• The KIPS Transactions:PartB
• /
• v.17B no.3
• /
• pp.227-232
• /
• 2010

This paper proposes the real time lip reading method in the embedded environment. The embedded environment has the limited sources to use compared to existing PC environment, so it is hard to drive the lip reading system with existing PC environment in the embedded environment in real time. To solve the problem, this paper suggests detection methods of lip region, feature extraction of lips, and awareness methods of phonetic words suitable to the embedded environment. First, it detects the face region by using face color information to find out the accurate lip region and then detects the exact lip region by finding the position of both eyes from the detected face region and using the geometric relations. To detect strong features of lighting variables by the changing surroundings, histogram matching, lip folding, and RASTA filter were applied, and the properties extracted by using the principal component analysis(PCA) were used for recognition. The result of the test has shown the processing speed between 1.15 and 2.35 sec. according to vocalizations in the embedded environment of CPU 806Mhz, RAM 128MB specifications and obtained 77% of recognition as 139 among 180 words were recognized.

• Journal of agriculture & life science
• /
• v.45 no.6
• /
• pp.21-32
• /
• 2011

This research is intended to study literatures relating to western rocking chairs style in early 20th century in order to provide basic data of designs for rockers of today in Korea and investigate characteristics of rocking chair from academic, formative and pragmatic perspectives. During the first half of 20th century, western rocking chairs (1925~1945) embodied actively the simple functionalism concept that furniture design must follow functionality considerations. Therefore, bare wood rocking chairs were without any surface decoration and tubular steel frame rocking chairs often included black leather upholstery in a bold attempt to express exposed structure. And the fact that tubular steel produced such lightweight furniture was crucial importance. Many Modernist designer created curvaceous lines of new pattern changes in their furniture. The structure of Modern rocking chair became all-important, for stylistic as well as functional reasons. Designers equated exposed structure of tubular steel and wooden frame with integrity and rationality and create an equalitarian style of design. Especially, designers in the early 20th century did use various brilliantly colored upholstery and wooden frame with simple forms of modern characteristics.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.12
• /
• pp.11-19
• /
• 2013

This paper proposes an algorithm using vibration signals and texture analysis for mechanical fault diagnosis of an induction motor. We analyze characteristics of contrast and pattern of an image converted from vibration signal and extract three texture features using gray-level co-occurrence model(GLCM). Then, the extracted features are used as inputs of a multi-level support vector machine(MLSVM) which utilizes the radial basis function(RBF) kernel function to classify each fault type. In addition, we evaluate the classification performance with varying the parameter from 0.3 to 1.0 for the RBF kernel function of MLSVM, and the proposed algorithm achieved 100% classification accuracy with the parameter of the RBF from 0.3 to 1.0. Moreover, the proposed algorithm achieved about 98% classification accuracy with 15dB and 20dB noise inserted vibration signals.

• The Journal of Korean Institute of Information Technology
• /
• v.16 no.12
• /
• pp.75-83
• /
• 2018

Recently, autonomous vehicles have been actively studied. Pedestrian detection and recognition technology is important in autonomous vehicles. Pedestrian detection using CNN(Convolutional Neural Netwrok), which is mainly used recently, generally shows good performance, but there is a performance degradation depending on the environment of the image. In this paper, we propose a pedestrian detection system applying long-term memory structure of hippocampal neural network based on CNN network with LGP-FL (Local Gradient Pattern-Feature Layer) added. First, change the input image to a size of $227{\times}227$. Then, the feature is extracted through a total of 5 layers of convolution layer. In the process, LGP-FL adds the LGP feature pattern and stores the high-frequency pattern in the long-term memory. In the detection process, it is possible to detect the pedestrian more accurately by detecting using the LGP feature pattern information robust to brightness and color change. A comparison of the existing methods and the proposed method confirmed the increase of detection rate of about 1~4%.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.5
• /
• pp.975-986
• /
• 2022

