• Journal of the Korean Society for Precision Engineering
• /
• v.20 no.8
• /
• pp.70-75
• /
• 2003

It is very important to inspect the color of printed texture in the textile process. The standard colorimetric system used for the recognition of the color in the textile industry. It uses XYZ color system defined by CIE (Commission Internationale de 1Eclairage), but is too expensive. Therefore, in this paper, we propose a color inspection system of the printed texture using a color scanner. Because the scanner uses RGB value for color, it is necessary the mapping from RGB to XYZ. However, the mapping is not simple, and the scanner has even positional deviation because of the geometric characteristics. To transform from RGB to XYZ, we used a NN (neural network) model and also compensated the positional deviation. In real experiments, we could get fairly exact XYZ value from the proposed color inspection system in spite of using a color scanner with large measuring area.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.383-386
• /
• 2002

It is very important to inspect color of printed texture in the textile process. To distinguish the color of the printed texture, RGB color values obtained from a scanner must be transformed to the standard colorimetric system used in the textile industry. It is XYZ color system that is defined by CIE(Commission Internationale do 1Eclairage). The mapping from RGB to XYZ color values is not simple and the scanner has even a positional deviation of RGB colors. In this paper an automatic color inspection method using a general scanning machine is presented. We used a U(neural network) model to map RGB to XYZ and compensate the positional error. In the real experiments, this inspection system shows to get very exact XYZ values from the traditional scanner regardless of the measuring position.

• Journal of Biosystems Engineering
• /
• v.17 no.2
• /
• pp.123-131
• /
• 1992

This study was carried out to analyze the characteristics of the color computer vision to discriminate apple surface color for grading apples by their color. It was intended to develop the techniques to be able to discriminate apple color as precisely as human inspection does. For the purpose, discrimination of apple color by human inspection was checked and justified ; various illumination methods for various frames of the color computer vision(R, G, B, H, S and I frames) were tested ; and several methods to analyze image informations of the color computer vision were tried to evaluate their ability to discriminate apple color close to the human inspection.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.4B
• /
• pp.630-636
• /
• 2010

Ocular inspection in oriental medicine, which identifies sickness by patient's skin color, is usually applied by doctor's subjective judgment. In order to reduce the subjectiveness of diagnosis, we propose a method of objective and quantitative analysis for ocular inspection. The most issued features for ocular inspection are how to identify the color of patients' face in various situations, and how to link the relation between color and sickness. For resolving these two issues, the color system of CIE Lab is adopted for analyzing and classifying the color characteristics. The classification of color features is verified by experiments on groups of patients and non-patients. The results of experiments showed that the proposed method can provide an objective means for ocular inspection using patient's skin color.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.5
• /
• pp.71-75
• /
• 2004

An efficient color compensation method is proposed to reduce the color difference between the camera based inspection system and the colorimeter based inspection system in a plasma display panel production line. The color compensation matrix can be constructed by using the relationship between RGB to XYZ conversion matrices, which are obtained by the RGB primaries and reference white chromaticity coordinates. Experimental results show that the non-contact color inspection system using the proposed color compensation method satisfactorily compensates the chromaticity coordinates acquired by the area color CCD camera to be matched to those measured by the colorimeter for various test color.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.10
• /
• pp.112-118
• /
• 2021

In this study, an inspection method using a color image is proposed to conduct a real-time inspection of covalent organic framework (COF) films to detect defects, if any. The COF film consists of an upper pattern SR and a lower PI. The proposed system detects the defects of more than 20 ㎛ on the SR surface owing to the characteristics of the pattern, whereas on the PI surface, it detects defects of more than 4 ㎛ by utilizing a micro-optical system. In the existing system, it is difficult for the operator to conduct a full inspection through a high-performance microscope. The proposed inspection algorithm performs the inspection by separating each color component using the color contrast of the pattern on the SR side, and on the PI surface it inspects the bonding state of the mounted chip. As a result, it is possible to confirm the exact location of the defects through the SR and PI surface inspections in the implemented inspection.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2005.07a
• /
• pp.85-88
• /
• 2005

A low-cost and high-speed PDP color inspection system can be constructed by using a CCD camera against a colorimeter. Though the inspection can be done using RGB signals obtained by a camera, it has some difficulty to introduce human color sensitivity. Thus, it is quite desirable to convert the RGB values into the XYZ values that can be compared to the values of a colorimeter. Accordingly, the current study proposes a color conversion method that can analytically calculate the RGB-to-XYZ conversion matrix by utilizing the RGB primaries and the reference white. Experiments on Macbeth colorchecker colors showed that the average color difference between the converted XYZ values of the proposed method and the measured XYZ values of a colorimeter is much below the threshold of distinguishing two adjacent color patches.

• IE interfaces
• /
• v.9 no.1
• /
• pp.63-71
• /
• 1996

A wire harness is an assembly cables and/or wires to transmit signals between electronic assemblies in automobiles and electronic appliances. Inspection of such a wire harness is to check the sequence of assembled cabled each of which is identified by its own color. This paper presents an automated visual inspection system for wire harnesses incorporating back-propagation neural network as a color identification device. The tests performed by using real test specimens show that the inspection system works well enough.

• Journal of Biosystems Engineering
• /
• v.35 no.2
• /
• pp.138-145
• /
• 2010

An on-line algorithm that discriminates brown rice kernels on their echelon feeder using color image processing is presented for quality inspection. A rapid color image segmentation algorithm based on Bayesian clustering method was developed by means of the look-up table which was made from the significant clusters selected by experts. A robust estimation method was presented to improve the stability of color clusters. Discriminant analysis of color distributions was employed to distinguish nine types of brown rice kernels. Discrimination accuracies of the on-line discrimination algorithm were ranged from 72% to 85% for the sound, cracked, green-transparent and green-opaque, greater than 93% for colored, red, and unhulled, about 92% for white-opaque and 67% for chalky, respectively.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1763-1766
• /
• 2003

This paper proposes a non-contact color inspection system for plasma display panel (PDP). The red, green, and blue test pattern images are acquired by using the area color CCD camera at the various distance from the PDP. The RGB values are obtained from the region of interest (ROI) which are extracted by applying the image processing to the test pattern image. Finally, the CIE xy and u'v' chromaticity coordinates of the test pattern images according to the distance are acquired from the RGB color coordinates.