• Journal of Korea Multimedia Society
• /
• v.14 no.3
• /
• pp.356-367
• /
• 2011

In this paper, we proposed a new car engine sealing inspection system based on image processing and understanding. The car engine sealing inspection plays very important role for protecting leakage caused by inappropriate sealing, which is a crucial point for productivity of car engines. The proposed inspection system has been aimed to enhance the previously proposed sealing inspection systems based on image processing, which have high computation complexity and low performance for correctly inspecting some contamination by oil with similar color with that of sealing. Moreover, the previously proposed system has a difficulty in installing the camera system on the sealing machine. The proposed system considers a difference of images before and after sealing obtained from one static camera. By utilizing a difference of images, the proposed system shows very robust performance using a proposed simple depth checking algorithm for some contamination cases by oil with similar color with that of sealing and the total inspection system is simple and cheap to implement. According to the experiments conducted in a real car product line, the proposed inspection system shows better inspection performance and needs smaller implementation cost than three other previously proposed system working in current car sealing inspection systems.

• Journal of Fashion Business
• /
• v.18 no.2
• /
• pp.66-79
• /
• 2014

The purpose of this study was to find out the difference between preferred hairstyle and pursued-image of hairstyle according to demographic characteristics. The method of this study is a content analysis and survey research using a questionnaire, which consisted of items of pursued-image of hairstyle, preferred hairstyle and demographic characteristics. 450 women were selected as subjects of this study; they were randomly selected from hair salon located in Seoul, Inchon and Bundang. For the material analysis, We used the statistical program of SPSS 12.0; frequencies, factor nalysis, one-way ANOVA and Duncan's multiple range test, T Test and ${\chi}^2$ Test were carried out as the methods of analysis. The research findings were as follows. First, the results of hairstyles according to the content analysis usually resulted 5 hairstyles, such as cuts and crew cut, bobbed hair, long layered hair styles and nonelayered long hair styles. Second, under the survey regarding the difference of preferred hairstyle and pursued-image of hairstyle according to demographic characteristics. variety of hair styles due to the subjects were more willing to try a consciousness about other's suggestions and how they are portrayed. Moreover a low level of education was ralated to a attempting a variety of styles, considering their social life. Subjects with higher age, education level and salary preferred a glamorous image as well as crew cuts. Which made them look younger. However, when they were younger, they preferred long nonelayered hair styles. In conclusion, age, average monthly income and education level are important variations affecting the property of change in hairstyles and pursued-image of hairstyles.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.13 no.4
• /
• pp.284-290
• /
• 2013

Feature detection is very important to image processing area. In this paper we compare and analyze some characteristics of image processing algorithms for corner and blob feature detection. We also analyze the simulation results through image matching process. We show that how these algorithms work and how fast they execute. The simulation results are shown for helping us to select an algorithm or several algorithms extracting corner and blob feature.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.51 no.4
• /
• pp.37-42
• /
• 2009

This study extracted Near Infrared (NIR) band using Image Processing Technology (IPT), and calculated Normalized Difference Vegetation Index (NDVI). Aerial photography from Daum portal in combination with high resolution satellite image was employed to improve vegetation sensitivity by extracting NIR band and calculating NDVI with comparison to QuickBird result. The extracted NIR band and NDVI through IPT presented similar distribution pattern. In addition, a regression analysis by land cover character showed high correlation paddy and forest Therefore, this approach could be acceptable to acquire vegetation environment information.

• Journal of the Korean Society of Visualization
• /
• v.13 no.3
• /
• pp.15-19
• /
• 2015

We developed a high-throughput microscopy (HTM) method which enabled us to replace a conventional phase contrast microscopy (PCM) method that has been used as a standard analytical method for airborne asbestos. We could obtain the concentration of airborne asbestos fibers under detection limit by automated image processing and analysis using HTM method. Here we propose an improved image processing algorithm with variable parameters to enhance the accuracy of the HTM analysis. Since the variable parameters that compensate the difference of the brightness are applied to the individual images in our new image processing method, it is possible to enhance the accuracy of the automatic image analysis method for sample slides with low asbestos concentration that caused errors in binary image processing. We demonstrated that enumeration of fibers by improved image processing algorithm remarkably enhanced the accuracy of HTM analysis in comparison with PCM. The improved HTM method can be a potential alternative to conventional PCM.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.14 no.6
• /
• pp.6-11
• /
• 2000

The Purpose of this study was to investigate the Color Image according of Language and Nonlanguage stimulant. 185 university students were selected in this experimental study. The result of this study were as follow:It was classified into the sense of activity, warmth, refinement and weight by Factors Analysis. There was significant difference between Language and Nonlanguage stimulant. Namely, the evaluation of color image by Nonlanguage stimulant was expressed strong. In particular, Red and Yellow were not shown the difference of evaluation by the stimulant. But Blue and Green were shown the difference of evaluation.