Deep learning is attracting great attention, showing excellent performance in image processing, but is vulnerable to adversarial attacks that cause the model to misclassify through perturbation on input data. Adversarial examples generated by adversarial attacks are minimally perturbated where it is difficult to identify, so visual features of the images are not generally changed. Unlikely deep learning models, people are not fooled by adversarial examples, because they classify the images based on such visual features of images. This paper proposes adversarial attack detection method using Symbolic Representation, which is a visual and symbolic features such as color, shape of the image. We detect a adversarial examples by comparing the converted Symbolic Representation from the classification results for the input image and Symbolic Representation extracted from the input images. As a result of measuring performance on adversarial examples by various attack method, detection rates differed depending on attack targets and methods, but was up to 99.02% for specific target attack.

• Journal of IKEEE
• /
• v.28 no.3
• /
• pp.390-396
• /
• 2024

Vision Transformer (ViT) learns relationships between patches, but it may overlook important features such as color, texture, and boundaries, which can result in performance limitations in fields like medical imaging or facial recognition. To address this issue, this study proposes the Pairwise Attention Reinforcement (PAR) model. The PAR model takes both the training image and a reference image as input into the encoder, calculates the similarity between the two images, and matches the attention score maps of images with high similarity, reinforcing the matching areas of the training image. This process emphasizes important features between images and allows even subtle differences to be distinguished. In experiments using clock-drawing test data, the PAR model achieved a Precision of 0.9516, Recall of 0.8883, F1-Score of 0.9166, and an Accuracy of 92.93%. The proposed model showed a 12% performance improvement compared to API-Net, which uses the pairwise attention approach, and demonstrated a 2% performance improvement over the ViT model.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.27 no.12
• /
• pp.1397-1404
• /
• 2003

2002년 월드컵 전야제에서는 한국문화를 소개해 세계인의 환호를 받았는데 그 중에는 칠석동 민속축제인 고싸움놀이가 펼쳐졌다. 칠석동 민속축제는 일반 서민복식의 전통복 형태를 보여주는 복식(服飾)을 실제 착용하고 축제를 행하고 있으므로, 점차 사라져 가는 전통복식을 놀이문화를 통해 직접 확인할 수 있다는 점에서 연구가치를 갖는다. 본 연구의 목적은 국제화 시대에 우리 전통문화에 대한 정체성 확립을 위해 시대적 변화에 따라 변해 가는 민속복식을 무형문화재로 지정되어 있는 칠석동 고싸움놀이를 중심으로 시대적 흐름을 통한 고싸움놀이의 전수과정에서 형성되어 온 민속축제복식의 구성과 특성을 살펴보는데 있다. 연구방법은 광주지역인 광산구 칠석동 마을을 중심으로 자료조사와 현장조사를 병행하였다. 자료조사는 민속에 관련된 전공서적과 무형문화재 조사보고서, 행사팜플렛 등을 참고하였고, 현장조사는 고싸움 축제에 참가하여 복식 전반에 대한사진촬영과 마을축제 참여하는 마을사람들을 중심으로 축제복식에 관한 면담조사를 하였다. 칠석동 고싸움 축제복식은 행사가 진행되는 내용에 따라 크게 4가지로 분류할 수 있는데 본격적인 고싸움이 시작되기 전날 밤에 당산나무에 제를 지내는 당산제 복식, 마을의 평안과 고싸움의 흥을 돋우기 위한 농악복식, 고싸움이 시작되기 전에 아낙네들이 손과 손을 맞잡고 둥글게 돌며 화합을 다짐하는 강강수월래 복식, 한해 풍년을 기원하는 고싸움복식이 있다. 칠석동 고싸움 축제복식의 특성을 요약하면 다음과 같다. 첫째, 구성면에서는 농경제의(農耕祭衣)와 안택축원(安宅祝願的)을 기원하는 민속놀이축제복식으로 일상생활에 착용하는 복식을 이용한 농경 의례복의 다(多)기능성이 강조된 것으로 나타났다. 둘째, 색상은 우리조상의 백의(白衣)의 상징인 일상복인 백색 위에 오방색을 사용하여 화려하고도 강렬한 원색의 색상조화가 특징적으로 나타났다. 셋째, 형태면에서는 양쪽어깨와 허리선의 면 분할이나 비례를 통해 허리부분의 동작에 따른 유동적인 선이 부각되고 있다. 특히, 평면구성의 단조로움은 흔들리는 몸동작에 따른 고름의 율동미와 축제복식의 착장 방법에 따른 한국복식의 형태미를 보여주었다.

