• 지능정보연구
• /
• 제18권2호
• /
• pp.47-60
• /
• 2012

비디오 데이터는 구조화되지 않은 복합 데이터의 형태를 지닌다. 이러한 비디오 데이터의 효율적인 관리 및 검색을 위한 비디오 데이터 구조화의 중요성이 대두되면서 콘텐츠 내 시각적 특징을 기반으로 비디오 씬(scene)을 탐지하고자 하는 연구가 활발히 진행되었다. 기존의 연구들은 주로 색상 정보만을 이용하여 샷(shot) 간의 유사도 평가를 기반한 클러스터링(clustering)을 통해 비디오 씬을 탐지하고자 하였다. 하지만 비디오 데이터의 색상 정보는 노이즈(noise)를 포함하고, 특정 사물의 개입 등으로 인해 급격하게 변화하기 때문에 색상만을 특징으로 고려할 경우, 비디오 샷 혹은 씬에 대한 올바른 식별과 디졸브(dissolve), 페이드(fade), 와이프(wipe)와 같은 화면의 점진적인 전환(gradual transitions) 탐지는 어렵다. 이러한 문제점을 해결하기 위해, 본 논문에서는 프레임(frame)의 컬러 히스토그램과 코너 에지, 그리고 객체 컬러 히스토그램에 해당하는 시각적 특징을 기반으로 동일한 이벤트를 구성하는 의미적으로 유사한 샷의 클러스터링을 통해 비디오 씬을 탐지하는 방법(Scene Detector by using Color histogram, corner Edge and Object color histogram, SDCEO)을 제안한다. SDCEO는 샷 바운더리 식별을 위해 컬러 히스토그램 분석 단계에서 각 프레임의 컬러 히스토그램 정보를 이용하여 1차적으로 연관성 있는 연속된 프레임을 샷 바운더리로 병합한 후, 코너 에지 분석 단계에서 병합된 샷 내 처음과 마지막 프레임의 코너 에지 특징 비교를 통하여 샷 바운더리를 정제하여 최종 샷을 식별한다. 키프레임 추출 단계에서는 샷 내 프레임간 유사도 비교를 통해 모든 프레임과 가장 유사한 프레임을 각 샷을 대표하는 키프레임으로 추출한다. 그 후, 비디오 씬 탐지를 위해, 컬러 히스토그램과 객체 컬러 히스토 그램에 해당하는 프레임의 시각적 특징을 기반으로 상향식 계층 클러스터링 방법을 이용하여 의미적인 연관성을 지니는 샷의 군집화를 통해 비디오 씬을 탐지하는 방법이다. 본 논문에서는 SDCEO의 프로토 타입을 구축하고 3개의 비디오 데이터를 이용한 실험을 통하여 SDCEO의 효율성을 평가하였고 샷 바운더리 식별의 성능의 정확도는 평균 93.3%, 비디오 씬 탐지 성능의 정확도는 평균 83.3%로 만족할만한 성능을 보였다.

• Journal of Multimedia Information System
• /
• 제2권1호
• /
• pp.171-178
• /
• 2015

This article describes 3 dimensional (3D) face recognition system using histogram of oriented gradients (HOG) based on face curvature. The surface curvatures in the face contain the most important personal feature information. In this paper, 3D face images are recognized by the face components: cheek, eyes, mouth, and nose. For the proposed approach, the first step uses the face curvatures which present the facial features for 3D face images, after normalization using the singular value decomposition (SVD). Fisherface method is then applied to each component curvature face. The reason for adapting the Fisherface method maintains the surface attribute for the face curvature, even though it can generate reduced image dimension. And histogram of oriented gradients (HOG) descriptor is one of the state-of-art methods which have been shown to significantly outperform the existing feature set for several objects detection and recognition. In the last step, the linear discriminant analysis is explained for each component. The experimental results showed that the proposed approach leads to higher detection accuracy rate than other methods.

• 한국멀티미디어학회논문지
• /
• 제18권12호
• /
• pp.1519-1527
• /
• 2015

TFT-LCD automatic defect inspection system for detecting defects in place of the visual tester does pre-processing, candidate defect pixel detection, and recognition and classification through a blob analysis. An over-detection result of defects acts as an undue burden of blob analysis for recognition and classification. In this paper, we propose defect detection method based on the histogram distribution modeling of TFT-LCD image to minimize over-detection of candidate defective pixels. Primary defect candidate pixels are detected estimating the skewness of the luminance distribution histogram of the background pixels. Based on the detected defect pixels, the defective pixels other than noise pixels are detected using the distribution histogram model of the local area. Experimental results confirm that the proposed method shows an excellent defect detection result on the image containing the various types of defects and the reduction of the degree of over-detection as well.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.912-919
• /
• 2022

The study is an image-based assessment that uses image processing techniques to determine the condition of concrete with surface cracks. The preparations of the dataset include resizing and image filtering to ensure statistical homogeneity and noise reduction. The image dataset is then segmented, making it more suited for extracting important features and easier to evaluate. The image is transformed into grayscale which removes the hue and saturation but retains the luminance. To create a clean edge map, the edge detection process is utilized to extract the major edge features of the image. The Otsu method is used to minimize intraclass variation between black and white pixels. Additionally, the median filter was employed to reduce noise while keeping the borders of the image. Image processing techniques are used to enhance the significant features of the concrete image, especially the defects. In this study, the tonal zones of the histogram and its properties are used to analyze the condition of the concrete. By examining the histogram, the viewer will be able to determine the information on the image through the number of pixels associated and each tonal characteristic on a graph. The features of the five tonal zones of the histogram which implies the qualities of the concrete image may be evaluated based on the quality of the contrast, brightness, highlights, shadow spikes, or the condition of the shadow region that corresponds to the foreground.

