• The Journal of Korea Robotics Society
• /
• v.15 no.1
• /
• pp.1-7
• /
• 2020

In this paper, we introduce the methodology that utilizes deep learning-based front-end to enhance underwater feature matching. Both optical camera and sonar are widely applicable sensors in underwater research, however, each sensor has its own weaknesses, such as light condition and turbidity for the optic camera, and noise for sonar. To overcome the problems, we proposed the opti-acoustic transformation method. Since feature detection in sonar image is challenging, we converted the sonar image to an optic style image. Maintaining the main contents in the sonar image, CNN-based style transfer method changed the style of the image that facilitates feature detection. Finally, we verified our result using cosine similarity comparison and feature matching against the original optic image.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.96.6-96
• /
• 2002

In this study an image processing system is designed and developed, which can detect and assort some defects on the surface of an object moving with high speed. For real time surface detection of high speed moving object, the fast processing should be managed and the image information including some surface features should be captured. It is difficult to acquire the noise free image due to various light sources and high speed moving materials under the environment of the general industrial site. In general, because pre-processing methods are employed for getting a noise free feature, the image processing speed has some limitation and the expensive image processing devices are required. This...

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.16 no.5
• /
• pp.122-128
• /
• 2007

The electric part of thermal SEM(Scanning Electron Microscopy) consists of high voltage generation, lens control, and image processing. Several methodologies for enhancing SEM image are addressed and those results are verified through analyses and experiments. The controller employes a DSP(Digital Signal Processing), making the system more flexible and convenient than the classical analogue based controller. In some parts based the analog circuit, there are inevitable sources of noise and image distortion. The experimental investigation is provided along with analytical proof to enhance the SEM image.

• Proceedings of the KSRS Conference
• /
• 2008.10a
• /
• pp.126-129
• /
• 2008

In this paper, we proposed a method extracting an object from background of the satellite image. The image segmentation techniques have been widely studied for the technology to segment image and to synthesis segment object with other images. Proposed algorithm is to perform the edge detection of a selected object using genetic algorithm. We segment region of object based on detection edge using watershed algorithm. We separated background and object in indefinite region using gradual region merge from segment object. And, we make GUI for the application of the proposed algorithm to various tests. To demonstrate the effectiveness of the proposed method, several analysis on the satellite images are performed.

• Fibers and Polymers
• /
• v.6 no.2
• /
• pp.162-168
• /
• 2005

A methodology for the objective evaluation of water repellency is studied using image analysis of the sprayed pattern on woven fabrics according to a standard spray test (AATCC Test Method 22-2001). The wet area ratio obtained from the spray standard test ranking is found to be exponentially related with its water repellency rating. Mean filtering is used to remove the effect of weave texture and the transmitted light through interyarn spaces. The ring frame of the instrument and wet region are recognized using Otsu thresholding technique. And Hough transform and outline operation are used to obtain the size and position of the ring frame. The objective assessment of the water repellency using image processing can reduce unnecessary confusion in the subjective determination of the water repellency.

• Korean Journal of Optics and Photonics
• /
• v.16 no.3
• /
• pp.225-234
• /
• 2005

In the integral imaging system for 3D display, the elemental image size is closely related to the several variables, such as the size of elemental lens, the distance between elemental lens and elemental image, etc., on the pick up system. We have analyzed the geometric relation between the variables. In addition, we have investigated the integrated image variation for the individual and whole conversion of the size of the elemental images, different from in pick up process, and presented experimental results.

• Journal of KIISE:Computer Systems and Theory
• /
• v.28 no.12
• /
• pp.653-659
• /
• 2001

In this paper, we propose an efficient algorithm for constructing cylindrical panoramic image. At first, we describe a fast image alignment algorithm, which matches image strips located on equal distance for image centers. And then, we explain how to estimate accurately the effective focal length of camera by a bisection method. Although there is a limitation in that the image should be taken by a camera with pure panning motion, the proposed simple and fast algorithm is applicable to practical application.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06b
• /
• pp.193-195
• /
• 2006

As multimedia information increases sharply, In image retrieval field the method that can analyze image data quickly and exactly is required. In the case of image data, because each data includes a lot of informations, between accuracy and speed of retrieval become trade-off. To solve these problem, feature vector extracting process that use Genetic Algorithm for implementing prompt and correct image clustering system in case of retrieval of mass image data is proposed. After extracting color and texture features, the representative feature vector among these features is extracted by using Genetic Algorithm.

• Journal of the Korean Society for Precision Engineering
• /
• v.25 no.5
• /
• pp.89-95
• /
• 2008

The Acousto-Optic Tunable Filter (AOTF) is a high-speed full-field monochromator which generates two spectrally filtered light beams with ordinary and extraordinary polarization state. Thus, AOTF is widely used to build full-field spectral imaging system or spectral domain interferometer. However, AOTF has a big problem that the angle of diffracted light changes according to the scanning of wavelength, which makes image shift on CCD plane In this paper, we propose an analytic design of prism system to compensate the image shift. The detailed analysis of light paths in a prism and basic experimental results are presented to verify our proposed compensation method. The experimental results agree with simulation results based on suggested prism model and image shift is minimized at optimal condition. Also, it can be extended to compensate the image shift for ordinary and extraordinary polarized light simultaneously.

• Journal of Institute of Convergence Technology
• /
• v.3 no.2
• /
• pp.45-49
• /
• 2013

Instant custom embroidered souvenir manufacturing system was studied. Recently customers want to get individually specialized souvenir. We present a modular manufacturing system and implementation of image processing, conversion of punching data. The manufacturing system consist of main module, photographing module and U/I module. We can change the system easily through modularization. Image Processing was necessary for making punching data. We developed sketch typed image processing and image processing which used brightness. Brightness type is suitable for instant embroidered souvenir. This study showed that fusion of embroidery technology and image processing technology can make a new business successfully.