• 한국지능시스템학회논문지
• /
• 제19권6호
• /
• pp.787-795
• /
• 2009

본 논문에서는 영상의 화질개선을 위해 로지스틱 함수에 기반을 둔 히스토그램 평활화 방법을 제안하였다. 여기서 히스토그램 평활화는 영상의 밝기를 조정함으로써 화질을 개선하는 간단하고 효과적인 공간영역 기반 처리기법이다. 또한 로지스틱 함수는 비선형의 변환함수로 영상의 명암도 발생빈도수에 따라 밝기개선 정도를 적응적으로 조정하기 위함이다. 특히 영상의 히스토그램에서 최대 발생빈도수를 가지는 명암도와 최대 명암도 및 전체 픽셀수만을 이용한 유연한 비대칭의 로지스틱 함수를 제안함으로써, 기존 로지스틱 함수에서의 지수함수 계산 부담과 최적의 계수 값을 경험적으로 사전에 설정해야하는 제약을 해결하였다. 제안된 기법을 다양한 크기의 해상도와 히스토그램 분포를 가지는 영상을 대상으로 실험한 결과, 기존의 히스토그램 평활화와 적응적 변형 히스토그램 평활화보다도 우수한 화질개선 성능과 빠른 평활화 속도가 있음을 확인하였다. 또한 제안된 기법은 멀티미디어 시스템에서 실시간 평활화 기법으로도 충분히 이용될 수 있음을 확인하였다.

• 한국통신학회논문지
• /
• 제33권1C호
• /
• pp.45-52
• /
• 2008

본 논문에서는 Perceptually Weighted Histogram(PWH)과 Gaussian Weighted Histogram Intersection(GWHI) 알고리즘을 기술한다. 이러한 알고리즘들은 영상검색에서 명확한 결과를 이끌어 낼 수 있지만 빛의 변화에 의해 히스토그램이 변화될 수 있다는 단점이 있다. 즉, 같은 두 영상이 빛의 세기가 약간 다를 때 쉽게 매치되지 않을 수 있다. 그래서 빛의 밝기나 색상에 의해 변화된 영상을 같은 영상으로 처리할 수 있는 히스토그램 매칭 알고리즘(Histogram Matching Algorithm)을 제안한다. 실험결과, 제안한 알고리즘은 기존의 PWH와 GWHI 알고리즘보다 recall에서 각각 32%, 30%, precision에서 각각 38%, 34%까지 우수한 결과를 보였다. 따라서 제안한 알고리즘은 빛의 변화가 일어난 영상도 쉽게 검색할 수 있음을 알 수 있다.

• 한국생산제조학회지
• /
• 제7권3호
• /
• pp.126-131
• /
• 1998

In computer vision system of modern industry precise measuring has lots of dfficulties because of measurement error due to distortion phenomenon. Among the difficulties, the distortion of edge is regraded as a dominent problem. which is caused by the vlurred image. The blurred image apperar when camera can not discriminate its precise focus. So. it is very important to decide focus of lens and to develop algorithm in order to correct distortion phenomenon. Thus. discrimination criteria obtained by image information of precise focus must be fixed in advance. The gray level histogram of image acquired from blurred edge tends to show a uniform distribution. Bimodal intensity histogram is related with condition of focus, and it is possible to find good condition of focus by using bimodal histogram of entropy.

• 대한전자공학회논문지SP
• /
• 제41권6호
• /
• pp.195-208
• /
• 2004

히스토그램은 여러 가지 응용적인 측면에서 매우 유용한 방법이며, 단순한 계산법과 편리성이 강조되면서, 오늘날 디지털 이미지 프로세싱에서는 기본적인 방법이 되었다. 하지만 히스토그램을 사용하는 방법의 근본적인 한계점은 영상에서 픽셀의 공간적인 위치 정보를 없애 버린다는 것이다. 본 논문은 공간적인 위치정보를 포함한 히스토그램(공간 히스토그램)을 제시하여 영상을 재해석한다. 또한 그 결과를 이용하여 레벨 순서별 Recursive 메디안 필터를 구현 하였다. 제안한 Recursive 메디안 필터는 기존의 Recursive 메디안 필터와 비교 했을 때, 에지 보존 측면에서 상당 부분 개선된 결과를 보였다.

• ETRI Journal
• /
• 제39권1호
• /
• pp.76-86
• /
• 2017

In this study, we propose an automatic contrast enhancement method based on transfer function modification (TFM) by histogram equalization. Previous histogram-based global contrast enhancement techniques employ histogram modification, whereas we propose a direct TFM technique that considers the mean brightness of an image during contrast enhancement. The mean point shifting method using a transfer function is proposed to preserve the mean brightness of an image. In addition, the linearization of transfer function technique, which has a histogram flattening effect, is designed to reduce visual artifacts. An attenuation factor is automatically determined using the maximum value of the probability density function in an image to control its rate of contrast. A new quantitative measurement method called sparsity of a histogram is proposed to obtain a better objective comparison relative to previous global contrast enhancement methods. According to our experimental results, we demonstrated the performance of our proposed method based on generalized measures and the newly proposed measurement.

