• Journal of Broadcast Engineering
• /
• v.18 no.3
• /
• pp.372-379
• /
• 2013

In this paper, we proposed a content-based image retrieval algorithm using local binary patterns and HSV color histogram. Images are retrieved using image input in image retrieval system. Many researches are based on global feature distribution such as color, texture and shape. These techniques decrease the retrieval performance in images which contained background the large amount of image. To overcome this drawback, the proposed method extract background fast and emphasize the feature of object by shrinking the background. The proposed method uses HSV color histogram and Local Binary Patterns. We also extract the Local Binary Patterns in quantized Hue domain. Experimental results show that the proposed method 82% precision using Corel 1000 database.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.11a
• /
• pp.290-293
• /
• 2003

다중 물체 추적은 움직이는 물체를 추출하고 검출된 정보와 물체 정보를 이용하여 움직임 궤도률 추적하는 것이다. 따라서 정확한 움직임 추적이 수행되려면 효율적인 물체의 추출이 선행 되어 져야 한다. 일반적으로 영상 분할 알고리즘은 다양한 증류의 영상에 대한 물체의 수학적 모델이 찌대로 설정되어 있지 않기 때문에 물체를 정확하게 분리해 내기 어렵다. 그러나 물체의 추출에 주로 처리 속도가 빠른 배경영상을 이용한 차(difference) 영상 기법과 반 자동 영상분할인 Snake Model이 갖는 Active Contour 알고리즘과 같이 물체 추출 과정에서 물체의 정의니 semantic 정보를 부여 한다면 개선된 영상 분할의 결과를 얻을 수 있다. 따라서 차 영상 기법과 semantic 정보를 가진 영상분할 알고리즘은 동영상에서 움직임 물체의 VOP(Video Object Plane)를 생성하는 매우 현실적인 방법이다. 본 논문에서는 영상의 상위 레벨Semantic 정보를 이용하기 위해 변형 Snake Model를 이용한 영상분할 방법을 이용하여 영상을 추출한다. 추출된 물체는 윤곽선(곡선) 정보와 함께 에지 성분의 기울기에서 얻은 특징 점을 이용하여 물체를 추적해 나간다.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.4
• /
• pp.866-876
• /
• 1996

A feature extraction method for the objects that have a circular cross section is proposed.To implement a robust recognition system which can effectively deal with various types of 2-dimensional image and 3-dimensional image, both 2- dimensional information and 3-dimensional information should be collectively extracted and combined for the optimum. For this, this paper presents a feature extraction method for 3-dimensional objects, particularly for the objects with a circular cross section which most objects in the real world are known to have. Firstly, the Z gradient is proposed to extract the shape information from those objects. Using this information, normal vectors are derived from the surface patches. The intersection points between the vectors are applied to the geometric feature extraction.Also, for more accurate recognition, a feature extraction method for between surface regions is proposed.Finally, the extraction method of function information is investigated for the final recognition process.The usefulness of the proposed method is proved through the experimentation.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.3
• /
• pp.621-629
• /
• 2016

This paper presents a decision method of middle ear disease which is developed in children and adults. In the proposed method, features are extracted from the middle ear disease images and normal images using HoG (histogram of oriented gradient) descriptor and the extracted features are learned by SVM (support vector machine) classifier. To obtain an input vector into SVM, an input image is resized to a predefined size and then the resized image is partitioned into 16 blocks each of which is partitioned into 4 sub-blocks (namely cell). Finally, the feature vector with 576 components is given by using HoG with 9 bins and it is used as SVM learning and classification. Input images are classified by SVM classifier based on the model of learning features. Experimental results show that the proposed method yields the precision of over 90% in decision.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.1
• /
• pp.57-64
• /
• 2013

In this paper, we propose the classification method of medicine bottle images using the features with color and size information. It is difficult to classify with size feature only, because there are many similar sizes of bottles. Therefore, we suggest a classification method based on color information, which robust to illumination variations. First, we extract MBR(Minimum Boundary Rectangle) of medicine bottle area using Binary Threshold of Red, Green, and Blue in image and classify images with size. Then, hue information and RGB color average rate are used to classify image, which features are robust to lighting variations. Finally, using SURF(Speed Up Robust Features) algorithm, corresponding image can be found from candidates with previous extracted features. The proposed method makes to reduce execution time and minimize the error rate and is confirmed to be reliable and efficient from experiment.

