• Journal of Korea Multimedia Society
• /
• v.25 no.11
• /
• pp.1582-1590
• /
• 2022

Due to the situation of the widespread of the coronavirus, which causes the problem of lack of face image data occluded by masks at recent time, in order to solve the related problems, this paper proposes a method to generate face images with masks using a combination of generative adversarial networks and spatial transformation networks based on CNN model. The system we proposed in this paper is based on the GAN, combined with multi-scale convolution kernels to extract features at different details of the human face images, and used Wasserstein divergence as the measure of the distance between real samples and synthetic samples in order to optimize Generator performance. Experiments show that the proposed method can effectively put masks on face images with high efficiency and fast reaction time and the synthesized human face images are pretty natural and real.

• Journal of Korea Multimedia Society
• /
• v.24 no.5
• /
• pp.701-708
• /
• 2021

As one of the most widely used technology in the world right now, Face recognition has already received widespread attention by all the researcher and institutes. It has been used in many fields such as safety protection, surveillance system, crime control and even in our ordinary life such as home security and so on. This technology with today's technology has advantages such as high connectivity and real time transformation. But we still need to improve its recognition rate, reaction time and also reduce impact of different environmental status to the whole system. So in this paper we proposed a face recognition system model with improved CNN which combining the characteristics of flat network and residual network, integrated learning, simplify network structure and enhance portability and also improve the recognition accuracy. We also used AR and ORL database to do the experiment and result shows higher recognition rate, efficiency and robustness for different image conditions.

• Journal of Multimedia Information System
• /
• v.8 no.1
• /
• pp.45-56
• /
• 2021

This document traces the new technologies development based on a deep classical Hill method improvement. Based on the chaos, this improvement begins with the 256 element body construction, which is to replace the classic ring used by all encryption systems. In order to facilitate the application of algebraic operators on the pixels, two substitution tables will be created, the first represents the discrete logarithm, while the second represents the discrete exponential. At the same time, a large invertible matrix whose structure will be explained in detail will be the subject of the advanced classical Hill technique improvement. To eliminate any linearity, this matrix will be accompanied by dynamic vectors to install an affine transformation. The simulation of a large number of images of different sizes and formats checked by our algorithm ensures the robustness of our method.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.308-314
• /
• 2022

As a result of the global effect of infectious diseases like COVID-19, remote patient monitoring has become a vital need. Surgical ICU monitors are attached around the clock for patients in critical care. Most ICU monitor systems, on the other hand, lack an output port for transferring data to an auxiliary device for post-processing. Similarly, strapping a slew of wearables to a patient for remote monitoring creates a great deal of discomfort and limits the patient's mobility. Hence, an unique remote monitoring technique for the ICU monitor's physiologically vital readings has been presented, recognizing this need as a research gap. This mechanism has been put to the test in a variety of modes, yielding an overall accuracy of close to 90%.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.171-172
• /
• 2009

질감 분류 기술은 패턴인식과 컴퓨터 비전 분야에서 널리 사용되는 기술로서, 최근 들어서는 감시 카메라 시스템에서의 정확한 객체 인식을 위한 회전 변화에 강인한 질감 분류 연구가 진행되고 있다. 본 논문에서는 순환 가보 웨이블렛 필터를 이용한 회전 변환에 강인한 질감 분류 방법을 제안한다. 제안하는 방법은 순환 가보 웨이블렛 필터링된 영상에서 전역 및 지역 특징 벡터를 계산하고 특징 벡터의 차이를 이용한 유사도 측정 판별식으로 질감 분류를 수행한다. Brodatz 질감 앨범을 이용한 실험에서 기존의 방법들보다 2~6% 향상된 질감 분류 비율을 확인할 수 있었다. 제안하는 방법은 질감 기반 객체 인식에 관련된 응용 분야에서 유용하게 사용될 수 있다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.526-528
• /
• 2022

In this study, through the capstone design project, an IoT based piano training system was developed after identifying problems in piano learning. The piano training system recognizes sheet music through image processing technology and checks whether the correct keyboard is struck through FFT transformation during piano practicing. By providing a visual effect and score display function using a rhythm game, it was possible to arouse interest in boring piano practice and increase the effect of piano learning.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.293-294
• /
• 2023

이 연구는 사람의 외적인 요소와 마이어스-브릭스가 제안한 16 가지 성격유형을 결부한 연구이다. 기존의 성격유형에 대한 기준을 기반으로 하여, 일반적인 MBTI 판독기와는 다르게 StyleCLIP 을 활용해서 추상적인 단어로 이미지를 변환하고 전이학습 AI 를 이용하여 비교 테스트를 진행한다. 최종적으로 이 연구를 통해 외모와 성격은 연관이 있다는 가설을 증명한다.

• The KIPS Transactions:PartB
• /
• v.18B no.2
• /
• pp.51-56
• /
• 2011

Algorithms for intrinsic images reduce color differences in RGB images caused by the temperature of black-body radiators. Based on the reference light and detecting single invariant direction, these algorithms are weak in real images which can have multiple invariant directions when the scene illuminant is a colored illuminant. To solve these problems, this paper proposes a method of acquiring an intrinsic image by omnidirectional projection of an ROI and a translation of white patch in the ${\chi}$-chromaticity space. Because it is not easy to analyze an image in the three-dimensional RGB space, the ${\chi}$-chromaticity is also employed without the brightness factor in this paper. After the effect of the colored illuminant is decreased by a translation of white patch, an invariant direction is detected by omnidirectional projection of an ROI in this chromaticity space. In case the RGB image has multiple invariant directions, only one ROI is selected with the bin, which has the highest frequency in 3D histogram. And then the two operations, projection and inverse transformation, make intrinsic image acquired. In the experiments, test images were four datasets presented by Ebner and evaluation methods was the follows: standard deviation of the invariant direction, the constancy measure, the color space measure and the color constancy measure. The experimental results showed that the proposed method had lower standard deviation than the entropy, that its performance was two times higher than the compared algorithm.

