• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2013년도 춘계학술대회
• /
• pp.379-381
• /
• 2013

본 논문에서는 문서 이미지에서 문장 사이에 공백영역의 기울기를 검출하고 보정하는 방법을 제안한다. 제안하는 방법은 문서 이미지에서 에지를 추출한 문장 사이에 가지는 공백들의 기울기 값을 통해 문서 이미지의 기울기를 보정한다. 문서 이미지를 일부의 영역으로 나누어서 처리함으로써 문서 내 외곽의 여백영역, 그림, 다단형식 등에 대해서 강건한 처리 결과를 보여준다. 제안하는 방법은 문자 영역의 픽셀을 이용하는 것이 아닌, 공백영역을 이용함으로써 기존의 방법보다 선명한 화질은 물론 저화질 문서 이미지에서도 효과적으로 보정된다.

• 방송공학회논문지
• /
• 제2권2호
• /
• pp.156-169
• /
• 1997

본 논문에서는 형태학적 연산(morphological operation)과 영역 융합(region merging) 방법을 이용한 영상 분할(image segmentation) 방법을 제안한다. 이를 위해서 형태학적 필터(morphological filter)를 이용하여 단순화한 영상에 대해, 다중크기 경사(multiscale gradient) 연산자를 이용하여 경사 영상(gradient image)을 얻는다. 경사 영상에 watershed 변환을 적용하면 분할 영상을 얻을 수 있는데, 이렇게 얻은 분할 영상은 대개 과분할(oversegmentation) 영상이므로, 분할 영역을 줄이기 위해 미소 영역(small region)이나 비슷한 특성을 갖는 인접 영역들은 서로 융합시킬 필요가 있다. 본 논문에서는 영역을 융합하기 위한 기준으로서 영역간의 평균 에지 강도와 각 영역의 화소값들에 비해 평균값을 사용하는데, 이러한 융합 기준은 contour following 과정에서 계산된다. 제안한 방법은 watershed 알고리듬, 영역에 기반한 영상 분할, 경계에 기반한 분할 방법을 결합한 방법으로서, 향상된 영상 분할이 가능함을 실험을 통하여 제시하였다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 The Third Asian Fuzzy Systems Symposium
• /
• pp.740-749
• /
• 1998

This paper proposes compression of image data using neural networks based on conjugate gradient method and dynamic tunneling system. The conjugate gradient method is applied for high speed optimization .The dynamic tunneling algorithms, which is the deterministic method with tunneling phenomenon, is applied for global optimization. Converging to the local minima by using the conjugate gradient method, the new initial point for escaping the local minima is estimated by dynamic tunneling system. The proposed method has been applied the image data compression of 12 ${\times}$12 pixels. The simulation results shows the proposed networks has better learning performance , in comparison with that using the conventional BP as learning algorithm.

• 한국멀티미디어학회논문지
• /
• 제7권12호
• /
• pp.1639-1649
• /
• 2004

In this paper, a method for detection of forged signatures based on spectral analysis of directional gradient density function and a weighted fuzzy classifier is proposed. The well defined outline of an incoming signature image is extracted in a preprocessing stage which includes noise reduction, automatic thresholding, image restoration and erosion process. The directional gradient density function derived from extracted signature outline is highly related to the overall shape of signature image, and thus its frequency spectrum is used as a feature set. With this spectral feature set, having a property to be invariant in size, shift, and rotation, a weighted fuzzy classifier is evaluated for the verification of freehand and random forgeries. Experiments show that less than 5% averaged error rate can be achieved on a database of 500 signature samples.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2001년도 추계학술대회 학술발표 논문집
• /
• pp.283-286
• /
• 2001

Based on a fuzzy system representation of gray scale images, we derive an edge detection algorithm whose convolution kernel is different from the known kernels such as those of Roberts', Prewitt's or Sobel's gradient. Our fuzzy system representation is an exact representation of the bicubic spline function which represents the gray scale image approximately. Hence the fuzzy system is a continuous function and it provides a natural way to define the gradient and the Laplacian operator. We show that the gradient at grid points can be evaluated by taking the convolution of the image with a 3 3 kernel. We also show that our gradient coupled with the approximate value of the continuous function generates an edge detection method which creates edge images clearer than those by other methods. A few examples of applying our methods are included.

