• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.6
• /
• pp.468-476
• /
• 2002

The confidence of information from image processing depends on the original image quality. Enhancing the confidence by an algorithm has an essential limitation. Especially, road images are exposed to lots of noisy sources, which makes image processing difficult. We, in this paper, propose a FNN (fuzzy-neural network) capable oi deciding the quality of a road image prior to extracting lane-related information. According to the decision by the FNN, road images are classified into good or bad to extract lane-related information. A CDF (cumulative distribution function), a function of edge histogram, is utilized to construct input parameters of the FNN, it is based on the fact that the shape of the CDF and the image quality has large correlation. Input pattern vector to the FNN consists of ten parameters in which nine parameters are from the CDF and the other one is from intensity distribution of raw image. Correlation analysis shows that each parameter represents the image quality well. According to the experimental results, the proposed FNN system was quite successful. We carried out simulations with real images taken by various lighting and weather conditions and achieved about 99% successful decision-making.

• Journal of the Korean Solar Energy Society
• /
• v.34 no.4
• /
• pp.91-99
• /
• 2014

The purpose of the study is to apprehend the preference of occupants to colors and installation locations for DSC combined windows and doors, and suggest a concept to optimize the design and function of windows and doors. A miniature model was made applying green, blue, and red colored DSC windows and doors to survey preference about DSC colors and applied location. And a survey was accomplished to 140 subjects by showing pictures of the model and the result of the survey became the basis for suggesting a concept to design DSC integrated windows and doors. Through the survey, blue color and upper part were chosen as the highest level of satisfaction in the situation of external brightness and residence. On the contrary to this, red color was chosen as the lowest level of preference when applied to both of upper and lower parts of winders and doors. Therefore, it's expected that, if various patterns of texture are developed for blue colored DSC, and installation is arranged based on upper part of windows and doors where lighting condition and comfort are less affected, then, conditions of brightness, view, and residents satisfaction will be equally fulfilled.

• Agricultural and Biosystems Engineering
• /
• v.4 no.1
• /
• pp.16-21
• /
• 2003

In the agricultural field, a machine vision system has been widely used to automate most inspection processes especially in quality grading. Though machine vision system was very effective in quantifying geometrical quality factors, it had a deficiency in quantifying color information. This study was conducted to evaluate color of beef using machine vision system. Though measuring color of a beef using machine vision system had an advantage of covering whole lean tissue area at a time compared to a colorimeter, it revealed the problem of sensitivity depending on the system components such as types of camera, lighting conditions, and so on. The effect of color balancing control of a camera was investigated and multi-layer BP neural network based color calibration process was developed. Color calibration network model was trained using reference color patches and showed the high correlation with L*a*b* coordinates of a colorimeter. The proposed calibration process showed the successful adaptability to various measurement environments such as different types of cameras and light sources. Compared results with the proposed calibration process and MLR based calibration were also presented. Color calibration network was also successfully applied to measure the color of the beef. However, it was suggested that reflectance properties of reference materials for calibration and test materials should be considered to achieve more accurate color measurement.

• Plant Biotechnology Reports
• /
• v.4 no.4
• /
• pp.303-309
• /
• 2010

Endoreduplication is a developmental process that is unique to plants and occurs in all plants. The present study aimed to assess endoreduplication in various explant tissues and regenerated somatic embryos of Doritaenopsis. We further investigated the effects of light quality on endoreduplication and somatic embryo proliferation. To this end, we studied endoreduplication in leaves and root tips from regenerated plantlets and somatic embryos and in developing somatic embryos under 4 types of lighting conditions: red light, red + far-red light, red + blue light, and white light. We found that the degree of endoreduplication varied in different explants, and that the choice of explants used also influenced the ploidy levels of the newly regenerated somatic embryos. The DNA content of the leaf (2C-8C) was less than that of the root tip (2C-16C) and somatic embryo (2C-64C). In terms of light quality, the combination of red and far-red light produced the highest number of somatic embryos, while maintaining a low degree of endoreduplication. The data obtained indicate that this light combination stimulates somatic embryogenesis in Doritaenopsis and may exert some control on endoreduplication during cell division. These findings can be applied to achieve a reduction in somaclonal variations for the purpose of mass proliferation and genetic improvement.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.4
• /
• pp.1203-1222
• /
• 2012

To provide active notification and enhance drivers'awareness of their surroundings, a vision-based collision warning system that detects and monitors surrounding vehicles is proposed in this paper. The main objective is to prevent possible vehicle collisions by monitoring the status of surrounding vehicles, including the distance to the other vehicles in front, behind, to the left and to the right sides. In addition, the proposed system collects and integrates this information to provide advisory warnings to drivers. To offer the correct notification, an algorithm based on features of edge and morphology to detect vehicles is also presented. The proposed system has been implemented in embedded systems and evaluated on real roads in various lighting and weather conditions. The experimental results indicate that the vehicle detection ratios were higher than 97% in the daytime, and appropriate for real road applications.