• The Journal of the Korea Contents Association
• /
• v.13 no.12
• /
• pp.38-47
• /
• 2013

An image coding based on MRC model, a kind of multi-layer image model, first segments a screen image into foreground, mask, and background layers, and then compresses each layer using a codec that is suitable to the layer. The mask layer defines the position of foreground regions such as textual and graphical contents. The colour signal of the foreground (background) region is saved in the foreground (background) layer. The mask layer which contains the segmentation result of foreground and background regions is of importance since its accuracy directly affects the overall coding performance of the codec. This paper proposes a new layer segmentation algorithm for the MRC based image coding. The proposed method extracts text pixels from the background using morphological top hat filtering. The application of white or black top hat transformation to local blocks is controlled by the information of relative brightness of text compared to the background. In the proposed method, the boundary information of text that is extracted from the edge map of the block is used for the robust decision on the relative brightness of text. Simulation results show that the proposed method is superior to the conventional methods.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2007.05a
• /
• pp.836-840
• /
• 2007

Large-Scale Particle Image Velocimetry (LSPIV)는 Particle Image Velocimetry (PIV)를 자연하천이나 실험실에서 넓은 영역($4m^2{\sim}45,000m^2$)에 적용할 수 있도록 확장시킨 것으로 지난 10여년 이상 세계적으로 널리 이에 대한 연구가 진행되고 있다. PIV는 seeding, illumination, recording 그리고 image processing으로 구성된다. LSPIV(Large Scale PIV)는 PIV의 기본원리를 근거로 하여 기존의 PIV에 비하여 실험실 내에서의 수리모형실험이나 일반 하천에서의 유속측정과 같은 큰 규모의 흐름해석을 할 수 있도록 seeding, illumination에 대한 조정이 필요하고, 촬영된 image에 대한 왜곡을 없애는 작업이 필요하다. LSPIV는 PIV의 네가지 단계를 포함하여 seeding, illumination, recording, image transformation, image processing 및 post-processing의 여섯 단계로 구성되어진다 (Li, 2002). LSPIV를 일반 하천에 적용시, 자연발생적인 tracers - 난류로 인한 표면 교란, 부유물, 수공구조물로 인해서 발생하는 자연 발생되는 거품 - 가 풍부해서 seeding이 불필요한 경우를 제외하고는 정확한 유속장의 해석을 위하여 인공적인 seeding을 필요로 한다. 일반적으로 Seeding 재료로 많이 이용되는 것은 wood mulch, Ecofoam, grain-straw 등이다. 하천에서 자연발생적 혹은 인위적 seeding을 하였을 때 이들 tracers의 물리적인 속성으로 바람에 쉽게 영향을 받고 이로 인하여 실제의 물표면유속을 대표하지 못하는 경우가 있다. 이에 실험실의 개수로에서 여러 가지 이용 가능한 tracers에 대하여 바람에 의한 오차 발생의 정도를 조사하였다. 실험에 사용된 seeding 재료로는 black polypropylene, Ecofoam, white polystyrene의 세가지를 이용하였다. black polypropylene (SG=0.92)과 white polystyrene (SG=0.0125)은 폭 1 m 이내의 개수로 실험 장치에서 유속장의 해석에 많이 이용되고 Ecofoam (SG=0.0065)은 수리 모형실험에서 많이 이용된다. seeding 물질에 따른 바람의 영향을 분석하기 위해서 폭 60cm의 개수로에서 seeding 물질을 변경하면서 펌프의 조작에 의해 3가지 단면평균유속을 발생시키고, 각 평균유속조건에 대해 4가지의 바람세기 - 바람이 없을 때와 팬의 바람세기를 1단, 2단, 3단으로 조정 - 를 발생시켰으며, 개수로위에서 촬영한 이미지의 상류측기준점으로부터 0.3556m 하류 지점을 횡단하는 단면의 표면유속을 측정하여 비교하였고, 그 단면의 중앙에서 물표면 바로 위 지점의 풍속을 측정하였다. 각 Seeding 물질에 대해 팬을 켜지 않았을 때, 즉 바람의 영향이 없을 때 측정한 표면유속을 바람의 세기가 변한 경우의 기준 표면유속으로 이용하였다. 본 연구의 결과 비중이 0.01 내외인 Ecofoam과 white polystyrene에 비해 비중이 0.92인 black polypropylene은 대부분이 물속에 잠겨 있어 흐름과 거의 일치하여 움직임을 알 수 있었다. 또한 흐름의 평균유속이 0.165 m/s의 저유속에서 바람이 tracers에 미치는 영향이 평균유속 0.558m/s인 경우보다 커서, 바람의 세기의 증가에 따라 표면유속 측정값이 급속히 감소되었다. 흐름의 평균유속이 큰 경우에는 바람이 tracer에 마치는 영향이 현격히 줄어듬을 보이고 있다. 결론적으로 유속이 증가함에 따라 바람의 영향은 감소하나, 바람의 영향을 최소화시키기 위해서는 가급적 비중이 큰 물질(0.5