• 대한토목학회논문집
• /
• 제28권6A호
• /
• pp.873-880
• /
• 2008

구조물의 열화 또는 손상상태 점검 시 정기적인 외관조사는 매우 중요한 역할을 담당한다. 이때 실시되는 외관조사는 주로 조사자의 스케치나 일반 카메라를 이용한 사진촬영에 의해 이루어지고 있다. 이럴 경우, 조사에 많은 노력과 시간이 소요된다. 따라서 본 연구에서는 보다 효율적이고 효과적인 조사를 위하여, 터널 외관상의 결함을 자동인식 할 수 있는 시스템을 개발하고자 한다. 이 과정에서 결함 손상인식을 위한 화상처리기술과 데이터 관리 및 분석 시스템이 중점적으로 개발 응용되었다. 이를 통해 콘크리트의 균열, 누수, 백화, 박리, 박락, 손상 등의 결함을 인식하여 데이터를 획득하고, 지속적이고 체계적인 데이터 관리시스템을 구축하여, 터널의 안전성 확보, 기능성 유지, 수명연장 등의 효과를 얻고자 한다.

• 한국정보통신학회논문지
• /
• 제13권11호
• /
• pp.2283-2288
• /
• 2009

인간의 시각정보처리는 망막에서 입력된 영상을 시각피질에 전달될 때 많은 특성을 가지고 있다. 그 중에서 확대성질과 방향성에 대한 민감도를 분석하여 영상인식에 미치는 영향을 분석하고자 한다. 확대성질은 중심와의 영역이 시각피질에서 확대영역으로 할당되는 사실을 확대배율이라고 부른다. 방향수직반응의 가중치와 수평 및 대각선반응의 가중치를 여러 가지로 변동하여 영상의 인식률을 비교함으로써 수직반응 정도에 매우 민감함을 보이며 차후 인간시각모델 구성에 적용하고자 한다.

• ETRI Journal
• /
• 제39권1호
• /
• pp.97-107
• /
• 2017

A fast and accurate building-level visual place recognition method built on an image-retrieval scheme using street-view images is proposed. Reference images generated from street-view images usually depict multiple buildings and confusing regions, such as roads, sky, and vehicles, which degrades retrieval accuracy and causes matching ambiguity. The proposed practical database refinement method uses informative reference image and keypoint selection. For database refinement, the method uses a spatial layout of the buildings in the reference image, specifically a building-identification mask image, which is obtained from a prebuilt three-dimensional model of the site. A global-positioning-system-aware retrieval structure is incorporated in it. To evaluate the method, we constructed a dataset over an area of $0.26km^2$. It was comprised of 38,700 reference images and corresponding building-identification mask images. The proposed method removed 25% of the database images using informative reference image selection. It achieved 85.6% recall of the top five candidates in 1.25 s of full processing. The method thus achieved high accuracy at a low computational complexity.

• 제어로봇시스템학회논문지
• /
• 제17권2호
• /
• pp.93-101
• /
• 2011

For mobile robot, recognizing its current location is very important to navigate autonomously. Especially, loop closing detection that robot recognize location where it has visited before is a kernel problem to solve localization. A considerable amount of research has been conducted on loop closing detection and localization based on appearance because vision sensor has an advantage in terms of costs and various approaching methods to solve this problem. In case of scenes that consist of repeated structures like in corridors, perceptual aliasing in which, the two different locations are recognized as the same, occurs frequently. In this paper, we propose an improved method to recognize location in the scenes which have similar structures. We extracted salient regions from images using visual attention model and calculated weights using distinctive features in the salient region. It makes possible to emphasize unique features in the scene to classify similar-looking locations. In the results of corridor recognition experiments, proposed method showed improved recognition performance. It shows 78.2% in the accuracy of single floor corridor recognition and 71.5% for multi floor corridors recognition.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권4호
• /
• pp.403-410
• /
• 2004

바이모달 음성인식기는 잡음 환경하 음성인식 성능을 향상하기 위해 고안되었다. 바이모달 음 성인식기에 있어 영상을 통한 시각 특징 추출은 매우 중요한 역할을 하며 이를 위한 입술 위치 검출은 시각 특징 추출을 위한 중요한 선결 과제이다 본 논문은 색상분포와 SVM을 이용하여 시각 특징 추출을 위한 입술 위치 검출 방법을 제안하였다. 제안된 방법은 얼굴색/입술 색상 분포를 학습하여 이로부터 입술의 초기 위치를 빠르게 찾아내고 SVM을 이용하여 입술의 정확한 위치를 찾음으로써 정확하고 빠르게 입술의 위치를 찾도록 하였으며 실험을 통해 바이모달 인식기에 적용하기에 적합함을 알 수 있었다.

