• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.991-998
• /
• 2022

Recently, object recognition using image/video signals is rapidly spreading on autonomous driving and mobile phones. However, the actual input image/video signals are easily exposed to a poor illuminance environment. A recent researches for improving illumination enable to estimate and compensate the illumination parameters. In this study, we propose VE-DCE (video enhancement zero-reference deep curve estimation) to improve the illumination of low-light images. The proposed VE-DCE uses unsupervised learning-based zero-reference deep curve, which is one of the latest among learning based estimation techniques. Experimental results show that the proposed method can achieve the quality of low-light video as well as images compared to the previous method. In addition, it can reduce the computational complexity with respect to the existing method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.4 no.1
• /
• pp.25-44
• /
• 2010

With the increasing popularity of mobile devices, it has become necessary to protect private information and content in these devices. Face recognition has been favored over conventional passwords or security keys, because it can be easily implemented using a built-in camera, while providing user convenience. However, because mobile devices can be used both indoors and outdoors, there can be many illumination changes, which can reduce the accuracy of face recognition. Therefore, we propose a new face recognition method on a mobile device robust to illumination variations. This research makes the following four original contributions. First, we compared the performance of face recognition with illumination variations on mobile devices for several illumination normalization procedures suitable for mobile devices with low processing power. These include the Retinex filter, histogram equalization and histogram stretching. Second, we compared the performance for global and local methods of face recognition such as PCA (Principal Component Analysis), LNMF (Local Non-negative Matrix Factorization) and LBP (Local Binary Pattern) using an integer-based kernel suitable for mobile devices having low processing power. Third, the characteristics of each method according to the illumination va iations are analyzed. Fourth, we use two matching scores for several methods of illumination normalization, Retinex and histogram stretching, which show the best and $2^{nd}$ best performances, respectively. These are used as the inputs of an SVM (Support Vector Machine) classifier, which can increase the accuracy of face recognition. Experimental results with two databases (data collected by a mobile device and the AR database) showed that the accuracy of face recognition achieved by the proposed method was superior to that of other methods.

• Journal of the Optical Society of Korea
• /
• v.20 no.2
• /
• pp.234-238
• /
• 2016

A new method to design a low distortion, even relative illumination, optical see-through head-mounted display (HMD) with a freeform reflective mirror (FFRM) based on the two similar ellipsoids structure is proposed. The HMD we have realized has a simple structure which consists of two similar ellipsoid surfaces, an FFRM, a 7-piece co-axis relay lens, and an OLED. This structure can be applied to offset distortion, reach even relative illumination, and correct the off-axis aberrations. The HMD we finally have realized has a near 3% low distortion, a higher than 80% relative illumination, and a 40°×30° field of view (FOV).

• The Journal of the Korea Contents Association
• /
• v.13 no.10
• /
• pp.19-26
• /
• 2013

In the Malaysian license plates, alphabets and numerals which are made by plastic, are adhered to a frame as embossing style and occasionally characters in horizontal, vertical directions are aligned with narrow space. So the extraction of character stroke information can be hard in the vehicle images of low illumination intensity. In this paper, Malaysian license plate recognition algorithm for low illumination intensity image is proposed. DoG filtering based character stroke generation method is introduced to derive exact connected components of strokes in the vehicle image of low illumination intensity. After localization of plate by connected component analysis, characters are segmented and recognized. Algorithm is experimented for the 6,046 vehicle images captured in Kuala Lumpur by IR camera without using any special light during day and night. The experimental results show that recognition accuracy of plates is 96.1%.

• 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 Information Processing Systems
• /
• v.18 no.4
• /
• pp.575-586
• /
• 2022

