• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.615-618
• /
• 2019

이 모듈은 오픈소스인 Tesseract OCR 및 Open CV 라이브러리와 Raspberry Pi를 사용하여 저렴한 비용으로 구현합니다. 컴팩트한 사이즈로 사람이 직접 들고 움직이면서도 사용이 가능하며 사용자의 니즈에 따라서 한 곳에 위치하여도 사용 가능합니다. Open CV 라이브러리를 사용하여 이미지 이진화, 노이즈 필터링 후에 흑백 이미지를 만들고 윤곽선 검출 알고리즘을 통해서 번호판 영역을 추출하여 Tesseract OCR 엔진을 사용해서 차량 번호판이 추출된 이미지에서 차량 번호를 인식 합니다. 인식된 번호는 Tkinter 와 Python, 데이터베이스를 활용하여 구현된 GUI프로그램을 통해서 유료주차장(선불, 후불) 또는 아파트에서 사용할 수 있는 주차장 관리 서비스를 함께 제공합니다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.76-78
• /
• 2022

기계 소비(machine consumption)를 대상으로 하는 이미지 및 비디오의 압축 목표는 사람이 소비하는 것과 다를 수 있다. 예를 들어, 인간의 소비에는 이미지 및 비디오의 전체 캡처 영역이 필요하지만, 기계는 응용 프로그램에서 요구하는 이미지 또는 비디오의 일부만 사용할 수 있다. 이 논문에서는, 효과적인 기계 소비를 위한 영상 압축 방법 개발을 통한 다중 임무(task) 수행 성능 개선 및 압축률(bpp) 향상을 목적으로, 관심 객체(object of interest) 또는 관심 영역(region of interest)을 식별하기 위한 신경망 기반 영상 분석 작업을 수행하는 전처리 네트워크 구성 방법을 제안한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.99-100
• /
• 2024

다양한 변종들의 존재와 잘 알려지지 않은 취약점을 이용한 공격은 악성코드 수집을 어렵게 하는 요인들이다. 부족한 악성코드 수를 보완하고자 생성 모델을 활용한 이미지 기반의 악성코드 데이터를 증강한 연구들도 존재하였다. 하지만 생성 모델이 실제 악성코드를 생성할 수 있는지에 대한 분석은 진행되지 않았다. 본 연구는 VGG-11 모델을 활용해 실제 악성코드와 생성된 악성코드 이미지의 이진 분류하였다. 실험 결과 VGG-11 모델은 99.9%의 정확도로 두 영상을 다르게 판단한다

• Journal of KIISE
• /
• v.42 no.12
• /
• pp.1474-1479
• /
• 2015

With mobile devices showing marked improvement in performance in the age of the Internet of Things (IoT), there is demand for rapid processing of the extensive amount of multimedia big data. However, because research on image searching is focused mainly on increasing accuracy despite environmental changes, the development of fast processing of high-resolution multimedia data queries is slow and inefficient. Hence, we suggest a new distributed image search algorithm that ensures both high accuracy and rapid response by using feature extraction of distributed images based on MapReduce, and solves the problem of memory scalability based on BIRCH indexing. In addition, we conducted an experiment on the accuracy, processing time, and scalability of this algorithm to confirm its excellent performance.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.12
• /
• pp.1514-1519
• /
• 2019

IVUS is an intra-operative imaging modality that facilitates observing and appraising the vessel wall structure of the human coronary arteries. IVUS is regularly used to locate the atherosclerosis lesions in the coronary arteries. Auto-segmentation of the vessel structure is important to detect the disorder of coronary artery. In this paper, we propose a simple strategy to extract Intima/Adventitia area effectively using fuzzy binarization from intravascular images. The proposed method apply fuzzy binarization to find the adventitia but apply average binarization to locate the intima since they have different homogeneity of pixel intensity comparing with the environment. In this paper, we demonstrate an effective auto-segmentation method for detecting the interior/exterior of the vessel walls by differentiating the fuzzy binarization result and average binarization result from IVUS image. Important statistics such as Intima-Media Thickness (IMT) or volume of a target area can be easily computed from result.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.4
• /
• pp.789-796
• /
• 2013

