• 한국측량학회지
• /
• 제37권5호
• /
• pp.323-330
• /
• 2019

Radiometric normalization with multi-temporal satellite images is essential for time series analysis and change detection. Generally, relative radiometric normalization, which is an image-based method, is performed, and histogram matching is a representative method for normalizing the non-linear properties. However, since it utilizes global statistical information only, local information is not considered at all. Thus, this paper proposes a histogram matching method considering local information. The proposed method divides histograms based on density, mean, and standard deviation of image intensities, and performs histogram matching locally on the sub-histogram. The matched histogram is then further partitioned and this process is performed again, iteratively, controlled with the wasserstein distance. Finally, the proposed method is compared to global histogram matching. The experimental results show that the proposed method is visually and quantitatively superior to the conventional method, which indicates the applicability of the proposed method to the radiometric normalization of multi-temporal images with non-linear properties.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.304-306
• /
• 2007

Methods of Object recognition from camera image are to compare features of color. edge or pattern with model in a general way. SIFT(scale-invariant feature transform) has good performance but that has high complexity of computation. Using simple color histogram has low complexity. but low performance. In this paper we represent a model as a color cooccurrence histogram. and we improve performance using pyramid matching. The color cooccurrence histogram keeps track of the number of pairs of certain colored pixels that occur at certain separation distances in image space. The color cooccurrence histogram adds geometric information to the normal color histogram. We suggest object recognition by pyramid matching of color cooccurrence histogram.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2008년도 학술대회 1부
• /
• pp.517-521
• /
• 2008

Hand motion classification problem is considered as basis for sign or gesture recognition. We promote optical flow as main feature extracted from images sequences to simultaneously segment the motion's area by its magnitude and characterize the motion' s directions by its orientation. We manage the flow orientation histogram as motion descriptor. A motion is encoded by concatenating the flow orientation histogram from several frames. We utilize simple histogram matching to classify the motion sequences. Attempted experiments show the feasibility of our method for hand motion localization and classification.

• ETRI Journal
• /
• 제24권1호
• /
• pp.23-30
• /
• 2002

MPEG-7 Visual Standard specifies a set of descriptors that can be used to measure similarity in images or video. Among them, the Edge Histogram Descriptor describes edge distribution with a histogram based on local edge distribution in an image. Since the Edge Histogram Descriptor recommended for the MPEG-7 standard represents only local edge distribution in the image, the matching performance for image retrieval may not be satisfactory. This paper proposes the use of global and semi-local edge histograms generated directly from the local histogram bins to increase the matching performance. Then, the global, semi-global, and local histograms of images are combined to measure the image similarity and are compared with the MPEG-7 descriptor of the local-only histogram. Since we exploit the absolute location of the edge in the image as well as its global composition, the proposed matching method can retrieve semantically similar images. Experiments on MPEG-7 test images show that the proposed method yields better retrieval performance by an amount of 0.04 in ANMRR, which shows a significant difference in visual inspection.

• 한국멀티미디어학회논문지
• /
• 제16권8호
• /
• pp.927-933
• /
• 2013

OpenCV (Open Computer Vision)에서 제공하는 얼굴 인식 알고리즘에서는 Haar 특징(Haar feature)들과 대상 영상의 정합 과정인 Haar 매칭 (Haar Matching)을 통하여 얼굴을 검출하는데, 이때 Haar 특징들은 정면 얼굴로 구성된 훈련 영상을 통해 학습된다. 따라서 OpenCV의 얼굴 검출 방법은 정면 얼굴에 대해서는 높은 얼굴 검출율을 보이지만, 정면을 응시하지 않거나 얼굴의 형태가 변형된 경우에는 얼굴을 정확하게 검출하지 못하는 경우가 빈번히 발생한다. 본 논문에서는 측면 얼굴 혹은 형태가 변형된 얼굴에서도 컬러 히스토그램의 분포 특성은 유사하다고 가정하고, 히스토그램 패턴 매칭(histogram pattern matching)을 이용한 얼굴 검출 방법을 제안한다. 제안한 방법에서는 Haar 매칭 오류가 발생한 프레임에 대하여, 정확하게 검출된 이전 프레임의 얼굴 영역에 대한 히스토그램 패턴 매칭을 통하여 가장 유사한 히스토그램 분포를 갖는 영역을 얼굴로 인식한다. 제안한 방법의 얼굴 검출 알고리즘의 성능을 평가하기 위한 모의실험에서 제안한 얼굴 검출 방법이 OpenCV보다 얼굴 검출율이 8% 정도 향상됨을 확인하였다.