• Journal of KIISE
• /
• v.42 no.2
• /
• pp.203-212
• /
• 2015

This paper proposes a traffic sign recognition method in real road environments. The video stream in driving environments has two different characteristics compared to a general object video stream. First, the number of traffic sign types is limited and their shapes are mostly simple. Second, the camera cannot take clear pictures in the road scenes since there are many illumination changes and weather conditions are continuously changing. In this paper, we improve a modified census transform(MCT) to extract features effectively from the road scenes that have many illumination changes. The extracted features are collected by histograms and are transformed by the dense descriptors into very high dimensional vectors. Then, the high dimensional descriptors are encoded into a low dimensional feature vector by Fisher-vector coding and Gaussian Mixture Model. The proposed method shows illumination invariant detection and recognition, and the performance is sufficient to detect and recognize traffic signs in real-time with high accuracy.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.865-868
• /
• 2017

일반적으로 비디오로부터 캡션을 생성하는 작업은 입력 비디오로부터 특징을 추출해내는 과정과 추출한 특징을 이용하여 캡션을 생성해내는 과정을 포함한다. 본 논문에서는 효과적인 비디오 캡션 생성을 위한 심층 신경망 모델과 그 학습 방법을 소개한다. 본 논문에서는 입력 비디오를 표현하는 시각 특징 외에, 비디오를 효과적으로 표현하는 동적 의미 특징과 정적 의미 특징을 입력 특징으로 이용한다. 본 논문에서 입력 비디오의 시각 특징들은 C3D, ResNet과 같은 합성곱 신경망을 이용하여 추출하지만, 의미 특징은 본 논문에서 제안하는 의미 특징 추출 네트워크를 활용하여 추출한다. 그리고 이러한 특징들을 기반으로 비디오 캡션을 효과적으로 생성하기 위하여 선택적 주의집중 캡션 생성 네트워크를 제안한다. Youtube 동영상으로부터 수집된 MSVD 데이터 집합을 이용한 다양한 실험을 통해, 본 논문에서 제안한 모델의 성능과 효과를 확인할 수 있었다.

• Journal of the Korea Society of Computer and Information
• /
• v.6 no.1
• /
• pp.31-37
• /
• 2001

Human psychovisual phenomena involved in extracting features is more sensitive in dark regions than in bright regions Therefore, feature extracting operators should be considered local intensities in order to perceive objects analogous to human vision system. Generally, conventional feature extracting operators have some handicaps like an computational complexity or multivariable needs. In this paper a novel feature extracting operator is proposed to overcome these demerits. This operator could be implemented very simply and be proved good performances through experiments applied to synthetic and real images.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.01a
• /
• pp.227-228
• /
• 2013

본 논문에서는 연속적으로 입력되는 스테레오 입체 영상으로부터 2차원과 3차원의 특징을 결합하여 군집화함으로써 대상 물체를 보다 강건하게 분할하는 기법을 제안한다. 제안된 방법에서는 촬영된 장면의 좌우 영상으로부터 스테레오 정합 알고리즘을 이용해 영상의 각 화소별로 카메라와 물체 사이의 거리를 나타내는 깊이 특징을 추출한다. 그런 다음, 깊이와 색상 특징을 효과적으로 군집화하여 배경에 해당하는 영역을 제외하고, 전경에 해당하는 대상 물체를 감지한다. 실험에서는 제안된 방법을 여러가지 영상에 적용하여 테스트를 해 보았으며, 제안된 방법이 기존의 2차원 기반의 물체 분리 방법에 비해 보다 강건하게 대상물체를 분할함을 확인하였다.

• Journal of the Korean Society of Radiology
• /
• v.6 no.4
• /
• pp.305-311
• /
• 2012

This study compares the TE and UTE is to evaluate. We was programming by DWT of Matlab Tool-box for evaluation. M-program used feature value extract between TE Images and UTE Images. Two images using the extracted feature values were compared. Comparison of similar features two images phase was found to have value.