It is known that the detection of hopping signals without any information about hopping duration and hopping frequency is rather difficult. This paper considers the blind detection of hopping signal's information such as hopping duration and hopping frequency from the sampled wideband signals. In order to find hopping information from the wideband signals, multiple narrow-band filters are required in general, which leads to huge implementation complexity. Instead, this paper employs the polyphase DFT(discrete Fourier transform) filterbank to reduce the implementation complexity. This paper propose hopping signal detection algorithm from the polyphase DFT filterbank output. Specifically, based on the binary image processing, the proposed algorithm is developed to decrease the memory size and H/W complexity. The performance of the proposed algorithm is evaluated through the computer simulation and FPGA (field programmable gate array) implementation.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.44 no.3 s.357
• /
• pp.65-71
• /
• 2007

We propose a pixel-level automatic calibration circuit scheme that initializes a capacitive fingerprint sensor LSI to eliminate the influence of the surface condition and environment, which is degraded by dirt during long-time use, process variation and ambient temperature. The sample chip is fabricated on $0.35{\mu}m$ standard CMOS process. The calibration is executed by optimizing the reference voltage in each pixel to make the sensor signals of all pixels the same. The calibration control circuit is composed of the sensing circuit and charge pumping circuit, and calibrates all pixels in a short time. 16-level gray scale fingerprint images can be captured to increase the accuracy of identification. This confirms that the scheme is effective for capturing consistent clear images during long-time use.

• Science of Emotion and Sensibility
• /
• v.14 no.1
• /
• pp.49-58
• /
• 2011

This study is the one on space image and preference of stylish hotels. And in addition to them, it is the one to verify the minimal style arrangement in the survey results about verbal image and color image of stylish according to gender and age which are the precedent studies. The research result has found that there was no any meaningful difference in gender and age. And the result which extracted the representative languages to investigate correlationship between space image and verbal image of stylish has done that you feel that space image is stylish recognizing individual, sensuous, simple and urban characteristics. Also, space image and preference has done that there are B Hotel of Robby space, C Hotel of food and drink space and A Hotel of room space and color image and preference has done that there are respectively high brightness and low chroma, high brightness and low chroma and low brightness and low chroma. They are the same result with the minimal style arrangement which was recognized as the most stylish things in the precedent studies. It has found that the respondents recognize space image of Stylish hotels as refined, sensuous and individual one linguistically and space of high brightness and low chroma, low brightness and low chroma and low brightness and low chroma as the stylish things. The purpose of the study is to suggest the new design directions for stylish space display and design marketing.

• The Journal of the Korea Contents Association
• /
• v.12 no.5
• /
• pp.154-162
• /
• 2012

We can expect an effective color marketing to build up a positive industrial image as it is easy for consumer to approach due to the ability of colors to affect human consciousness and sub-consciousness more than any other factor. The purpose of this research is to draw attention to the importance of color communication and to find strategies to elevate the brand image by surveying the degree of influence color communication has when forming a brand image. In order to conduct effective research, we executed theoretical and collaborative analysis through research materials and documents. If you take a look at the outcome of this research, brands that brings credibility and likability to its customers are not brands that uses color communication, but brands that utilize marketing strategies that build up credibility for quite some time. Also, preference over colors are distinctive. It turned out to be that the color of a brand logo that one likes has very little to do with one's favorite color. When people choose a brand, they are choosing the brand not because of the color of the brand logo, but its credibility and likability that the brand offers. It proves that the color of the brand logo has nothing to do with the colors that people prefer. The relationship between the color that consumers prefer and the image and emotional color that forms brand image is negligible. However, since research shows that there was a relationship between the color you prefer and the emotional color that forms brand images, it seems to be important to figure out what color customers prefer rather than the color that shows customers' self image. Unlike existing color communication research, through this research, we would like to know how to utilize the color communication strategically in the forming of brand images and take a look at the relationship between customers' preferences and the image of each brand logo's emotional color.

• Journal of the Korean Geotechnical Society
• /
• v.27 no.11
• /
• pp.83-92
• /
• 2011

The random and heterogeneous pore structure is a significant factor that dominates physical and mechanical behaviors of soils such as fluid flow and geomechanical responses driven by loading. The characterization method using non-destructive testing such as micro X-ray CT technique which has a high resolution with micrometer unit allows to observe internal structure of soils. However, the application has been limited to qualitatively observe 2D and 3D CT images and to obtain the void ratio at macro-scale although the CT images contain enormous information of materials of interests. In this study, we constructed the 3D particle and pore structures based on sequentially taken 2D images of glass beads and quantitatively defined complex pore structure with void cell and void channel. This approach was enabled by implementing image processing techniques that include coordinate transformation, binarization, Delaunay Triangulation, and Euclidean Distance Transform. It was confirmed that the suggested algorithm allows to quantitatively evaluate the distribution of void cells and their connectivity of heterogeneous pore structures for glass beads.