• Journal of KIISE:Software and Applications
• /
• v.33 no.11
• /
• pp.936-941
• /
• 2006

To apply object recognition techniques to real environment, illumination compensation method should be developed. As effective illumination compensation model, we focused our attention on Retinex model and illumination-Reflectance model, implemented them, and experimented on their performance. We implemented Retinex model with Single Scale Retinex, Multi-Scale Retinex, and Retinex Neural Network and Multi-Scale Retinex Neural Network, neural network model of Retinex model. Also, we implemented illumination-Reflectance model with reflectance image calculation by calculating an illumination image by low frequency filtering in frequency domain of Discrete Cosine Transform and Wavelet Transform, and Gaussian blurring. We compare their illumination compensation performance to facial images under nine illumination directions. We also compare their performance after post processing using Principal Component Analysis(PCA). As a result, illumination Reflectance model showed better performance and their overall performance was improved when illumination compensated images were post processed by PCA.

• Journal of Korea Multimedia Society
• /
• v.19 no.2
• /
• pp.233-239
• /
• 2016

Color enhancement basically deals with color manipulation in digital images. Recently, the technique has become widely used as a result of the increasing use of digital cameras. Retinex-based colorenhancement algorithms are a popular technique. In this paper, retinex with bilateral filtering is proposed to improve the quality of poorly illuminated images. Generally, it consists of three main steps: first, a retinex-based algorithm with color restoration; second, transformation mapping using histogram matching; and finally, smoothing the image using a bilateral filter. The experimental results demonstrate that the proposed method can successfully enhance image contrast while avoiding the halo effect and maintaining the color distribution in the image.

• Journal of Korea Multimedia Society
• /
• v.21 no.2
• /
• pp.108-116
• /
• 2018

In this paper, we propose an image enhancement method based on Multi-Scale Retinex theory that designs Unsharp Masking Filter (UMF) and emphasizes the contrast ratio adaptively. Unsharp Masking (UM) technique emphasizes image sharpness and improves contrast ratio by adding high frequency component to the original image. The high frequency component is obtained by differentiating between original image and low frequency image. In this paper, we present how to design an UMF kernel and to adaptively apply it to increase the contrast ratio according to multi-scale retinex theory which resembles human visual system. Experimental results show that the proposed method has better quantitative performance indexes such as PSNR, ambe & SSIM and better qualitative feature like halo artifact suppression.

• Journal of information and communication convergence engineering
• /
• v.8 no.3
• /
• pp.323-327
• /
• 2010

Recently, the television market trend is change to HD television and the need of the study on HD image enhancement is increased rapidly. To enhancement of image quality, the retinex algorithm is commonly used. That's why we studied how to accelerate the retinex algorithm with CUDA on GPGPU (general purpose graphics processing unit). Calculating average part in retinex algorithm is similar to pyramidal calculation. We parallelize this recursive pyramidal average calculating for all layers, map the average data into the 2D plane and reduce the calculating time dramatically. Sequential C code takes 8948ms to get the average values for all layers in $1024{\times}1024$ image, but proposed method takes only only about 0.9ms for the same image. We are going to study about the real-time HD video rendering and image enhancement.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.417-420
• /
• 2011

로봇이 능동적으로 행동하기 위해서는 외부 신호를 받아서 처리해야 되는데 여러 가지 센서 중에서도 영상처리가 중요해지고 있다. 하지만 영상처리를 사용하였을 경우는 예측할 수 없는 외부환경으로부터 영향을 받을 수 있다. 예를 들면 조명이 일정한 내부 환경에서는 인식이 가능하나 외부환경에서는 불가능한 경우가 있다. 그러므로 로봇산업이 발전에 중요한 축을 담당하고 있는 영상처리에 분야 중에서 논문에서는 조명이 변하는 상황을 설정해보고 그 상황을 토대로 기존의 알고리즘인 [2][3] Single-scale Retinex. [4][5] Multi-scale Retinex와 인식률을 비교해보고 Single-scale Retinex을 기반으로 단순히 Multi- scale Retinex처럼 가중치를 같이 두는 것이 아니라 상황에 따라 가중치를 다르게 주는 알고리즘 'Adaptive Two Scale Relinex Algorilhm'을 소개하겠다. 더불어 앞으로 나아가야 될 방향에 대해서도 언급하겠다.

