• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.2 s.95
• /
• pp.39-49
• /
• 1999

This paper describes the development of a vision-aided position and orientation recognition system for automatically adjusting electronic tuners which control the waveform by rotating variable resisters. The position and orientation recognition system estimates the center and the angle of the tuner grooves so that the main controller may correct the difference from the ideal position and thereby manipulate the variable resisters automatically. In this paper a robust algorithm is suggested which estimates the center and the angle of the tuner grooves fast and precisly from the source image with lighting variance and video noise. In the algorithm morphological filtering, 8-chain coding, and invariant moments are sequentially used to figure out image segments concerned. The performance of the proposed system was evaluated using a set of real specimens. The results indicate the system works well enough to be used practically in real manufacturing lines. If the system adopts a high speed frame grabber which enables real time image processing, it can also be applied to positioning of robot manipulators as well as automated PCB adjusters.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.27 no.11
• /
• pp.1587-1594
• /
• 2003

Increased energy costs have placed demands for improved combustion efficiency, high equipment availability, low maintenance and safe operation. Furthermore low NO$_x\$ modification, installed due to strict environmental legislation, requires very careful combustion management. The flame monitoring system has been developed specially to satisfy these requirements. We aimed at gaining the relationship between the burner flame image and emissions such as NO$_x$ and unburned carbon in furnace by utilizing the image processing method. For the first step of development, its possibility test was undertaken with bench furnace. The test proceeded to the second step with pilot furnace and the system was observed to be effective for evaluating the combustion conditions. By using this technology, it is possible to perform continuous monitoring of the combustion conditions and instant detection of individual changes for each burner to prevent future loss of ignition. This may contribute to the saving of burner adjusting times for the changes of loads and fuels and to the reduction of the slagging as well.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.27 no.11
• /
• pp.1637-1644
• /
• 2003

Stereoscopic particle image velocimetry is a measurement technique to acquire three dimensional velocity field by two cameras. With a laser sheet illumination, the third velocity component can be deduced from out-of$.$plane velocity components using a stereoscopic matching method. Most industrial fluid flows are three dimensional turbulent flows, so it is necessary to use the stereoscopic PIV measurement method. However the existing stereoscopic PIV system seems hard to use since it is very expensive and complex. In this study we have developed a Miniature Stereo-PIV(MSPIV) system based on the concept of the Miniature PIV system which we have already developed. In this paper, we address the design and some primitive experimental results of the Miniature Stereo-PIV system. The Miniature Stereo-PIV system features relatively modest performances, but is considerably smaller, cheaper and easy to handle. The proposed Miniature Stereo-PIV system uses two one-chip-only CMOS cameras with digital output. Only two other chips are needed, one for a buffer memory and one for an interfacing logic that controls the system. Images are transferred to a personal computer (PC) via its standard parallel port. No extra hardware is required (in particular, no frame grabber board is needed).

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.38 no.7
• /
• pp.693-701
• /
• 2010

In this paper, it is proposed that an attitude and position estimation algorithm based on a stereo camera system for a helmet tracker. Stereo camera system consists of two CCD camera, a helmet, infrared LEDs and a frame grabber. Fifteen infrared LEDs are feature points which are used to determine the attitude and position of the helmet. These features are arranged in triangle pattern with different distance on the helmet. Vision-based the attitude and position algorithm consists of feature segmentation, projective reconstruction, model indexing and attitude estimation. In this paper, the attitude estimation algorithm using UQ (Unit Quaternion) is proposed. The UQ guarantee that the rotation matrix is a unitary matrix. The performance of presented algorithm is verified by simulation and experiment.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.21 no.8
• /
• pp.71-80
• /
• 2007

In this study, an inspection system for valve seal of automotive parts using standalone vision has been developed and presented. The system is comprised of eight CCD cameras, and mechanism that loads the automotive parts to the system for the inspection. An image processing algorithm for detecting two different types of defects of valve seals are developed and the effectiveness of the algorithm is experimentally verified. Inspection process is completed in 0.7 second with acceptable accuracy condition. It is envisaged that this inspection system will have a wide application in the automotive part manufacturing industry in the future.