• 방송공학회논문지
• /
• 제14권4호
• /
• pp.397-408
• /
• 2009

In this paper, we present a non-static color histogram method to retrieve clothing images that are similar to a query clothing. Given clothing area, our method automatically extracts major colors by using the octree-based quantization approach[16]. Then, a color palette that is composed of the major colors is generated. The feature of each clothing, which can be either a query or a database clothing image, is represented as a color histogram based on its color palette. We define the match color bins between two possibly different color palettes, and unify the color palettes by merging or deleting some color bins if necessary. The similarity between two histograms is measured by using the weighted Euclidean distance between the match color bins, where the weight is derived from the frequency of each bin. We compare our method with previous histogram matching methods through experiments. Compared to HSV cumulative histogram-based approach, our method improves the retrieval precision by 13.7 % with less number of color bins.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2015년도 춘계학술대회
• /
• pp.571-575
• /
• 2015

실시간으로 입력되는 영상으로부터 이동객체의 움직임 특징을 분석하는 시간적 히스토그램 기반의 행동패턴분석 알고리즘을 제안한다. 이동객체의 추적 및 분석을 위해 배경과 이동객체를 분리하는 배경학습을 행한다. 배경학습으로 추출된 이동객체는 무게중심 및 좌표연관성을 이용하여 객체를 식별한 후 객체별 추적을 행한다. 추적된 각 객체의 시작프레임, 종료프레임, 좌표정보, 크기정보를 연결리스트에 저장하여 관리한다. 시간적 히스토그램은 x, y좌표와 시간을 이용해 움직임 특징 패턴을 정의한 것으로 각 객체의 좌표정보와 비교하여 움직임특징 및 행동패턴을 파악한다. 시간적 히스토그램 기반 행동패턴분석시스템은 자체 수집한 데모영상에 대한 실험을 통해 초당 45~50 fps의 높은 처리속도를 유지하며 95%이상의 높은 추적율을 확인하였다.

• Journal of applied mathematics & informatics
• /
• 제27권1_2호
• /
• pp.175-182
• /
• 2009

Microscopic imaging system often requires the algorithm to adjust location of camera lenses automatically in machine level. An effort to detect the best focal point is naturally interpreted as a mathematical inverse problem [1]. Following Wiener's point of view [2], we interpret the focus level of images as the quantified factor appeared in image degradation model: g = $f{\ast}H+{\eta}$, a standard mathematical model for understanding signal or image degradation process [3]. In this paper we propose a simple, very fast and robust method to compare the degradation parameters among the multiple images given by introducing outlier analysis of histogram.

• Journal of the Korean Wood Science and Technology
• /
• 제26권2호
• /
• pp.29-37
• /
• 1998

An image analysis program with the function of measuring various quantitative characteristics in the transverse surface of wood was developed using Delphi 2.0. Data on pore characteristics (conditions for image processing, proportion of pores in relationship to other elements, tangential diameter, area, tangential and radial diameter, x and y coordinates of pore center, and geometric coefficients) were saved in text file format. In addition, the pore area histogram in the tangential and radial directions was saved as a BMP (bitmap) type file. Analyses indicated that quantitative characteristics such as the relative radial distribution of pores in a growth ring, pore tangential area histogram, and proportion of pore in lumen area appear to be useful in separating four diffuse-porous woods and four ring-porous woods on the species level.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.396-399
• /
• 2009

In this paper, we present a method to define a color similarity between color images using Octree-based quantization and similar color integration. The proposed method defines major colors from each image using Octree-based quantization. Two color palettes to consist of major colors are compared based on Euclidean distance and similar color bins between palettes are matched. Multiple matched color bins are integrated and major colors are adjusted. Color histogram based on the color palette is constructed for each image and the difference between two histograms is computed by the weighted Euclidean distance between the matched color bins in consideration of the frequency of each bin. As an experiment to validate the usefulness, we discriminated the same clothing from CCD camera images based on the proposed color similarity analysis. We retrieved the same clothing images with the success rate of 88 % using only color analysis without texture analysis.

• International Journal of Contents
• /
• 제9권3호
• /
• pp.1-9
• /
• 2013

In this paper, we propose a fast and accurate system for detecting pedestrians from a static image. Histogram of Oriented Gradients (HOG) is a well-known feature for pedestrian detection systems but extracting HOG is expensive due to its high dimensional vector. It will cause long processing time and large memory consumption in case of making a pedestrian detection system on high resolution image or video. In order to deal with this problem, we use Principal Components Analysis (PCA) technique to reduce the dimensionality of HOG. The output of PCA will be input for a linear SVM classifier for learning and testing. The experiment results showed that our proposed method reduces processing time but still maintains the similar detection rate. We got twenty five times faster than original HOG feature.