• 대한전자공학회논문지SP
• /
• 제47권1호
• /
• pp.120-127
• /
• 2010

본 논문은 높은 품질 SR 이미지를 획득하기 위해 국소 그라디언트를 기반으로 적응형 보간법을 이용하는 SR 방법을 제공한다. 이 방법에서, 내삽 화소와 인접하는 유효한 화소 사이에 거리는 국소 그라디언트 특징을 이용하여 고려되며, 보간 계수는 LR 이미지의 국소 그라디언트를 고려한다. 픽셀의 국소 그라디언트는 더 작을수록, 그리고 메디안 필터는 보간된 HR 이미지의 블러링과 노이즈를 감소시키기 위해 적용된다. 실험 결과는 특히 이미지의 에지 부분에서, 다른 방법과 비교하여 제안된 방법의 유효성을 보여준다.

• 한국멀티미디어학회논문지
• /
• 제24권2호
• /
• pp.178-185
• /
• 2021

Three-dimensional high-resolution magnetic resonance imaging (MRI) provides fine-level anatomical information for disease diagnosis. However, there is a limitation in obtaining high resolution due to the long scan time for wide spatial coverage. Therefore, in order to obtain a clear high-resolution(HR) image in a wide spatial coverage, a super-resolution technology that converts a low-resolution(LR) MRI image into a high-resolution is required. In this paper, we propose a super-resolution technique through filter learning based on information on the surrounding gradient information in 3D space from 3D MRI images. In the learning step, the gradient features of each voxel are computed through eigen-decomposition from 3D patch. Based on these features, we get the learned filters that minimize the difference of intensity between pairs of LR and HR images for similar features. In test step, the gradient feature of the patch is obtained for each voxel, and the filter is applied by selecting a filter corresponding to the feature closest to it. As a result of learning 100 T1 brain MRI images of HCP which is publicly opened, we showed that the performance improved by up to about 11% compared to the traditional interpolation method.

• 한국조경학회지
• /
• 제24권2호
• /
• pp.1-12
• /
• 1996

In order to develope a road landscape that is in harmony with landscaping purpose, degree of sight occupation by slopes at road sides was measured and physical elements composing the slope scenery were visually evaluated and the results are as follows : In analysis of sight occupation ratio by perspective method, gradient of the slopes influenced more on the sight occupation than height did and the driving lane occupied 2 to 3% more proportion of sight than the passing lane. When there is slope at one side of the road, difference in sight occupation between the lanes was increasing with deceased height and with increased gradient of the slopes. In visual analysis of the slope scenery, negative image was increasing with narrow road, increased height and gradient of the slopes. In visual analysis of the slope scenery, negative image was increasing with narrow road, increased height and gradient of the slopes. Particularly, the effect of gradient was critical on scenery. The effect of the slopes was negative at 60$^{\circ}$ or more but positive at 45$^{\circ}$or less gradient. This phenomenon was more conspicuous with wide 4 lane roads than wide 2 lane roads. Although direct comparison is difficult due to a great difference between Korea and U.S.A. in climate, land condition, road dimension, and public process of purchasing land, etc, it is desirable to treat road sides so that the scenery is in harmony with landscape around as well as emphasizing the regional characteristics, also giving friendly and comfortable image to drivers and nearby residents in addition to safety as can be seen in U.S.A.

• 한국해양공학회지
• /
• 제34권6호
• /
• pp.442-453
• /
• 2020

Underwater color images suffer from low visibility and color cast effects caused by light attenuation by water and floating particles. This study applied single image enhancement techniques to enhance the quality of underwater images and compared their performance with real underwater images taken in Korean waters. Dark channel prior (DCP), gradient transform, image fusion, and generative adversarial networks (GAN), such as cycleGAN and underwater GAN (UGAN), were considered for single image enhancement. Their performance was evaluated in terms of underwater image quality measure, underwater color image quality evaluation, gray-world assumption, and blur metric. The DCP saturated the underwater images to a specific greenish or bluish color tone and reduced the brightness of the background signal. The gradient transform method with two transmission maps were sensitive to the light source and highlighted the region exposed to light. Although image fusion enabled reasonable color correction, the object details were lost due to the last fusion step. CycleGAN corrected overall color tone relatively well but generated artifacts in the background. UGAN showed good visual quality and obtained the highest scores against all figures of merit (FOMs) by compensating for the colors and visibility compared to the other single enhancement methods.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.525-528
• /
• 1999

Abstract - In this paper, a segmentation method for brain Magnetic Resonance(MR) image using region clustering technique with statistical distribution of gradient image and fuzzy rules is described. The brain MRI consists of gray matter and white matter, cerebrospinal fluid. But due to noise, overlap, vagueness, and various parameters, segmentation of MR image is a very difficult task. We use gradient information rather than intensity directly from the MR images and find appropriate thresholds for region classification using gradient approximation, rayleigh distribution function, region clustering, and merging techniques. And then, we propose the adaptive fuzzy rules in order to extract anatomical structures and diseases from brain MR image data. The experimental results shows that the proposed segmentation algorithm given better performance than traditional segmentation techniques.