• Journal of the Korean housing association
• /
• v.17 no.2
• /
• pp.47-54
• /
• 2006

The purpose of this study is to investigate residential characters and consciousness about housing environment concerned with earth housing, and to suggest basic data reflectible on the planning of earth housing. Residential characters and consciousness are investigated with the people lived in forty seven earth housings located in nationwide scale through interviews and questionnaire. As a result, it is shown that a reason of health like sick house syndrome, residential environments such as ventilation and lighting, site environment such as neighbor and greenfield are very influential elements to the consciousness of inhabitants. Meanwhile, approximation of residential area, the connection with public facilities including medical service, educational and commercial conditions, additionally, preparation of disaster and crime prevention in a viewpoint of safety are pointed out as relatively weak ones. It means that earth housing is not systematically fixed as a residential site because it is personally progressed by small number of peoples having different reasons. For the improvement of systematic housing environment, development and proposition of various model are needed on earth housing and its site.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.45 no.2
• /
• pp.8-17
• /
• 2008

This paper proposes a robust license plate extraction method from images taken under unconstrained environments. Utilization of the color and the edge information in complementary fashion makes the proposed method deal with not only various lighting conditions, hilt blocking artifacts frequently observed in compressed images. Computational complexity is significantly reduced by applying Hough transform to estimate the skew angle, and subsequent do-skewing procedure only to the candidate regions. The true plate region is determined from the candidates under examination using clues including the aspect ratio, the number of zero crossings from vertical scan lines, and the number of connected components. The performance of the proposed method is evaluated using compressed images collected under various realistic circumstances. The experimental results show 94.9% of correct license plate extraction rate.

• The KIPS Transactions:PartB
• /
• v.15B no.4
• /
• pp.259-268
• /
• 2008

In an effort to increase the data capacity of one-dimensional symbology, 2D barcodes have been proposed a decade ago. In this paper, we present an effective 2D barcode detection algorithm from gray-level images, especially for the handheld 2D barcode recognition system. To locate the symbol inside the image, a criteria based on the block contrast is adopted, and a gray-scale projection with sub-pixel operation is utilized to segment the symbol precisely from the region of interest(ROI). Finally, the segmented ROI is normalized using the inverse perspective transformation for the following decoding processes. We also introduce the post-processing steps for decoding the QR-code. The proposed method ensures high performances under various lighting/printing conditions and strong perspective deformations. Experiments shows that our method is very robust and efficient in detecting the code area for the various types of 2D barcodes in real time.

• Korean Journal of Materials Research
• /
• v.9 no.7
• /
• pp.707-714
• /
• 1999

To save electrical energy as much as 40 % for fluorescent lighting, the reflectors coated with silver reflective thin films recently became popular with higher reflectivities and long life. The thin films fabricated by using sputtering techniques are produced mainly in U.S.A. On the other hand, some silver films deposited by using evaporation methods show low adhesion in general, although the reflectivity is no problem. We have studied various PVD methods to obtain thin films with high reflectivity and adhesion on a substrate of polyester, for a couple of years. Silver films manufactured byusing evaporation showed the reflectivity of 96.4 % and the adhesion of $12 kg/\textrm{cm}^2$. while samples manufactured by using sputtering depicted the adhesion as much as $20 Kg/\textrm{cm}^2$ that is almost double, although their reflectivity was not much different. X-ray diffraction spectra for the sputtered films demonstrated a preferential growth on (111) plane and the cross-sections of the specimens revealed a dense columnar structure to result in the enhanced adhesion.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.5
• /
• pp.1117-1124
• /
• 2018

Contrast enhancement plays an important role in various computer vision systems, since their usability can be improved with visibility enhancement of the images affected by weather and lighting conditions. This paper introduces a histogram modification algorithm that reflects the properties of original images in order to eliminate the saturation effect and washed-out of image details due to the over-enhancement. Our method modifies the original histogram so that an additive term fill histogram pits and the gamma correction suppresses histogram spikes. The parameters for the additive term and gamma correction are adjusted automatically according to statistical properties of the images. Experimental results for various low contrast and hazy images demonstrate that the proposed contrast enhancement improves visibility and reduces haze components effectively, while preserving the characteristics of original images, than the conventional methods.