• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권10호
• /
• pp.5112-5129
• /
• 2019

Image enhancement is a challenging problem in the field of image processing, especially low-light color images enhancement. This paper proposed a robust and comprehensive enhancement method based several points. First, the idea of bright channel is introduced to estimate the illumination map which is used to attain the enhancing result with Retinex model, and the color constancy is keep as well. Second, in order eliminate the illumination offsets wrongly estimated, morphological closing operation is used to modify the initial estimating illumination. Furthermore, in order to avoid fabricating edges, enlarged noises and over-smoothed visual features appearing in enhancing result, a multi-scale closing operation is used. At last, in order to avoiding the haloes and artifacts presented in enhancing result caused by gradient information lost in previous step, guided filtering is introduced to deal with previous result with guided image is initial bright channel. The proposed method can get good illumination map, and attain very effective enhancing results, including dark area is enhanced with more visual features, color natural and constancy, avoiding artifacts and over-enhanced, and eliminating Incorrect light offsets.

• 한국항공우주학회지
• /
• 제44권1호
• /
• pp.33-39
• /
• 2016

칼라 영상의 안개제거 기술이 다양하게 연구되어 왔으며 이 중 칼라 안개 영상의 특성을 토대로 도출한 Dark Channel Prior(DCP) 모델을 이용한 방법이 가장 활발하게 이용되고 있다. 한편 근적외선 영상을 이용한 응용이 널리 사용되고 있으며 근적외선 영상에 존재하는 안개를 제거할 필요가 있음에도 불구하고 기존에 근적외선 영상을 대상으로 하는 안개 제거 기술이 제안되지 않았다. 본 논문에서는 칼라 영상과 근적외선 영상을 안개 제거 측면에서 비교 분석을 수행하며 적외선 영상에 기존의 칼라 안개 제거 알고리즘 기법을 적용했을 때 나타나는 결과를 분석한다. 또한 근적외선 영상에서의 특징에 맞게 기존 칼라 안개 제거 기법을 수정한 기법을 제안하고 그 결과를 분석한다.

• Journal of Multimedia Information System
• /
• 제8권3호
• /
• pp.175-182
• /
• 2021

Oral cancer is ranked second most diagnosed cancer among Indian population and ranked sixth all around the world. Oral cancer is one of the deadliest cancers with high mortality rate and very less 5-year survival rates even after treatment. It becomes necessary to detect oral malignancies as early as possible so that timely treatment may be given to patient and increase the survival chances. In recent years deep learning based frameworks have been proposed by many researchers that can detect malignancies from medical images. In this paper we have proposed a deep learning-based framework which detects oral cancer from histopathology images very efficiently. We have designed our model to split the color channels and extract deep features from these individual channels rather than single combined channel with the help of Efficient NET B3. These features from different channels are fused by using feature fusion module designed as a layer and placed before dense layers of Efficient NET. The experiments were performed on our own dataset collected from hospitals. We also performed experiments of BreakHis, and ICML datasets to evaluate our model. The results produced by our model are very good as compared to previously reported results.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume I
• /
• pp.60-63
• /
• 2006

Geostationary Ocean Color Imager (GOCI) is under development to provide a monitoring of oceancolor around the Korean Peninsula from geostationary platforms. It is planned to be loaded on Communication, Ocean, and Meteorological Satellite (COMS) of Korea. In this paper radiometric calibration concept of the GOCI is introduced. The GOCI radiometric response is modeled as a nonlinear system in order to reflect a nonlinear characteristic of detector. In this paper estimation approaches for radiometric parameters of GOCI model are discussed. For the GOCI, the offset signal depends on each spectral channel because dark current offset signal is a function of integration time which is different from channel to channel. The offset parameter can be estimated by using offset signal measurements for two integration time setting is described.

• Communications for Statistical Applications and Methods
• /
• 제10권2호
• /
• pp.325-332
• /
• 2003

This study was to develop a system for grading apples by their color using statistical image processing. T-test was used to detect edges in apple images and the chain code method was used for contour coding. The histogram and mean gray level of each RGB channel in a ring-shaped region was used to compare apple colors to reference apple color.

• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2002년도 International Meeting on Information Display
• /
• pp.617-620
• /
• 2002

Quantitative analysis of dynamic false contours on PDP is essential to evaluate the performance of algorithms for false contour reduction. It also serves as an optimization criterion for selecting the subfield pattern. In this paper, a color difference in uniform color space is defined as a new measure for dynamic false contours. Unlike the measures in previous works, it accounts for the channel dependencies among the RGB color channels.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권10호
• /
• pp.5039-5055
• /
• 2018

The quality of natural outdoor images captured by visible camera sensors is usually degraded by the haze present in the atmosphere. In this paper, a fast image dehazing method based on visible image and near-infrared fusion is proposed. In the proposed method, a visible and a near-infrared (NIR) image of the same scene is fused based on the dual-tree complex wavelet transform (DT-CWT) to generate a dehazed color image. The color of the fusion image is regulated through haze concentration estimated by dark channel prior (DCP). The experiment results demonstrate that the proposed method outperforms the conventional dehazing methods and effectively solves the color distortion problem in the dehazing process.

• 한국정보통신학회논문지
• /
• 제18권8호
• /
• pp.1981-1986
• /
• 2014

본 논문에서 다루는 문제는 채널의 위쪽 행에 위치한 P가지 색을 가지는 점들을 아래쪽 행의 점들에 밀도가 최소가 되도록 연결하는 채널 라우팅 문제이다. 위쪽 행에 위치한 점들이 동일한 색을 가지거나 단지 2가지 색을 가지는 경우는 [1, 2]에서 다루어졌다. 본 논문에서는 P가지 색을 가지는 경우로 일반화한다. 우선 임의의 값 d가 주어질 때, d이하의 밀도를 가지는 할당이 존재하는지 결정하는 문제를 O(p(n+m)log(n+m))시간에 풀 수 있음을 보인다. 이를 이용해서 최소 밀도 값의 할당을 찾는 문제를 해결할 수 있음을 보인다.

• 한국전자통신학회논문지
• /
• 제10권5호
• /
• pp.645-652
• /
• 2015

양식장 또는 바다와 같은 수중은 물방울과 다양한 부유물에 의하여 탁도가 높아지므로, 깊이에 따라 빛의 감쇠가 발생하고 부유물에 의한 빛의 산란 효과도 발생한다. 본 논문에서는 이러한 수중 환경에서 획득한 수중 영상의 가시성을 개선하기 위하여, dark channel prior 개념을 이용한 안개 제거 방법과 학습된 색상 변환 모델을 이용하여 색을 복원하는 수중 영상의 가시성 개선 방법을 제안하였다. 색상 변환 모델을 학습하기 위하여 여수와 포항에서 획득한 수중 패턴 영상을 사용하였으며, 제안 방법의 제안된 방법의 성능을 측정하기 위하여 여수, 거문도, 필리핀 등에서 수집한 수중 영상을 사용하여 가시성 개선 실험을 수행하였다. 실험 결과 제안 방법이 다양한 장소에서 수집된 수중 영상의 가시성을 개선시킴을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권8호
• /
• pp.2552-2570
• /
• 2022

Underwater images usually have various problems, such as the color cast of underwater images due to the attenuation of different lights in water, the darkness of image caused by the lack of light underwater, and the haze effect of underwater images because of the scattering of light. To address the above problems, the channel attention mechanism, strengthen-operate-subtract (SOS) boosting mechanism and gated fusion module are introduced in our paper, based on which, an underwater image recovery network is proposed. First, for the color cast problem of underwater images, the channel attention mechanism is incorporated in our model, which can well alleviate the color cast of underwater images. Second, as for the darkness of underwater images, the similarity between the target underwater image after dehazing and color correcting, and the image output by our model is used as the loss function, so as to increase the brightness of the underwater image. Finally, we employ the SOS boosting module to eliminate the haze effect of underwater images. Moreover, experiments were carried out to evaluate the performance of our model. The qualitative analysis results show that our method can be applied to effectively recover the underwater images, which outperformed most methods for comparison according to various criteria in the quantitative analysis.