• 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 Korean Academy of Oral and Maxillofacial Radiology
• /
• v.24 no.1
• /
• pp.137-147
• /
• 1994

A digital imaging system using Machintosh Ⅱ ci computer, high resolution Sony XC-77 CCD camera, Quickcapture Frame Grabber Board was evaluated for quantitative analysis of standardized periapical film with aluminum step wedge. The results were as follows: 1. Correlation between Al thickness and gray level was high-positively associated(r²=0.99, p<0.001). 2. Correlation between measured weight of experimental lesion and estimated relative lesion volume by digital subtracted radiography was also high-positively associated (r²=0.98, p<0.001). 3. As exposure time was increased, mean gray level was decreased(p<0.01) and slope of regression line between Al thickness and gray level was also decreased (p<0.01). And when the exposure time was shorter than 0.2 second, the value of r² was relatively low. On the basis of the above results, it is considered that this digital imaging system using a Macintosh Ⅱ ci computer & a high resolution CCD monochrome camera will be useful in evaluating digitized image from standardized periapical film quantitatively.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.2 no.1
• /
• pp.89-93
• /
• 2002

This paper introduces a vision-based on-line fabric inspection methodology of woven textile fabrics. Current procedure for determination of fabric defects in the textile industry is performed by human in the off-line stage. The advantage of the on-line inspection system is not only defect detection and identification, but also 벼ality improvement by a feedback control loop to adjust set-points. The proposed inspection system consists of hardware and software components. The hardware components consist of CCD array cameras, a frame grabber and appropriate illumination. The software routines capitalize upon vertical and horizontal scanning algorithms characteristic of a particular deflect. The signal to noise ratio (SNR) calculation based on the results of the wavelet transform is performed to measure any deflects. The defect declaration is carried out employing SNR and scanning methods. Test results from different types of defect and different style of fabric demonstrate the effectiveness of the proposed inspection system.

• Proceedings of the KSME Conference
• /
• 2002.08a
• /
• pp.517-520
• /
• 2002

Stereoscopic particle image velocimetry is a measurement technique to acquire of three dimensional velocity field by two cameras. With a laser sheet illumination, the third velocity component can be deduced by out-of-plane velocity components using a stereoscopic matching method. Industrial fluid flows are almost three dimensional turbulent flows, so it is necessary to use the stereoscopic PIV measurement method. However the existing stereoscopic PIV system seems hard to use since it is very expensive and complex. In this study we have developed a Stereoscopic Miniature PIV(MPIV) system based on the concept of the Miniature PIV system which we have already developed. In this paper, we address the design and some first experimental results of the stereoscopic PIV system. The Stereoscopic MPIV system features relatively modest performances, but is considerably smaller, cheaper and easy to handle. The proposed Stereoscopic MPIV system uses two one-chip-only CMOS cameras with digital output. Only two other chips are needed, one for a buffer memory and one for an interfacing logic that controls the system. Images are transferred to a personal computer (PC) via its standard parallel port. No extra hardware is required (in particular, no frame grabber board is needed).

• Journal of Mechanical Science and Technology
• /
• v.15 no.12
• /
• pp.1775-1783
• /
• 2001

For two decades, there has been an active research to enhance the performances of Particle Image Velocimetry (PIV) systems. However, the resulting systems are somewhat very costly, cumbersome and delicate. In this paper, we address the design and some first experimental results of a PIV system belonging to the opposite paradigm. The Miniature PIV or MPIV system feature relatively modest performances, but is considerably smaller (out MPIV could hold in dia. 40 mm$\times$120 mm), cheaper (out MPIV total cost is less than $500) and easy to handle. Potential applications include industrial velocity sensors. The proposed MPIV system uses a one-chip-only CMOS camera with digital output. Only two other chips are needed, one for a buffer memory and one for an interfacing logic that controls the system. Images are transferred to a personal computer (PC or laptop) via its standard parallel port. No extra hardware is required (in particular, no frame grabber board is needed). In our first MPIV prototype presented in this paper, the strobe lighting is generated by a cheap 5 mW laser pointer diode. Experimental results are presented and discussed.