• Journal of information and communication convergence engineering
• /
• 제2권2호
• /
• pp.132-137
• /
• 2004

Most of the current computer vision theories are based on hypotheses that are difficult to apply to the real world, and they simply imitate a coarse form of the human visual system. As a result, they have not been showing satisfying results. In the human visual system, there is a mechanism that processes information due to memory degradation with time and limited storage space. Starting from research on the human visual system, this study analyzes a mechanism that processes input information when information is transferred from the retina to ganglion cells. In this study, a model for the characteristics of ganglion cells in the retina is proposed after considering the structure of the retina and the efficiency of storage space. The MNIST database of handwritten letters is used as data for this research, and ART2 and SOM as recognizers. The results of this study show that the proposed recognition model is not much different from the general recognition model in terms of recognition rate, but the efficiency of storage space can be improved by constructing a mechanism that processes input information.

• 디지털융복합연구
• /
• 제14권8호
• /
• pp.233-243
• /
• 2016

소음환경에서의 음성인식 문제점으로 인해 1990년대 중반부터 음성정보와 영양정보를 결합한 AVSR(Audio Visual Speech Recognition) 시스템이 제안되었고, Lip Reading은 AVSR 시스템에서 시각적 특징으로 사용되었다. 본 연구는 효율적인 AVSR 시스템을 구축하기 위해 입 모양만을 이용한 발화 단어 인식률을 극대화하는데 목적이 있다. 본 연구에서는 입 모양 인식을 위해 실험단어를 발화한 입력 영상으로부터 영상의 전처리 과정을 수행하고 입술 영역을 검출한다. 이후 DNN(Deep Neural Network)의 일종인 CNN(Convolution Neural Network)을 이용하여 발화구간을 검출하고, 동일한 네트워크를 사용하여 입 모양 특징 벡터를 추출하여 HMM(Hidden Markov Mode)으로 인식 실험을 진행하였다. 그 결과 발화구간 검출 결과는 91%의 인식률을 보임으로써 Threshold를 이용한 방법에 비해 높은 성능을 나타냈다. 또한 입모양 인식 실험에서 화자종속 실험은 88.5%, 화자 독립 실험은 80.2%로 이전 연구들에 비해 높은 결과를 보였다.

• Journal of Multimedia Information System
• /
• 제9권1호
• /
• pp.1-10
• /
• 2022

China is a big country in animal fur industry. The total production and consumption of fur are increasing year by year. However, the recognition of fur in the fur production process still mainly relies on the visual identification of skilled workers, and the stability and consistency of products cannot be guaranteed. In response to this problem, this paper proposes a feature fusion-based animal fur recognition network on the basis of typical convolutional neural network structure, relying on rapidly developing deep learning techniques. This network superimposes texture feature - the most prominent feature of fur image - into the channel dimension of input image. The output feature map of the first layer convolution is inverted to obtain the inverted feature map and concat it into the original output feature map, then Leaky ReLU is used for activation, which makes full use of the texture information of fur image and the inverted feature information. Experimental results show that the algorithm improves the recognition accuracy by 9.08% on Fur_Recognition dataset and 6.41% on CIFAR-10 dataset. The algorithm in this paper can change the current situation that fur recognition relies on manual visual method to classify, and can lay foundation for improving the efficiency of fur production technology.

• Journal of Information Processing Systems
• /
• 제20권3호
• /
• pp.328-336
• /
• 2024

Visual communication is widely used and enhanced in modern society, where there is an increasing demand for spirituality. Museum robots are one of many service robots that can replace humans to provide services such as display, interpretation and dialogue. For the improvement of museum guide robots, the paper proposes a human-robot interaction system based on visual communication skills. The system is based on a deep neural mesh structure and utilizes theoretical analysis of computer vision to introduce a Tiny+CBAM mesh structure in the gesture recognition component. This combines basic gestures and gesture states to design and evaluate gesture actions. The test results indicated that the improved Tiny+CBAM mesh structure could enhance the mean average precision value by 13.56% while maintaining a loss of less than 3 frames per second during static basic gesture recognition. After testing the system's dynamic gesture performance, it was found to be over 95% accurate for all items except double click. Additionally, it was 100% accurate for the action displayed on the current page.

• 패션비즈니스
• /
• 제8권1호
• /
• pp.49-60
• /
• 2004

Merchandise should show a visual message that gives consumers' life an additional meaning besides practicality. This should be based on the concept of the merchandise. But in reality, concept is not often properly shown at the store and this is the result more of an inadequate recognition of the merchandise than the store environment. Therefore, this study promotes the recognition of the emotional and cultural point of merchandise, and applies keywords extracted from the practise of marketing to sales strategies for the growth of the fashion business and the VMD expansion.