Uneven light in real-world causes visual degradation for underexposed regions. For these regions, insufficient consideration during enhancement procedure will result in over-/under-exposure, loss of details and color distortion. Confronting such challenges, an unsupervised low-light image enhancement network is proposed in this paper based on the guidance of the unpaired low-/normal-light images. The key components in our network include super-resolution module (SRM), a GAN-based low-light image enhancement network (LLIEN), and denoising-scaling module (DSM). The SRM improves the resolution of the low-light input images before illumination enhancement. Such design philosophy improves the effectiveness of texture details preservation by operating in high-resolution space. Subsequently, local lightness attention module in LLIEN effectively distinguishes unevenly illuminated areas and puts emphasis on low-light areas, ensuring the spatial consistency of illumination for locally underexposed images. Then, multiple discriminators, i.e., global discriminator, local region discriminator, and color discriminator performs assessment from different perspectives to avoid over-/under-exposure and color distortion, which guides the network to generate images that in line with human aesthetic perception. Finally, the DSM performs noise removal and obtains high-quality enhanced images. Both qualitative and quantitative experiments demonstrate that our approach achieves favorable results, which indicates its superior capacity on illumination and texture details restoration.

• Korean Institute of Interior Design Journal
• /
• v.19 no.4
• /
• pp.82-89
• /
• 2010

The studies published up to now, related to the correlation between spatial structure and visitors' behavior in a museum are rather relatively lacking when it comes to the in-depth consideration for the effect of the actual exhibition environment. So the main purpose of this study is to define the correlation between the light environment and the visitors' behavior. Towards this end, this study uses 'space syntax' to quantify the spatial structure with 'integration', 'connectivity' and 'control value'. Meanwhile, 'tracking score' and 'tracking frequency' were selected as the scope among the indices of behavior's analysis. The results of this study are as follows; First, integration and correlation of tracking score and tracking frequency are lowest when it comes to the extra large historical museums where the difference of intensity of illumination by each convex space. Meanwhile, the most considerable effect is exerted by control value. Compared to tracking score, tracking frequency is closely related to 'syntactic variables'. Second, visitors do not take the short cut the dark exhibition space even when very dark exhibition spaces continue after passing through relatively bright space. Analysis of visitors' behavior by control value in the exhibition space composed of this type of intensity of illumination environment is not valid. Third, visitors move to relatively brighter transitional space compared to the exhibition space with low intensity of illumination when passing through dark exhibition continually. Meanwhile, when visitors pass through the exhibition space there is some difference intensity of illumination they move to relatively dark exhibition center among the subsequent exhibition spaces. Accordingly, when the composition of exhibition space that continues onto the environment of low intensity of illumination is inevitable, differentiating intensity of illumination appropriately would be effective in inducing visit to the subsequent exhibition space.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.22 no.2
• /
• pp.185-196
• /
• 2020

Low-pressure sodium lamps, high-pressure sodium lamps and fluorescent lamps etc are mainly used tunnel lighting in Rep. of Korea. Power rates for tunnel lighting are known to account for the highest percentage in the tunnel maintenance costs. Therefore, tunnel lights are being replaced by LED that have advantages such as low power consumption and longevity. To analysis effect of replacement low pressure sodium lamp with LED, illumination and monthly power usage for a year are investigated for 8 tunnels. Power usage for tunnel lighting is decreased by 26.1% to 59.6%, and illumination is increased by 34.1% to 293% replacing low pressure sodium lamp with LED.

• The Journal of Korea Robotics Society
• /
• v.6 no.2
• /
• pp.173-181
• /
• 2011

Recognition of traffic signs helps an unmanned ground vehicle to decide its behavior correctly, and it can reduce traffic accidents. However, low cost traffic sign recognition using a vision sensor is very difficult because the signs are exposed to various illumination conditions. This paper proposes a new approach to solve this problem using an illuminometer which detects the intensity of illumination. Using the intensity of illumination, the recognizer adjusts the parameters for image processing. Therefore, we can reduce the loss of information such as the shape and color of traffic signs. Experimental results show that the proposed method is able to improve the performance of traffic sign recognition in various weather and lighting conditions.

• Journal of the Semiconductor & Display Technology
• /
• v.16 no.3
• /
• pp.14-19
• /
• 2017

In this paper, a fused illumination mechanism for detecting surface defects in steel plates was designed by applying the discriminant function that can differentiate the contrast of defects and non-defects. There is low contrast, non-uniformity, and no feature characteristics in steel plate surfaces. The fused illumination mechanism is devised, based on those characteristics. Optimum parameters of the fused illumination mechanism are determined by applying the discriminant function after acquiring the defect image in steel plate surfaces. The performance of the proposed mechanism is verified by experminets.