• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.34S no.6
• /
• pp.21-29
• /
• 1997

In this paper, we propose a new approach for recovering 3-D shape and extracting the reflectance properties of surface from intensity images. Photometric stereo method(PSM) is genrally based on the direct illumination. In this paper, the reflectance function is derived by interoduceing the indirect diffuse illumination in PSM and then applied to hybrid reflectance model which consists of two components; the lambertian and the specular reflectance. Under the hybrid reflectance model and the indirect diffuse illumination circumstance, the reflectance properties of sample surface can be extracting by normal sampler and then 3-D shape of an object can be recovered based on extracting reflectance properties. This method is rapid because of using the reference table and simplifies the restriction condition about the reflectance function existing in prior studies. Th erecovery efficiency in our method is better than that in prior studies. Also, this method is applied to various types of surfaces by defining general reflectance function.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.12
• /
• pp.1115-1121
• /
• 2015

Fast inspection of solder ball bumps in ball grid array (BGA) is an important issue in the flip chip bonding technology. Particularly, semiconductor industry has required faster and more accurate inspection of micron-size solder bumps in flip chip bonding, as the density of balls increase dramatically. In this paper, we describe an inspection approach of BGA balls by using 5-step ring illumination device and normalized cross-correlation (NCC) method. The images of BGA ball by the illumination device show unique and distinguishable characteristic contours by their 3-D shapes, which are called as "iso-slope contours". Template images of reference ball samples can be produced artificially by the hybrid reflectance model and 3D data of balls. NCC values between test and template samples are very robust and reliable under well-structured condition. The 200 samples on real wafer are tested and show good practical feasibility of the proposed method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.3A
• /
• pp.276-283
• /
• 2002

This paper proposes a new color constancy algorithm using the maximum luminance surface. This method uses a linear model which represents the characteristics of human visual system. The most important process of linear model is the estimation of the spectral distributions of illumination from an input image. To estimate of the spectral distributions of illumination from an input image, we first estimate spectral distribution functions of reflected light on the brightest surface. Then, we estimate surface reflectance functions corresponding to the maximum luminance surface using a principal component analysis of the given munsell chips. We finally estimate the spectral distributions of illumination in an image. Using an estimated illumination, we recover an image by scaling it regularly for the lightness calibration. From the experimental results, the proposed method was effective in recovering the color images compared with others.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1287-1292
• /
• 2005

This paper presents an effective pattern classification model by designing an artificial neural network based pattern classifiers for face recognition. First, a RGB image inputted from a frame grabber is converted into a HSV image which is similar to the human beings' vision system. Then, the coarse facial region is extracted using the hue(H) and saturation(S) components except intensity(V) component which is sensitive to the environmental illumination. Next, the fine facial region extraction process is performed by matching with the edge and gray based templates. To make a light-invariant and qualified facial image, histogram equalization and intensity compensation processing using illumination plane are performed. The finally extracted and enhanced facial images are used for training the pattern classification models. The proposed H-ART2 model which has the hierarchical ART2 layers and F-LVQ model which is optimized by fuzzy membership make it possible to classify facial patterns by optimizing relations of clusters and searching clustered reference patterns effectively. Experimental results show that the proposed face recognition system is as good as the SVM model which is famous for face recognition field in recognition rate and even better in classification speed. Moreover high recognition rate could be acquired by combining the proposed neural classification models.

• Journal of the Optical Society of Korea
• /
• v.15 no.1
• /
• pp.38-43
• /
• 2011

We have developed a simple model of a bright-room contrast ratio (BRCR) measurement system for plasma display panels (PDPs) adopting a contrast enhancement film (CEF) by using an illumination design tool. Only four model parameters were used, namely, total ambient illumination power delivered by fluorescent lamps, a panel scattering rate, illuminance of PDP white patterns, and the absorption coefficient of a color adjusting film. These parameters were determined by simple optical measurements and matching simulations. The proposed model was employed to predict the BRCR values of four different CEF samples, and the simulated ones were found to be in agreement with measured ones within about 10% relative-error.

