• ETRI Journal
• /
• 제37권4호
• /
• pp.793-803
• /
• 2015

We propose a novel HMI UI/UX for an in-vehicle infotainment system. Our proposed HMI UI comprises multimodal interfaces that allow a driver to safely and intuitively manipulate an infotainment system while driving. Our analysis of a touchscreen interface-based HMI UI/UX reveals that a driver's use of such an interface while driving can cause the driver to be seriously distracted. Our proposed HMI UI/UX is a novel manipulation mechanism for a vehicle infotainment service. It consists of several interfaces that incorporate a variety of modalities, such as speech recognition, a manipulating device, and hand gesture recognition. In addition, we provide an HMI UI framework designed to be manipulated using a simple method based on four directions and one selection motion. Extensive quantitative and qualitative in-vehicle experiments demonstrate that the proposed HMI UI/UX is an efficient mechanism through which to manipulate an infotainment system while driving.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.547-550
• /
• 2009

The object recognition mechanism of human being is not well understood yet. On research of animal experiment using an ape, however, neurons that respond to simple shape (e.g. circle, triangle, square and so on) were found. And Hypothesis has been set up as human being may recognize object as combination of such simple shapes. That mechanism is called Figure Alphabet Hypothesis, and those simple shapes are called Figure Alphabet. As one way to research object recognition algorithm, we focused attention to this Figure Alphabet Hypothesis. Getting idea from it, we proposed the feature extraction algorithm for object recognition. In this paper, we described recognition of binarized images of multifont alphabet characters by the recognition model which combined three-layered neural network in the feature extraction algorithm. First of all, we calculated the difference between the learning image data set and the template by the feature extraction algorithm. The computed finite difference is a feature quantity of the feature extraction algorithm. We had it input the feature quantity to the neural network model and learn by backpropagation (BP method). We had the recognition model recognize the unknown image data set and found the correct answer rate. To estimate the performance of the contriving recognition model, we had the unknown image data set recognized by a conventional neural network. As a result, the contriving recognition model showed a higher correct answer rate than a conventional neural network model. Therefore the validity of the contriving recognition model could be proved. We'll plan the research a recognition of natural image by the contriving recognition model in the future.

• Journal of Information Processing Systems
• /
• 제9권2호
• /
• pp.333-348
• /
• 2013

Mobile authentication/identification has grown into a priority issue nowadays because of its existing outdated mechanisms, such as PINs or passwords. In this paper, we introduce gait recognition by using a mobile accelerometer as not only effective but also as an implicit identification model. Unlike previous works, the gait recognition only performs well with a particular mobile specification (e.g., a fixed sampling rate). Our work focuses on constructing a unique adaptive mechanism that could be independently deployed with the specification of mobile devices. To do this, the impact of the sampling rate on the preprocessing steps, such as noise elimination, data segmentation, and feature extraction, is examined in depth. Moreover, the degrees of agreement between the gait features that were extracted from two different mobiles, including both the Average Error Rate (AER) and Intra-class Correlation Coefficients (ICC), are assessed to evaluate the possibility of constructing a device-independent mechanism. We achieved the classification accuracy approximately $91.33{\pm}0.67%$ for both devices, which showed that it is feasible and reliable to construct adaptive cross-device gait recognition on a mobile phone.

• 한국멀티미디어학회논문지
• /
• 제24권10호
• /
• pp.1380-1390
• /
• 2021

The video face recognition (FR) is one of the most popular researches in the field of computer vision due to a variety of applications. In particular, research using the attention mechanism is being actively conducted. In video face recognition, attention represents where to focus on by using the input value of the whole or a specific region, or which frame to focus on when there are many frames. In this paper, we propose a novel attention based deep learning method. Main novelties of our method are (1) the use of combining two loss functions, namely weighted Softmax loss function and a Triplet loss function and (2) the feasibility of end-to-end learning which includes the feature embedding network and attention weight computation. The feature embedding network has a positive effect on the attention weight computation by using combined loss function and end-to-end learning. To demonstrate the effectiveness of our proposed method, extensive and comparative experiments have been carried out to evaluate our method on IJB-A dataset with their standard evaluation protocols. Our proposed method represented better or comparable recognition rate compared to other state-of-the-art video FR methods.