• Journal of the Semiconductor & Display Technology
• /
• v.10 no.4
• /
• pp.95-100
• /
• 2011

This paper proposes a new method of vehicle brake lights detection and recognition using an R-filtering. Firstly, the proposed method processes the R-filtering with the first input image and then with the second one in order to detect brake lights. Secondly, the method counts the number of red pixels and computes the mean value in each R-filtered image. The difference rates between the numbers of the red pixels and between the mean values of two images are defined in this paper. Through the analysis of the difference rates, it can recognize whether brake lights are turned on or off, and whether the vehicle ahead is being approached or not. The proposed method is implemented using C language in an embedded Linux system for a high-speed real-time image processing. Experiment results show that the proposed algorithm is quite successful.

• Journal of Fashion Business
• /
• v.10 no.4
• /
• pp.70-77
• /
• 2006

The purpose of this study is to evaluate the differences of visual image by variations in the location and width of the waist band of the one-piece dress. The stimuli are 24 samples: 8 variations of the location of the waist band and 3 variations of the width of the waist band. The data has been obtained from 50 fashion design majors. The data has analyzed by Factor Analysis, Anova, Scheff's Test and the MCA method. The results of the study are as follows. According to the result of factor analysis of the visual image based on the changes in the location and width of waist bands, three factors were identified- attractiveness, elegance and practicality. Among them, attractiveness was found to be the most important. The visual image was evaluated positively when waist bands were positioned above the natural waist line and negatively when waist bands were positioned below the natural waist line regardless of their width. In addition, the visual image based on the width of waist bands for one-piece dress was the most positive when the width was 4.5cm. No significant difference was observed in the visual image according to band width when the waist bands were positioned below the natural waist line. The interaction of visual image according to the location and width of waist bands for one-piece dress did not appear. As the main effect, significant differences were observed in all of the three factors according to the location of waist bands, but only two factors excluding elegance showed some difference according to the width of waist bands. When multiple classification analysis was applied to the factors without interaction, the location of waist bands appeared to have more significant effect on visual image than the width of waist bands.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.42 no.5
• /
• pp.571-578
• /
• 1997

The development of new approaches for wheat grain hardness assessment may impact the grain industry in marketing, milling and breeding. This experiment was to develop a new method for fast identification between softness and hardness, and for maintaining germinability of seed after measurement in wheat. Results from the comparisons of accuracy and significance between image analysis and conventional methods(NIRS and textrometer) were summarized. Data obatined from image analysis for grain hardness did not show any difference from those of the conventional methods. The protein content analyzed by micro-Kjeldahl method was significantly correlated with the grain hardness measured by image analysis, textrometer, and NIRS. The analysis for wheat grain hardness using image analysis may be used as an alternative method to the conventional methods. This method also takes the seeds after analysis can be utilized as breeding materials in early generations.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.13 no.2
• /
• pp.35-46
• /
• 2011

The purpose of this study was to investigate the effect of mass media on women's clothing image, make-up image, and hair image. The subjects of the study were 306 women who lived in Gyeongnam area. Data were collected during June in 2009. Statistical analysis used in this study were frequency, F-test, t-test, Duncan test, factor analysis, Cronbach's ${\alpha}$, correlation coefficient, and multiple regression. The results of this study were as follows. The mass media according to the demographic characteristic of women showed significant difference. Three factors of clothing image were titled as elegance, youth, and visibility. Three factors of make-up image were titled as modern, romanticism, and mediocrity. Four factors of hair image were titled as attraction, individuality, gentleness, and cuteness. The mass media resulted in correlation with the clothing image, make-up image, and hair image. The mass media had a influence on the clothing image, make-up image, and hair image. The study results are highly expected to be used as useful sources in one's image formation and a marketing plan.