• Journal of Information Processing Systems
• /
• v.14 no.6
• /
• pp.1307-1317
• /
• 2018

To deal with the problems of occlusion, pose variations and illumination changes in the object tracking system, a regression model weighted multi-templates mean-shift (MS) algorithm is proposed in this paper. Target templates and occlusion templates are extracted to compose a multi-templates set. Then, the MS algorithm is applied to the multi-templates set for obtaining the candidate areas. Moreover, a regression model is trained to estimate the Bhattacharyya coefficients between the templates and candidate areas. Finally, the geometric center of the tracked areas is considered as the object's position. The proposed algorithm is evaluated on several classical videos. The experimental results show that the regression model weighted multi-templates MS algorithm can track an object accurately in terms of occlusion, illumination changes and pose variations.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.26 no.9
• /
• pp.1-7
• /
• 2012

In this paper, we present a new lighting control method considering ambient light in addition to the required lighting illumination for efficient energy saving of a LED stand. We estimate accurate environmental illuminance using a cheap illuminance sensor by modeling measured- and actual-illuminance using quadratic polynomial approximation. The relation between PWM(Pulse Width Modulation) duty ratio and illuminance intensity is modeled by a linear model. Illumination of the LED stand is controlled by estimating the difference of required illumination and the estimated ambient illumination. The developed LED stand has reduced electric energy consumption compared with a conventional manually controlled LED stand with the same lighting source. In addition, human subject evaluation shows that the LED stand, which is applied the proposed method, is more satisfactory than conventional ones since the proposed automatic controlled illumination produce more accurately required lighting and it is convenient.

• Journal of Broadcast Engineering
• /
• v.21 no.2
• /
• pp.268-271
• /
• 2016

In video sequences, foreground object detection being composed of a background model and a background subtraction is an important part of diverse computer vision applications. However, object detection might fail in sudden illumination changes. In this letter, an illumination-robust background detection is proposed to address this problem. The method can provide quick adaption to current illumination condition using two background models with different adaption rates. Since the proposed method is a non-parametric approach, experimental results show that the proposed algorithm outperforms several state-of-art non-parametric approaches and provides low computational cost.

• Journal of KIISE
• /
• v.42 no.2
• /
• pp.203-212
• /
• 2015

This paper proposes a traffic sign recognition method in real road environments. The video stream in driving environments has two different characteristics compared to a general object video stream. First, the number of traffic sign types is limited and their shapes are mostly simple. Second, the camera cannot take clear pictures in the road scenes since there are many illumination changes and weather conditions are continuously changing. In this paper, we improve a modified census transform(MCT) to extract features effectively from the road scenes that have many illumination changes. The extracted features are collected by histograms and are transformed by the dense descriptors into very high dimensional vectors. Then, the high dimensional descriptors are encoded into a low dimensional feature vector by Fisher-vector coding and Gaussian Mixture Model. The proposed method shows illumination invariant detection and recognition, and the performance is sufficient to detect and recognize traffic signs in real-time with high accuracy.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.62 no.5
• /
• pp.63-72
• /
• 2020

Solar-sharing, which is an agricultural photovoltaic system installing solar panels on the upper part of crop growing field, has especially drawn attention. Because paddy fields for cultivating crops are large flat areas, there have been various attempts to utilize solar energy for solar photovoltaic as well as growth of crops in agriculture. Solar-sharing was first proposed in Japan, and has been actively studied for optimization and practical uses. The domestic climate differs from the climate conditions in which the solar-sharing has been widely studied, therefore, it is required to develop the solar-sharing technology suitable for the domestic climate. In this study, a simulation model was developed to analyze the change of solar radiation resulted from the solar-sharing installation. Monthly solar illumination intensity and the change of illumination intensity according to the various conditions of solar panel installation were simulated. The results of monthly illumination analysis differed by altitude of the sun, which was related to season. In addition, it was analyzed that the monthly illumination decreased by up to 42% due to solar-sharing. Accordingly, it is recommended that solar-sharing should be installed as a way to maximize the efficiency of solar photovoltaic system while minimizing the decrease in solar radiation reaching the crops.