• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.9
• /
• pp.699-704
• /
• 2016

In this paper, we propose a development method for a drowsiness detection system using retinex theory and edge information for vehicle safety. Detection of a drowsy state of a driver is very important because the drowsiness of driver is often the main cause of many car accidents. After acquiring an image of the entire face, we executed the pre-process step using the retinex theory. We then applied a technique for the detection of the white pixels using edge information. Experimental results showed that the proposed method improved the accuracy of detecting drowsiness to nearly 98%, and can be used to prevent a car accident caused by the driver's drowsiness.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.06a
• /
• pp.242-245
• /
• 2016

본 논문에서는 단일 노출 영상으로부터 다수의 가상 노출 영상을 생성하고, 그 영상을 한 장의 HDR 영상으로 합성하여 SDR 디스플레이 시스템에 개선된 화질의 영상을 보여주도록 하는 방법을 제안한다. 이 방법에서는 주어진 단일 노출 영상을 Retinex 이론을 적용하여 조명 성분과 반사 성분으로 분리하고, 새로운 노출 조절 알고리즘을 제안하여 다수의 가상 조명 성분과 원본 이미지의 반사 성분을 생성하며 이들을 이용하여 다수의 가상 노출 영상을 생성한다. 생성된 다수의 가상 노출 영상은 가중치 합성 함수에 의해서 암부의 세부 표현력이 개선되고 명암비가 높아져 SDR display 에서도 우수한 화질의 HDR 영상으로 변환된다. 기존에 제안된 알고리즘과 비교 실험을 통해, 본 논문에서 제안된 HDR 영상 합성 기법의 성능을 증명한다.

• Proceedings of the Korean Society Of Semiconductor Equipment Technology
• /
• 2006.05a
• /
• pp.265-268
• /
• 2006

본 논문에서는 레티넥스(Retinex) 이론을 이용한 영상개선 알고리즘을 분석하고, 이를 최적화하기 위한 알고리즘을 제안하였다. 기존의 알고리즘이 가진 큰 단점인 수행속도를 보완하기 위해 그리고 작아진 필터 크기 때문에 충분한 면적의 조명정보를 분석하지 못하는 단점을 보완하기 위해 우리의 알고리즘에는 주변함수의 필터크기를 원래의 알고리즘과 비교하여 보다 작은 크기로 조절함으로써, 연산속도를 대폭 감소시킬 수 있었고 4번째 채널로 흑백영상을 선택하므로 써 충분한 면적의 조명정보를 분석하지 못하는 단점을 보완하였다.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.727-728
• /
• 2006

In this paper, we analyzed the color restoration method to be used in the Multi-Scale Retinex and proposed new color restoration method. and, we compared the result of the algorithm to be proposed with conventional algorithm through the experiment.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.9 no.2
• /
• pp.223-228
• /
• 2016

A digital micromirror system was proposed for future smart learning. This system is the compact micro-projector with a built-in CMOS sensor modules. It can provide the various interfaces. The basis of interface is to recognize the finger tip on projected image. But the recognition rate of finger tip is very low due to various image degradations. In this paper, we propose the finger tip recognition algorithm that minimize the image degradation factors by using the Retinex transform and IR structuring light. By verifying the availability of the algorithm through experiment, the performance of finger tip recognition was confirmed. Therefore, the user interface can be able to be enhanced significantly in DMS.

• Journal of the Semiconductor & Display Technology
• /
• v.5 no.2 s.15
• /
• pp.15-18
• /
• 2006

This paper presents a optimizing algorithm getting through analyzing a image improvement algorithm using retinex theory. Improving a existing retinex theory's slow process speed, our proposal is that it controls a small filter size of surrounding function by comparing with original algorithm. So slow process speed decreased drastically. For filling a short of lighting information by small filter, we also selected gray image as a forth channel. Using the color constancy, we got fast process time like linear color correction and could do comfortable auto color rectification according to other images.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.10
• /
• pp.77-83
• /
• 2016

This paper presents an adaptive retinex algorithm using skewness for contrast enhancement of color images. In order to estimate the degree of low contrast of an image, skewness of luminance of an observed image is used to define a parameter, and a non-linear function is proposed to compensate the reflectance using the parameter and estimated reflectance. In addition, determination of gain and offset of the non-linear function is addressed using statistics of the estimated reflectance. The relation between an observed luminance and the compensated luminance is used to compensate color components with the reduction of computational cost. The experimental results show that the proposed algorithm has the capability to effectively improve the contrast without color distortion.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.8
• /
• pp.2749-2763
• /
• 2021

The desirable result of infrared (IR) and visible (VIS) image fusion should have textural details from VIS images and salient targets from IR images. However, detail information in the dark regions of VIS image has low contrast and blurry edges, resulting in performance degradation in image fusion. To resolve the troubles of fuzzy details in dark regions of VIS image fusion, we have proposed a method of reflectance estimation for IR and VIS image fusion. In order to maintain and enhance details in these dark regions, dark region approximation (DRA) is proposed to optimize the Retinex model. With the improved Retinex model based on DRA, quasi-Newton method is adopted to estimate the reflectance of a VIS image. The final fusion outcome is obtained by fusing the DRA-based reflectance of VIS image with IR image. Our method could simultaneously retain the low visibility details in VIS images and the high contrast targets in IR images. Experiment statistic shows that compared to some advanced approaches, the proposed method has superiority on detail preservation and visual quality.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.1
• /
• pp.1-7
• /
• 2011

In this paper, we propose the digital image enhancement method including local tone reproduction and preservation of the hue. In recent studies, an integrated multi-scale retinex (IMSR) has produced great naturalness in the resulting images through enhancement of visibility in dark area in input images. However, most methods, including IMSR, work in RGB color spaces. As such, this produces hue distortion from the perspective of the human visual system, that is, hue distortion in CIELAB color space. Accordingly, this paper proposes an tone reproduction and enhancement of saturation method in a device-independent color space, CIELAB, to preserve the hue and obtain a high contrast and naturalness. First, to achieve the desired objectives, the IMSR is then applied to only the $L^*$ values in CIELAB color space, normalization, and simple mapping function, thereby preserving the balance of the color components and enhancement of visibility. Then, saturation adjustment is performed by applying the ratio of the chroma variation at the sRGB gamut boundary according to the corrected luminance. In experiments, the proposed method is shown to improve the visibility in dark shadows and bright regions in the resulting images and reduce any color distortion then preference test are performed.

• Proceedings of the IEEK Conference
• /
• 2000.07a
• /
• pp.58-61
• /
• 2000

In this paper, we describe an effective method to enhance the color night images with spatio-temporal multi-scale retinex focused to the Intelligent Transportation System (ITS) applications such as in the single CCD based Electronic Toll Collection System (ETCS). The basic spatial retinex is known to provide color constancy while effectively removing local shades. However, it is relatively ineffective in night vision enhancement. Our proposed method, STMSR, exploits the iterative time averaging of image sequences to suppress the noise in consideration of the moving vehicles in image frame. In the STMSR method, the spatial term makes the dark images distinguishable and preserves the color information day and night while the temporal term reduces the noise effect for sharper and clearer reconstruction of the contents in each image frame. We show through representative simulations that incorporating both terms in the modeling produces the output sequential images visually more pleasing than the original dim images.