• International Journal of Contents
• /
• v.10 no.4
• /
• pp.1-10
• /
• 2014

In this paper, we propose a method to build an accurate initial trimap for the GrabCut algorithm without the need for human interaction. First, we identify a rough candidate for the label region of a bottle by applying a saliency map to find a salient area from the image. Then, the Hough Transformation method is used to detect the left and right borders of the label region, and the k-means algorithm is used to localize the upper and lower borders of the label of the bottle. These four borders are used to build an initial trimap for the GrabCut method. Finally, GrabCut segments accurate regions for the label. The experimental results for 130 wine bottle images demonstrated that the saliency map extracted a rough label region with an accuracy of 97.69% while also removing the complex background. The Hough transform and projection method accurately drew the outline of the label from the saliency area, and then the outline was used to build an initial trimap for GrabCut. Finally, the GrabCut algorithm successfully segmented the bottle label with an average accuracy of 92.31%. Therefore, we believe that our method is suitable for product label recognition systems that automatically segment product labels. Although our method achieved encouraging results, it has some limitations in that unreliable results are produced under conditions with varying illumination and reflections. Therefore, we are in the process of developing preprocessing algorithms to improve the proposed method to take into account variations in illumination and reflections.

• Journal of Environmental Health Sciences
• /
• v.38 no.2
• /
• pp.118-127
• /
• 2012

Objectives: This study was undertaken to assess the sanitary conditions in the kitchens of food court/cafeterias and determine seasonal variations. Methods: We measured environmental factors (air temperature, relative humidity, illumination intensity, noise level), and dropping airborne microbes (bacteria and fungi) in the kitchens of eight food court/cafeterias in four seasons (January, April, July, and October). Air temperature and relative humidity were measured with in/out thermo-hygrometers at 1.2-1.5 m above floor level. Illuminance measurement was performed through the multiple point method of Korean Standards (KS). Noise level was measured by the standard methods for the examination of environmental pollution (noise and vibration) of Korea. The estimation of dropping airborne bacteria and fungi was performed through use of Koch's method. Results: The highest kitchen air temperature was in July, and the lowest in January. The average temperature surpassed $21^{\circ}C$ throughout the seasons, suggesting a higher temperature than required for the safe handling of food. Humidity in all the kitchens was measured in the range of 50-60%. Half of the kitchens showed illumination intensities below 300 Lux in April. It was found that the sound pressure level of noise in almost all of the kitchens was higher than 85 dB (A). The highest levels of dropping airborne bacteria and fungi were noted in July. The numbers of airborne bacteria were higher than those of fungi. The levels of dropping airborne bacteria and fungi were affected by air temperature, relative humidity, season, and place. Conclusions: This study indicates that the kitchen environments were unqualified to supply safe food. The hygiene level of the kitchens should be improved.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.25 no.2
• /
• pp.37-43
• /
• 1989

The purpose of this study is to find the light intensity which induced maximum gathering rate and to observe the variation of the gathering rate both in daytime and at night by suing Rudder fish, Girella punctata(Gray). An experimental tank(360L*50W*55H cm) was set up in a dark room. An illumination system was attached to the end of one side of the tank to control horizontal light intensity. Eight artificial light sources were prepared by combination of three light bulbs(10W, 60W, 100W) and eight filters. During the experiment water depth was maintained 50cm level in the tank. The tank was marked into six longitudinal sections each being 60cm long to observe the distribution of fish. The fish were acclimatized in dark condition for 50 minutes prior to the main experiment. Upon turning on the light, the number of fish in each section was counted 60 times every 30 seconds, and the gathering rate was obtained from the average number of fish in each section. The light intensity inducing maximum gathering rate was 2.98 lux(1.90-4.40 lux) at daytime and 298.56 lux(188.44-444.96 lux) at night. The variation of the gathering rate of fish in illumination time was great and irregularly fluctuated, but did not show any definite pattern. It was somewhat difference between daytime and night.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.10
• /
• pp.3490-3507
• /
• 2014

License plate detection (LPD) is one of the most important aspects of an automatic license plate recognition system. Although there have been some successful license plate recognition (LPR) methods in past decades, it is still a challenging problem because of the diversity of plate formats and outdoor illumination conditions in image acquisition. Because the accurate detection of license plates under different conditions directly affects overall recognition system accuracy, different methods have been developed for LPD systems. In this paper, we propose a license plate detection method that is rapid and robust against variation, especially variations in illumination conditions. Taking the aspects of accuracy and speed into consideration, the proposed system consists of two stages. For each stage, Haar-like features are used to compute and select features from license plate images and a cascade classifier based on the concatenation of classifiers where each classifier is trained by an AdaBoost algorithm is used to classify parts of an image within a search window as either license plate or non-license plate. And it is followed by connected component analysis (CCA) for eliminating false positives. The two stages use different image preprocessing blocks: image preprocessing without adaptive thresholding for the first stage and image preprocessing with adaptive thresholding for the second stage. The method is faster and more accurate than most existing methods used in LPD. Experimental results demonstrate that the LPD rate is 98.38% and the average computational time is 54.64 ms.