• Journal of Korea Multimedia Society
• /
• v.13 no.11
• /
• pp.1621-1629
• /
• 2010

This paper presents an improved fast MSRCR algorithm that MSRs are commonly adopted at tone mapping in color vision. Conventional MSRs consist of three SSRs, which use three Gaussian functions with different scales as those surround ones. This convolution processes require much computation load. Therefore, the proposed algorithm adopts a hierarchical discrete correlation which is equivalent to Gaussian function and the Retinex process is only applied to the luminance channel in order to get a fast processing. A simple color preservation scheme is applied to the Retinex output from the luminance channel in the proposed MSRCR algorithm. Experimental results show that the proposed algorithm required less number of oprations and computation time about 1/9.5 and 1/3.5 times, respectively, than those of the simplest MSR and was equivalent to conventional MSRs.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.6 no.2
• /
• pp.225-230
• /
• 2011

This paper depict the system which reacts staly towards light changes, when object is detected using retinex. Previous interaction system does not react to transient light conditions. Since non-lighting condition was constructed in the limited space. However, if interaction contents work in the inside where the light changes, the light input is changed as the time goes by when the system detect objects with super sensitive camera few lighting transients makes system trouble. Thus, lighting is one of the most significant factors of the system.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2011.01a
• /
• pp.37-38
• /
• 2011

본 논문은 상대적으로 대비도 차이가 크게 나타나는 역광 이미지에 대해서 Retinex 알고리즘을 적용하여 보정 했을 경우 발생하는 밝은 영역에서의 컬러 성분의 손실을 개선하기 위한 새로운 기법을 제안한다. 역광 이미지의 경우 밝은 영역과 어두운 영역에 대한 밝기 차이가 매우 크게 발생하기 때문에 Retinex 알고리즘을 이용하여 영상의 대비도를 향상시킬 경우 밝은 영역에서의 컬러 성분이 손실되는 현상이 발생한다. 이러한 손실을 보완하기 위해서 원본 영상의 밝은 영역에 해당하는 컬러 성분을 Retinex 알고리즘으로 보정된 영상에 추가해준다. Fuzzy c-means 군집화 알고리즘을 이용하여 원본 영상에서의 밝은 영역과 어두운 영역에 대하여 모든 화소의 소속 정도를 나타내는 퍼지 소속 함수를 구한다. 밝은 영역에 대해서의 컬러 성분은 원본 영상 값에 밝은 영역 퍼지 소속 함수를 적용하고, 어두운 영역에 대해서의 컬러 성분은 Retinex 복원 영상 값에 어두운 영역 퍼지 소속 함수를 이용한다. 제안하는 알고리즘의 성능 평가를 위해 역광 현상이 강하게 나타나는 자연영상들을 대상으로 적용하여 기존의 Retinex 알고리즘(MSRCR) 보다 우수한 성능을 가지고 있음을 보였다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.3
• /
• pp.52-59
• /
• 2009

In general, methods based on histogram or a correction of gamma curve are usually utilized to enhance the contrast of captured image in the dark scene. These methods are efficient to enhance the contrast globally, however, they locally induced the low quality of image. Recently, to resolve the problem, the multi-scaled refiner algorithm improving the contrast with locally averaged lightness is proposed. However, estimating the locally averaged lightness, if there is the object with a high saturated color, the color distortion might be induced by the color of object. Thus, in this paper, the dominant chromaticity of image is estimated to correct the locally averaged lightness in multi-scaled retinex algorithm. Because the average chromaticity of image includes the chromaticity of illumination, the dominant chromaticity is estimated with dividing the average chromaticity of image by the estimated chromaticity of illumination from highlight region. In addition, to improve the lower chroma by multi-scaled retinex algorithm generally, the chroma was compensated preserving the hue in the CIELAB color space.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.2 s.314
• /
• pp.126-136
• /
• 2007

This paper presents an enhanced algorithm for compensating the visual quality in back-light image. Current cameras do not represent all details of scene into human's eye. Saturation and underexposure are common problems in back-light image. Retinex algorithm, derived from Land's theory on human visual perception is known to be effective in enhancing the contrast. However, its weaknesses are long processing time and low contrast of bright area in back-light scene because of compensating the details of dark area. In this paper, K-Retinex algorithm is proposed to reduce the processing time and enhance the contrast in both dark and bright area. To show the superiority of proposed algorithm, we compare the processing time, local standard deviation and contrast per pixel of each area above.