• 한국정보통신학회논문지
• /
• 제17권9호
• /
• pp.2206-2212
• /
• 2013

본 논문은 Fuzzy Contrast Enhancement 기법과 FCM을 이용하여 대비를 개선한 후, Fuzzy Contrast Enhancement를 간과 신장의 초음파 영상에 적용하여 지방간 농도 수치를 분류하는 방법을 제시한다. 간, 신장 영역을 촬영한 초음파 영상에서 촬영 정보나 눈금자 등과 같이 필요 없는 부분을 잡음으로 간주하여, 제거한 ROI 영상을 추출하고, Fuzzy Contrast Enhancement 알고리즘을 이용하여 명암 대비를 강조한다. Fuzzy Contrast Enhancement 기법이 적용된 간, 신장 영역 영상에서 평균 이진화를 적용한 후, 평균 이진화를 적용한 영상에 Blob 알고리즘을 적용하여 간, 신장 실질 영역의 ROI 영상을 추출한다. 추출한 간 영역과 신장영역의 ROI 영상을 FCM을 이용하여, 10개의 명암도 Level로 각 각 분류한 후, 분류된 간, 신장 실질 영역의 명암도 Level 중 많이 분포된 명암도 Level을 기준으로 간, 신장 실질 영역의 대표 명암도를 추출한다. 제안된 방법을 간, 신장 영역을 촬영한 초음파 영상에 적용하여 간의 지방도를 분류한 결과, 영상의학과 전문의의 판독과 일치하여 향후 지방간의 진단에 효과적으로 적용할 수 있는 방법이 될 수 있을 것으로 사료된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권3호
• /
• pp.1205-1223
• /
• 2018

Image enhancement is an emerging method for analyzing the images clearer for interpretation and analysis in the spatial domain. The goal of image enhancement is to serve an input image so that the resultant image is more suited to the particular application. In this paper, a novel method is proposed based on Mamdani fuzzy inference system (FIS) using multiple fuzzy membership functions. It is observed that the shape of membership function while converting the input image into the fuzzy domain is the essential important selection. Then, a set of fuzzy If-Then rule base in fuzzy domain gives the best result in image contrast enhancement. Based on a different combination of membership function shapes, a best predictive solution can be determined which can be suitable for different types of the input image as per application requirements. Our result analysis shows that the quality attributes such as PSNR, Index of Fuzziness (IOF) parameters give different performances with a selection of numbers and different sized membership function in the fuzzy domain. To get more insight, an optimization algorithm is proposed to identify the best combination of the fuzzy membership function for best image contrast enhancement.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2001년도 추계학술대회 학술발표 논문집
• /
• pp.279-282
• /
• 2001

This paper presents an image contrast enhancement technique for improving the low contrast images using the improved IAFC(Integrated Adaptive Fuzzy Clustering) Model. The low pictorial information of a low contrast image is due to the vagueness or fuzziness of the multivalued levels of brightness rather than randomness. Fuzzy image processing has three main stages, namely, image fuzzification, modification of membership values, and image defuzzification. Using a new model of automatic crossover point selection, optimal crossover point is selected automatically. The problem of crossover point selection can be considered as the two-category classification problem. The improved MEC can classify the image into two classes with unsupervised teaming rule. The proposed method is applied to some experimental images with 256 gray levels and the results are compared with those of the histogram equalization technique. We utilized the index of fuzziness as a measure of image quality. The results show that the proposed method is better than the histogram equalization technique.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2002년도 추계학술대회 및 정기총회
• /
• pp.295-299
• /
• 2002

This paper presents an image contrast enhancement technique for improving low contrast images. We applied fuzzy logic to develop an image contrast enhancement technique in the viewpoint of considering that the low pictorial information of a low contrast image is due to the vaguness or fuzziness of the multivalued levels of brightness rather than randomness. The fuzzy image contrast enhancement technique consists of three main stages, namely, image fuzzification, modification of membership values, and image defuzzification. In the stage of image fuzzification, we need to select a crossover point. To select the crossover point automatically the K-means algorithm is used. The problem of crossover point selection can be considered as the two-category, object and background, classification problem. The proposed method is applied to an experimental image with 256 gray levels and the result of the proposed method is compared with that of the histogram equalization technique. We used the index of fuzziness as a measure of image quality. The result shows that the proposed method is better than the histogram equalization technique.