• Korean Journal of Optics and Photonics
• /
• v.23 no.2
• /
• pp.55-63
• /
• 2012

We present results of optical design and fabrication of a light guiding plate (LGP) to be used as an illumination system for photobioreactors. Modeling of a light-emitting diode (LED) light source, a reflection film, and LGP patterns was performed. Especially, the LGP patterns were modeled as Lambertian scatterers. The modeling parameters (reflectance, scatterer width) were determined through matching simulations with the experimentally measured illuminance distribution for a test LGP. An LGP for an LED light source was designed with the extracted model parameters, and fabricated using a computerized numerical control machine. Optical characteristics including average illuminance and uniformity of illuminance distribution were measured for the fabricated LGP.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.1
• /
• pp.57-64
• /
• 2013

In this paper, we propose the classification method of medicine bottle images using the features with color and size information. It is difficult to classify with size feature only, because there are many similar sizes of bottles. Therefore, we suggest a classification method based on color information, which robust to illumination variations. First, we extract MBR(Minimum Boundary Rectangle) of medicine bottle area using Binary Threshold of Red, Green, and Blue in image and classify images with size. Then, hue information and RGB color average rate are used to classify image, which features are robust to lighting variations. Finally, using SURF(Speed Up Robust Features) algorithm, corresponding image can be found from candidates with previous extracted features. The proposed method makes to reduce execution time and minimize the error rate and is confirmed to be reliable and efficient from experiment.

• Journal of the Korean housing association
• /
• v.20 no.3
• /
• pp.1-10
• /
• 2009

The final aim of this study was to propose guidelines for the indoor environment of apartment remodeling projects. The first task of this study was to understand the major elements and the actual condition of the remodeling for apartment unit by carrying out in-depth interviews on residents and specialists. The open-access interviews were conducted with interior designers who have a wide experience of apartment remodeling and residents who live in recently remodeled apartment units. The second task was to evaluate the actual condition of the indoor environment and to analyze the main factors that affect the indoor environment in remodeled apartment units. Field measurements were carried out in twenty apartment units occupied after remodeling, recording indoor environment elements (indoor temperature, globe temperature, relative humidity, $CO_2$, CO, PM10, TVOC, HCHO, illumination, and equivalent noise level). Moreover, resident interviews and researcher observations were carried out to determine the contents of the remodeled unit and to investigate the architectural and living factors(like ventilation characteristics, etc.) related to the indoor environment. The results are as follows. The remodeling elements generally included the changing of lighting fixtures and finishing materials in all the spaces, the integration of the balcony into the children's room, the installation of furniture in the kitchen and the entrance, the changing storage furnitures and equipments in the bathroom. The average levels of each unit of relative humidity, $CO_2$, TVOC, HCHO, equivalent noise level, and illumination were proved to be on the whole in inadequate condition. The factors that affect these indoor elements were classified as remodeling factors (remodeling amounts, extent balcony integration, and lighting fixture exchange), ventilation characteristics, and living factors. According to these results, this research proposed the guidelines for the indoor environment in apartment remodeling projects.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.42 no.3 s.303
• /
• pp.63-70
• /
• 2005

The electrodeless lamps using the induction discharge have a long lifetime and a high tolerance for the variable output conditions of a ballast since they don't need the electrodes. This paper proposed two novel dimming algorithms for the Electrodeless lamps and described the resonant inverter adopted the proposed methods. The proposed dimming algorithms are based on the conventional burst dimming method which is normally adopted for LCD back-lights. One of the proposed algorithms is a improved burst dimming method, which controls the illumination by duty ratio of $5\%$ and its control circuit is formed by simple digital logics. The other algorithm is a burst PWM average duty ratio control method, which controls the illumination by duty ratio of $1\%$ and its control circuit is formed by more complex digital logics than the first method. To verify the validity of the proposed dimming methods, a prototype experimental setup for 100W Electrodeless lamps is carried out and its results are presented in this paper.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2002.08a
• /
• pp.807-810
• /
• 2002

$GdPO_4$:Tb phosphor particles with spherical shape and high photoluminescence were prepared by spray pyrolysis. The brightness of prepared $GdPO_4$:Tb under the vacuum ultraviolet(VUV) illumination was comparable with that of the commercial $Zn_2SiO_4$:Mn phosphor particles. The photoluminescence spectra of $GdPO_4$:Tb phosphor particles had maximum peak at 547 nm, and the sharp peaks at 480 nm, 580 nm, and 620 nm. The spherical morphology of prepared $GdPO_4$:Tb particles was completely maintained even after the posttreatment up to 1100 $^{\circ}C$. When the posttreatment temperature was over 1100 $^{\circ}C$, the particles did not have the spherical shape anymore. The average particle size of $GdPO_4$:Tb phosphor particles prepared by using $(NH_4)_2HPO_4$ was changed from 0.5 to 1.9 ${\mu}m$ and its effect on the PL intensity was investigated. It was found that the optimized $GdPO_4$:Tb particles have a good excitation spectrum comparable to that of the commercial $Zn_2SiO_4$:Mn phosphor particles under the VUV illumination from 140 to 220 nm. We concluded that the $GdPO_4$:Tb phosphor particles with spherical shape prepared by spray pyrolysis is a promising candidate for a green-emitting PDP phosphor.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.24 no.4
• /
• pp.144-149
• /
• 1988

The purpose of this study is to find the light intensity which induced maximum gathering rate and to observe the variation of the gathering rate both in daytime and tat night by using Striped puffer, Fugu xanthopterus (Temminck et Schlegel). An experimental tank(360L$\times$50W$\times$55H cm) was set up in a dark room. An illumination system was attached to the end of one side of the tank to control horizontal light intensity. Eight artificial light sources were prepared by combination of three light bulbs (10W, 60W, 100W) and eight filters. During the experiment water depth was maintained 50 cm level in the tank. The tank was marked into six longitudinal sections each being 60cm long to observe the distribution of fish. The fish were acclimatized in dark condition for 50 minutes prior to the main experiment. Upon turning on the light, the number of fish in each section was counted 60 times every 30 seconds, and the gathering rate was obtained from the average number of fish in each section. The light intensity inducing maximum gathering rate was 298.56 lux (188.44-444.96 lux) at daytime and 298.56 lux (188.44-444.96 lux) at night. The variation of the gathering rate of fish in illumination time was increasing trend fluctuately and did not show any distinctive difference between day and night.