산량을 줄이면서 검색의 효율을 증대시켰 다. 그리고 모양 특징 추출을 위한 전처리 과정에서 칼라 영상을 그레이 영상으로 변형한 후, 구현이 용이하고 실시간 윤곽선 추출이 가능한 DCT 알고리즘을 변형 이용하였다. 실험영상으로 150여개의 자동차 영상을 사용하여 기존 방법들과의 비교 실험을 통해 향상된 검색 결과를 얻을 수 있었다.