• Journal of Medicine and Life Science
• /
• 제16권1호
• /
• pp.1-5
• /
• 2019

Our purpose was to evaluate usefulness of the contrast-enhanced 3 dimensional fluid attenuated inversion recovery (3D-FLAIR) technique of half brain volume to diagnose the patients with facial neuritis based on segment-based analysis. We assessed retrospectively 17 consecutive patients who underwent brain MR imaging at 3 tesla for facial neuritis: 11 patients with idiopathic facial neuritis and 6 with herpes zoster oticus. Contrast enhanced 3D-FLAIR sequences of the half brain volume were analyzed and 3D T1-weighted sequence of the full brain volume were used as the base-line exam. Enhancement of the facial nerve was determined in each segment of 5 facial nerve segments by two radiologists. Sensitivity, specificity and accuracy of enhancement of each segment were assessed. The authors experienced a prompt fuzzy CSF enhancement in the fundus of the internal auditory canal in patients with enhancement of the canalicular segment. Interobserver agreement of CE 3D-FLAIR was excellent(${\kappa}$-value 0.885). Sensitivity, specificity, and accuracy of each segment are 1.0, 0.823, 0.912 in the canalicular segment; 0.118, 1.0, 0.559 in the labyrinthine segment; 0.823, 0.294, 0.559 in the anterior genu; 0.823, 0.529, 0.676 in the tympanic segment; 0.823, 0.235, 0.529 in the mastoid segment, respectively. In addition, those of prompt fuzzy enhancement were 0.647, 1.0, and 0.824, respectively. Incidence of prompt fuzzy enhancement with enhancement of the canalicular segment was 11 sites(55%): 6 (54.5%) in idiopathic facial neuritis and 5 (83.3%) in herpes zoster. Enhancement of the canalicular segment and prompt fuzzy enhancement on CE 3D-FLAIR was significantly correlated with occurrence of facial neuritis (p<0.001). CE 3D-FLAIR technique of the half brain volume is useful to evaluate the patients with facial neuritis as an adjunct sequence in addition to contrast-enhanced 3D T1-weighted sequence. On segment-based analysis, contrast enhancement of the canalicular segment is the most reliable. Prompt fuzzy enhancement is seen in not only herpes zoster, but in idiopathic facial neuritis.

• 한국멀티미디어학회논문지
• /
• 제11권4호
• /
• pp.462-470
• /
• 2008

본 논문은 저대비에 의한 영상 정보의 불확실성이 화소가 가지고 있는 명암도의 모호성과 애매성에 근거한다는 점에서 퍼지 변환 함수를 적용하여 영상 향상을 기하고자 한다. 명암도 분포가 한쪽으로 치우친 저대비 영상의 문제를 해결하고자 k-means 알고리즘을 사용하여 물체와 배경을 구분할 수 있는 자동 임계점을 찾고 이를 기준으로 영상의 밝은 부분과 어두운 부분의 대비 향상을 가져올 수 있도록 퍼지 변환 함수를 적용한다. 퍼지 변환 함수는 영상 향상을 위해 3단계-입력 영상을 퍼지 영역으로 변환시키는 퍼지화 단계와 대비를 향상시키는 대비 강화 단계 그리고 퍼지 영역을 다시 영상 영역으로 변환시키는 비퍼지화 단계로 제시된다. 향상된 영상의 성능을 평가하고자 퍼지성 지수와 엔트로피 지수를 제시하여 이를 히스토그램 균등화 기법과 비교하고 실험결과로 성능의 우수함을 보여준다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제15권1호
• /
• pp.35-44
• /
• 2015