• 한국산학기술학회논문지
• /
• 제7권6호
• /
• pp.1231-1236
• /
• 2006

영상의 화질을 개선하기 위한 많은 방법 중 비교적 간단하게 사용되는 방법 중 하나는 영상의 대비를 조절하는 것이다. 이러한 대비를 조절하는 방법 중 하나인 히스토그램 균등화는 영상 계조도 값의 분포를 균등 분포로 변환함으로써 화질을 개선한다. 그러나, 기존의 방법은 영상의 히스토그램 분포가 몇개의 계조도 값에 군집화되어 있다면 영상의 계조도가 과도하게 변하는 단점을 갖는다. 본 논문은 그레이스케일 영상에 대해 히스토그램의 형태를 고려해서 가우시안 함수에 기반한 히스토그램 매칭 방법을 제안한다. 제안된 방법은 영상이 과도하게 밝아지는 것을 제한하고 히스토그램의 분포가 몇 개의 계조도에 군집화되어 있는 영상에서의 에지 및 어두운 부분의 자세한 정보를 표현하는데 우수한 성능을 나타내었다.

• 한국멀티미디어학회논문지
• /
• 제10권12호
• /
• pp.1577-1584
• /
• 2007

Fingerprint verification is being adopted widely to provide positive identification with a high degree of confidence in all practical areas. This popular usage requires reliable methods for matching of these patterns. To meet the latest expectations, the paper presents a pair wise distance histogram method for fingerprint matching. Here, we introduced a randomized algorithm which exploits pair wise distances between the pairs of minutiae, as a basic feature for match. The method undergoes two steps for completion i.e. first it performs the matching locally then global matching parameters are calculated in second step. The proposed method is robust to common problems that fingerprint matching faces, such as scaling, rotation, translational changes and missing points etc. The paper includes the test of algorithm on various randomly generated minutiae and real fingerprints as well. The results of the tests resemble qualities and utility of method in related field.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 학술대회 논문집 정보 및 제어부문
• /
• pp.364-366
• /
• 2005

From the 90's, the image information retrieval methods have been on progress. As good examples of the methods, Conventional histogram method and merged-color histogram method were introduced. They could get good result in image retrieval. However, Conventional histogram method has disadvantages if the histogram is shifted as a result of intensity change. Merged-color histogram, also, causes more process so, it needs more time to retrieve images. In this paper, we propose an improved new method using Adaptive Color Histogram Bin Matching(AHB) in image retrieval. The proposed method has been tested and verified through a number of simulations using hundreds of images in a database. The simulation results have Quickly yielded the highly accurate candidate images in comparison to other retrieval methods. We show that AHB's can give superior results to color histograms for image retrieval.

• 대한원격탐사학회지
• /
• 제38권1호
• /
• pp.33-43
• /
• 2022

This study presents a method to restore an optical satellite image with distortion and occlusion due to fog, haze, and clouds to one that minimizes degradation factors by referring to the same type of peripheral image. Specifically, the time and cost of re-photographing were reduced by partially occluding a region. To maintain the original image's pixel value as much as possible and to maintain restored and unrestored area continuity, a simulation restoration technique modified with the Cycle Generative Adversarial Network (CycleGAN) method was developed. The accuracy of the simulated image was analyzed by comparing CycleGAN and histogram matching, as well as the pixel value distribution, with the original image. The results show that for Site 1 (out of three sites), the root mean square error and R² of CycleGAN were 169.36 and 0.9917, respectively, showing lower errors than those for histogram matching (170.43 and 0.9896, respectively). Further, comparison of the mean and standard deviation values of images simulated by CycleGAN and histogram matching with the ground truth pixel values confirmed the CycleGAN methodology as being closer to the ground truth value. Even for the histogram distribution of the simulated images, CycleGAN was closer to the ground truth than histogram matching.

• 전자공학회논문지
• /
• 제51권9호
• /
• pp.119-128
• /
• 2014

본 논문에서는 이전 연구 방법에서의 UV-histogram을 확장하여 적응적 UV-histogram을 제시함으로써, 복잡한 구성의 장면에서 사람의 검출율을 높이는 방법을 제시한다. 제안 방법은 먼저 U-histogram에서 사람 영역을 1차 추출하고, 각각의 레이블링된 U에서 V-histogram을 생성함으로써, 이전 방법에서 구분할 수 없었던 사람 후보 영역을 정확하게 추출한다. 또한 제안 방법은 사람 판정시, 초점거리와 거리에 따라 적응적인 크기를 가지는 오메가 모양의 템플릿을 이용하여 검출의 정확도를 높였으며, 누적 영상을 이용하여 오검출을 템플릿 재매칭 함으로써, occlusion에도 강인한 특성을 가진다. 실험 결과는 Bae의 연구방법에 비하여 복잡한 환경에서 약 15%의 정확도 향상, 80%의 재현율 향상을 보이며, Xia의 연구방법에 비하여 20배 빠른 수행속도를 보여, 제안 방법의 성능이 우수함을 입증한다.