• 한국컴퓨터정보학회논문지
• /
• 제24권6호
• /
• pp.73-80
• /
• 2019

In this paper, we propose an effective dynamic range compression (DRC) method of infrared images. A histogram of infrared images has narrow dynamic range compared to visible images. Hence, it is important to apply the effective DRC algorithm for high performance of an infrared image analysis. The proposed algorithm for high dynamic range divides an infrared image into the overlapped blocks and calculates Shannon's entropy of overlapped blocks. After that, we classify each block according to the value of entropy and apply adaptive histogram modification method each overlapped block. We make an intensity mapping function through result of the adaptive histogram modification method which is using standard-deviation and maximum value of histogram of classified blocks. Lastly, in order to reduce block artifact, we apply hanning window to the overlapped blocks. In experimental result, the proposed method showed better performance of dynamic range compression compared to previous algorithms.

• 인터넷정보학회논문지
• /
• 제13권3호
• /
• pp.61-73
• /
• 2012

본 논문에서는 영상의 밝기 평균과 분산을 이용하여 영상의 엔트로피를 최대화하는 히스토그램 명세화 기반의 영상 향상 기법을 제안한다. 제안 방법은 히스토그램 명세화 과정에서 입력 히스토그램과 목적 히스토그램 모두를 가우시안 분포로 모델링한다. 이 과정에서 입력 가우시안 분포의 평균과 분산은 입력영상의 밝기 평균값과 분산을 각각 그대로 사용한다. 목적 가우시안 분포의 평균도 입력영상의 밝기 평균값을 사용하지만, 분산은 출력 영상의 엔트로피가 최대화되는 분산을 결정하여 사용한다. 다양한 영상에 대한 실험 결과에 의하면, 기존 방법들에 비해 제안 방법은 영상의 평균 밝기를 잘 유지하면서 자연스러운 개선 결과를 보여준다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권9호
• /
• pp.3751-3770
• /
• 2015

Many sorts of image processing software facilitate image editing and also generate a great number of doctored images. Forensic technology emerges to detect the unintentional or malicious image operations. Most of forensic methods focus on the detection of single operations. However, a series of operations may be used to sequentially manipulate an image, which makes the operation detection problem complex. Forensic investigators always want to know as much exhaustive information about a suspicious image's entire processing history as possible. The detection of the operation chain, consisting of a series of operations, is a significant and challenging problem in the research field of forensics. In this paper, based on the histogram distribution uniformity of a manipulated image, we propose an operation chain detection scheme to identify histogram equalization (HE) followed by the dither-like operation (DLO). Two histogram features and a local spatial feature are utilized to further determine which DLO may have been applied. Both theoretical analysis and experimental results verify the effectiveness of our proposed scheme for both global and local scenarios.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제4권4호
• /
• pp.633-654
• /
• 2010

High quality camera images, with good contrast and intensity, are needed to obtain the desired information. Images need to be enhanced when they are dark or bright. The histogram equalization technique, which flattens the density distribution of an image, has been widely used to enhance image contrast due to its effectiveness and simplicity. This technique, however, cannot be used to enhance images that are either too dark or too bright. In addition, it is difficult to perform histogram equalization in real-time using a general-purpose computer. This paper proposes a histogram equalization technique with AGC (Automatic Gain Control) to extend the image enhancement range. It is designed using VHDL (VHSIC Hardware Description Language) to enhance images in real-time. The system is implemented with an FPGA (Field Programmable Gate Array). An image processing system with this FPGA is implemented. The performance of this image processing system is measured.

• International Journal of Advanced Culture Technology
• /
• 제3권2호
• /
• pp.161-170
• /
• 2015

Mean separated histogram equalization in order to preserve the original mean brightness has been proposed. To provide the minimum mean brightness error after the histogram modification, the input image's histogram is successively divided by the factor of 2 until the mean brightness error is satisfied the defined threshold. Then each divided group or sub-histogram will be independently equalized based on the proportional input mean. To provide the overall minimum mean brightness error, each group will be controlled by adding some certain pixels from the adjacent grey level of the next group for giving its mean near by the corresponding the divided mean. However, it still exists some little error which will be put into the next adjacent group. By successive dividing the original histogram, we found that the absolute mean brightness error is gradually decreased when the number of group is increased. Therefore, the error threshold is assigned in order to automatically dividing the original histogram for obtaining the desired absolute mean brightness error (AMBE). This process will be applied to the color image by treating each color independently.