• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.27 no.3
• /
• pp.59-65
• /
• 2004

This paper explores an image segmentation and representation method using Vector Quantization(VQ) on color and texture for content-based image retrieval system. The basic idea is a transformation from the raw pixel data to a small set of image regions which are coherent in color and texture space. These schemes are used for object-based image retrieval. Features for image retrieval are three color features from HSV color model and five texture features from Gray-level co-occurrence matrices. Once the feature extraction scheme is performed in the image, 8-dimensional feature vectors represent each pixel in the image. VQ algorithm is used to cluster each pixel data into groups. A representative feature table based on the dominant groups is obtained and used to retrieve similar images according to object within the image. The proposed method can retrieve similar images even in the case that the objects are translated, scaled, and rotated.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.1
• /
• pp.204-209
• /
• 2013

The image processing has been applied to various fields along with development of visual media. The boundary parts in which brightness of image dramatically changes are important factors in order to analysis characteristics of image because edge contains important information and significant features. A number of researches for detecting these edges have been conducted and conventional edge detection methods using relationship between adjacent pixels are that operation speed is superior, but the edge detection characteristics are insufficient because they use fixed mask without considering gray-level variation. In this paper, the novel algorithm using grey-level variation of image in mask is proposed.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.9
• /
• pp.2558-2562
• /
• 1999

This paper proposes on the methods of noise removal and edge extraction which is done by eliminating the ambiguities of the image using normalization and minimizing the entropy. Pre-existing methods have their own peculiarities and limitations, such as gray level distributions change very slowly or two regions which having similar gray level distribution are touched. This affects on the post processing such as feature extraction, as a result, this leads to false-recognition or no-recognition. Therefore, this paper proposes on the methods which overcome these problems. Finally, the effectiveness of this paper is demonstrated by several experiments.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.307-310
• /
• 2021

In the recent years, studies using Computer-Aided Diagnostics(CAD) have been actively conducted, such as signal and image processing technology using breast ultrasound images, automatic image optimization technology, and automatic detection and classification of breast masses. As computer diagnostic technology is developed, it is expected that early detection of cancer will proceed accurately and quickly, reducing health insurance and test ice for patients, and eliminating anxiety about biopsy. In this paper, a quantitative analysis of tumors was conducted in ultrasound images using a gray level co-occurrence matrix(GLCM) to experiment with the possibility of use for computer assistance diagnosis.

• Current Optics and Photonics
• /
• v.7 no.4
• /
• pp.387-397
• /
• 2023

Tooth surface shape error is an important parameter in gear accuracy evaluation. When tooth surface shape error is measured by laser interferometry, the gear interferogram is highly distorted and the gray level distribution is not uniform. Therefore, it is important for gear interferometry to extract the foreground region from the gear interference fringe image directly and accurately. This paper presents an approach for foreground extraction in gear interference images by leveraging the sinusoidal variation characteristics shown by the interference fringes. A gray level mask with an adaptive threshold is established to capture the relevant features, while a local variance evaluation function is employed to analyze the fluctuation state of the interference image and derive a repair mask. By combining these masks, the foreground region is directly extracted. Comparative evaluations using qualitative and quantitative assessment methods are performed to compare the proposed algorithm with both reference results and traditional approaches. The experimental findings reveal a remarkable degree of matching between the algorithm and the reference results. As a result, this method shows great potential for widespread application in the foreground extraction of gear interference images.

• Proceedings of the KIEE Conference
• /
• 2008.04a
• /
• pp.107-108
• /
• 2008

본 논문에서는 8-bits의 그레이레벨 영상에서 그레이레벨(gray-level) 값들의 발생 빈도(frequency)에 따른 순위 변환(Ranking-Transformation)을 이용한 효율적인 무손실 압축을 제안한다. 제안한 기법은 서로 인접한 픽셀의 그레이레벨의 쌍에 대한 발생 빈도를 토대로 원 영상의 그레이레벨 값을 이에 대응하는 순위 값으로 변환시킨다. 이때 부가정보가 발생하지 않도록 입력영상의 픽셀들에 대하여 한 픽셀씩 순차적으로 지정한 순위로 재구성한다. 실험결과, 부가 정보 없이 입력 영상을 압축하게 되어 엔트로피 부호화기를 통한 디지털 영상들의 효율적인 압축 성능 향상을 기대할 수 있다.

• Journal of ILASS-Korea
• /
• v.1 no.2
• /
• pp.66-73
• /
• 1996

The present study investigates experimentally the characteristics of liquid jet, which is, the spray flow in the normal direction of the air stream under the flow conditions of air velocity $110\sim125m/s$. The present study adopts with the flow visualization technique using a short duration light bulb and the image processing analyse with CCD camera. Two types of injector were used: one is a flat plate type, and the other is backward facing step type, which height are 5, 8, 10mm. Dispersion of liquid jet can be represented by gray level of CCD camera. In the upstream of liquid jet, the backward facing step shows better liquid jet penetration. However, in the downstream. mean droplet size for backward facing step injector is smaller than that for flat plate injector

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.11a
• /
• pp.511-514
• /
• 2003

본 연구는 입력된 영상으로부터 특정한 형태를 이루고 있는 대상 물체를 추출함에 있어, 처리에 소요되는 시간 비용(Time cost)을 줄이는 것을 목적으로 하고 있다. 이를 위하여 특정 관심 지역(Region of Interest)이나 대상 물체(Tareet object)의 경계 검출(Boundary detection)을 하는 과정에 통계학적 수치자료(SSM : Statistical Shape Model)를 사용한 접근법을 이용하였다. 또한, 향후 연구 방향인 의료 영상해석(Medical image analysis)으로의 확장성을 고려, 의료 영상 해석에 많이 사용되어지는 MRI, CT, X-Ray 이미지가 Gray level 영상이라는 것을 감안하여 Gray level 영상을 연구 대상으로 삼았다.

• Journal of the Optical Society of Korea
• /
• v.15 no.3
• /
• pp.244-251
• /
• 2011

We propose a new 2-step phase-shifting digital holographic optical encryption technique and analyze tolerance error for this cipher system. 2-step phase-shifting digital holograms are acquired by moving the PZT mirror with phase step of 0 or ${\pi}$/2 in the reference beam path of the Mach-Zehnder type interferometer. Digital hologram with the encrypted information is Fourier transform hologram and is recorded on CCD camera with 256 gray-level quantized intensities. The decryption performance of binary bit data and image data is analyzed by considering error factors. One of the most important errors is quantization error in detecting the digital hologram intensity on CCD. The more the number of quantization error pixels and the variation of gray-level increase, the more the number of error bits increases for decryption. Computer experiments show the results to be carried out encryption and decryption with the proposed method and the graph to analyze the tolerance of the quantization error in the system.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2006.08a
• /
• pp.1487-1490
• /
• 2006

One of the factors deteriorating PDP image quality is the nonlinearity and nonuniform of output luminance as a function of input gray level. A novel method using modified ADS driving scheme is proposed to decrease this nonlinearity. It optimizes the reset pulse and adjusts the subfields, makes the relation of output luminance and input gray level almost linear. This method can be applied to general commercial PDPs.