• Science of Emotion and Sensibility
• /
• v.15 no.2
• /
• pp.231-238
• /
• 2012

This study aims for building an application system of converting sound into color image based on synesthetic perception. As the major features of input sound, both scale and octave elements extracted from F0(fundamental frequency) were converted into both hue and intensity elements of HSI color model, respectively. In this paper, we used the fixed saturation value as 0.5. On the basis of color model conversion theory, the HSI color model was then converted into the RGB model, so that a color image of the BMP format was finally created. In experiments, the basic system was implemented on both software and hardware(TMS320C6713 DSP) platforms based on the proposed sound-color image conversion method. The results revealed that diverse color images with different hues and intensities were created depending on scales and octaves extracted from the F0 of input sound signals. The outputs on the hardware platform were also identical to those on the software platform.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.3
• /
• pp.36-41
• /
• 2002

Generally, cartoon images are simple and involve a small number of colors and often include large homogeneous regions with same color or gradient. In this paper, effective compression method for complementary quadtree was suggested for cartoon images, by using those properties. And with progressive transmission, this method involves a progressive increase in the image resolution at the receiver from a lower to a higher resolution during the transmission of data. This is an effective way of using a limited transmission channel, because, after estimating the value of the data in the early transmission period, a decision can be made whether or not to proceed with the transmission of the remaining part. Since the proposed method is lossless and involves progressive transmission, it was compared with progressive PNG and progressive GIF, which had same functions.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2017.04a
• /
• pp.141-141
• /
• 2017

장미과(Rosaceae)에 속하는 딸기(Fragaria ananassa Duch.)는 비타민 C가 풍부하고 독특한 향기를 갖는 과채류로서 겨울에서 봄까지의 기간 동안 대부분 생식으로 소비되고 있다. 국내에서 재배되는 품종으로는 설향, 매향, 장희 등이 있으며 품종에 따라 성분과 함량이 다양하지만 일반적으로 유기산이 많아서 신맛과 단맛이 조화로운 특징이 있다. 소비자들이 딸기를 구입할 때 딸기가 포장된 상자에 모양이 일정하고 붉은 색상이 선명한 딸기에 호감을 갖게 된다. 딸기는 품종에 따라 기준이 되는 모양이 다르기 때문에 숙련된 선별사에 의해서 대부분 육안으로 선별되고 있는 실정이다. 하지만 개인적인 선별 능력의 차이와 주관적인 판단으로 인해 규격을 벗어난 딸기가 혼입되어 전체적인 품질 등급을 떨어뜨리는 경우가 종종 발생하기도 한다. 따라서 본 연구에서는 품종별로 기준이 되는 표준 형상과 비정상적인 모양의 기형 딸기를 객관적으로 판별하여 선별할 수 있는 영상 시스템을 구축하기 위해 수행되었으며 표준이 되는 딸기의 3차원 형상을 구축하기 위해 2차원 레이저 변위 센서를 이용하여 딸기의 입체 영상을 구축하고자 하였다. 실험을 위해 사용된 딸기는 시중에서 구입한 설향 품종이었으며 2차원 레이저 변위 센서는 라인 스캔 방식으로 1회 프로파일 스캔에 1,280개의 데이터 포인터를 획득할 수 있으며 분해능은 0.095~0.17 mm이었다. 상부에 부착된 2차원 레이저 변위 센서와 하부에 놓인 딸기의 거리는 100 mm였다. 획득한 딸기의 2차원 영상은 높이 차이를 이용하여 색상 농도로 표현하였으며 이 영상을 다시 3차원 영상으로 구축하였다.