The main purpose of image enhancement is to improve certain characteristics of an image to improve its visual quality. This paper proposes a method for image contrast enhancement that can be applied to both medical and natural images. The proposed algorithm is designed to achieve contrast enhancement while also preserving the local image details. To achieve this, the proposed method combines local image contrast preserving dynamic range compression and contrast limited adaptive histogram equalization (CLAHE). Global gain parameters for contrast enhancement are inadequate for preserving local image details. Therefore, in the proposed method, in order to preserve local image details, local contrast enhancement at any pixel position is performed based on the corresponding local gain parameter, which is calculated according to the current pixel neighborhood edge density. Different image quality measures are used for evaluating the performance of the proposed method. Experimental results show that the proposed method provides more information about the image details, which can help facilitate further image analysis.

• 한국지능시스템학회논문지
• /
• 제11권9호
• /
• pp.777-781
• /
• 2001

본 논문은 저대비 영상을 처리하여 보다 향상된 영상을 얻고자 펴지 함소와 개선된 IAFC 모델을 적용한 영상 대비 향상 기법을 제안한다. 저대비에 의한 영상 정보의 불확실성이 무작위성보다 명암도의 모호성과 퍼지성에 근거한다는 점에서 퍼지 집합이론을 영상 향상 기법을 개발하는데 적용한다. 영상 향상의 단계를 퍼지화, 대비 강화 연산, 비퍼지화 단계로 나눠볼 수 있으며, 퍼지화 및 비퍼지화 과정에서 적절한 교차점 선택이 요구되고 이때 개선된 IAFC 모델을 적용하여 최적의 교차점을 선택한다. 데이터 대한 정신없이 임계 파라미터를 조정함으로써 클러스터링을 할 수 있는 개선된 IAFC 모델로 두 클래스만을 형성하도록 하여 명암도의 애매성이 최대가 되는 교차점을 찾아 대비를 강화시킨다. 대비 향상의 정략적 측정을 위해 퍼지성 지수를 사용하며 히스토그램 균등화 기법을 사용한 대비 향상 결과와 비교한다. 저대비 영상에 대해 최적의 교차점의 위치를 정하는 제안한 기법의 결과가 많은 실험영상을 통해 우수함을 보여주고 있다.

• 한국멀티미디어학회논문지
• /
• 제18권7호
• /
• pp.806-817
• /
• 2015

The contrast limited adaptive histogram equalization(CLAHE) is an advanced method for the histogram equalization which is a common contrast enhancement technique. The CLAHE divides the image into sections, and applies the contrast limited histogram equalization for each section. X-ray images can be classified into three areas: skin, bone, and air area. In clinical application, the interest area is limited to the skin or bone area depending on the diagnosis region. The CLAHE could deteriorate X-ray image quality because the CLAHE enhances the area which doesn't need to be enhanced. In this paper, we propose a new method which automatically determines the clip limit of CLAHE's parameter to improve X-ray image quality using fuzzy logic. We introduce fuzzy logic which is possible to determine clip limit proportional to the interest of users. Experimental results show that the proposed method improve images according to the user's preference by focusing on the subject.

• 전자공학회논문지B
• /
• 제31B권8호
• /
• pp.181-191
• /
• 1994

A new method for enhancing blurred images using fuzzy logic concepts is proposed. Blurred images contain blurred boundaries which make it difficult to detect edges and segment areas in images. In order to sharpen blurred edges local contrast information of an image and erosion/dilation properties of local min/max operations are used in which local min/max operations are fuzzy logic operations. so that given images are transformed to fuzzy images and then these operations are applied on them. In this method the sharpening operation can be iteratively applied to the image to get better deblurring effect and gray-scale "salt-and-pepper" noises are suppressed. the efficiency of our algorithm is demonstrated through experimental results obtained with artificially-made blurred images and real blurred images.