• 한국음향학회지
• /
• 제41권5호
• /
• pp.518-524
• /
• 2022

본 논문에서는 합성곱 신경망과 주의집중 메커니즘을 결합하여 뇌파 신호로부터 감정적 스트레스 인식 성능을 향상시키는 방식을 제안한다. 제안하는 방식에서는 뇌파 신호를 5개의 주파수 영역으로 분해하고, 각 주파수 영역에 합성곱 신경망 계층을 사용하여 뇌파 특징의 공간정보를 획득한 후에 게이트 트랜스포머를 이용한 주의집중 메커니즘을 사용하여 각 주파수 대역에서 두드러진 주파수 정보를 학습하고, 주파수 간 대역 매핑을 통해 보완 주파수 정보를 학습하여 최종 주의집중 표현에 반영한다. DEAP 데이터세트와 6명의 피 실험자가 참여한 뇌파 스트레스 인식 실험을 통해, 제안된 방식이 기존 방식과 비교하여 뇌파 기반 스트레스 인식 성능 향상에 효과가 있음을 보여준다.

• 제어로봇시스템학회논문지
• /
• 제14권4호
• /
• pp.369-375
• /
• 2008

The kinematics and control problem of a visual alignment system is investigated, which plays a crucial role in the fabrication process of flat panel displays. The first solution is the inverse kinematics of a 4PPR parallel alignment mechanism. It determines the driving distance of each joint to compensate the misalignment between mask and panel. Second, an efficient vision algorithm for fast alignment mark recognition is suggested, where by extracting essential feature points to represent the geometry of a mark, the geometric template matching enables much faster object recognition comparing with the general template matching. Finally, the overall visual alignment process including the kinematic solution, vision algorithm, and joint control is implemented and experimental results are given.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1990년도 한국자동제어학술회의논문집(국제학술편); KOEX, Seoul; 26-27 Oct. 1990
• /
• pp.929-932
• /
• 1990

This paper considers the problem of patterns recognition using the artificial neural network systems. The artificial neural network systems provide an effective tool for classifying patterns and/or characters by learning them in a certain repeated hashion. The mechanism of the learning process and the structure of neural network systems used are main concerns in the accurate and fast classification of the patterns which are slightly different each other. The neural network system employed in this study has three layers structure which is composed of input, intermidiate, and output layers. Our main concern is to develope an effective learning mechanism how to learn the patterns fastly and accurately. The experimental study performed shows that there exists an effective learning method to get higher recognition ratio in classifying the several different patterns by artificial neural network system constructed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권11호
• /
• pp.5580-5593
• /
• 2019

A malicious Uniform Resource Locator (URL) recognition and detection method based on the combination of Attention mechanism with Convolutional Neural Network and Long Short-Term Memory Network (Attention-Based CNN-LSTM), is proposed. Firstly, the WHOIS check method is used to extract and filter features, including the URL texture information, the URL string statistical information of attributes and the WHOIS information, and the features are subsequently encoded and pre-processed followed by inputting them to the constructed Convolutional Neural Network (CNN) convolution layer to extract local features. Secondly, in accordance with the weights from the Attention mechanism, the generated local features are input into the Long-Short Term Memory (LSTM) model, and subsequently pooled to calculate the global features of the URLs. Finally, the URLs are detected and classified by the SoftMax function using global features. The results demonstrate that compared with the existing methods, the Attention-based CNN-LSTM mechanism has higher accuracy for malicious URL detection.

• International Journal of Contents
• /
• 제15권4호
• /
• pp.8-15
• /
• 2019

This paper presents a solution of the 'Quick, Draw! Doodle Recognition Challenge' hosted by Google. Doodles are drawings comprised of concrete representational meaning or abstract lines creatively expressed by individuals. In this challenge, a doodle is presented as a sequence of sketches. From the view of at the sketch level, to learn the pattern of strokes representing a doodle, we propose a sequential model stacked with multiple convolution layers and Long Short-Term Memory (LSTM) cells following the attention mechanism [15]. From the view at the image level, we use multiple models pre-trained on ImageNet to recognize the doodle. Finally, an ensemble and a post-processing method using the minimum cost flow algorithm are introduced to combine multiple models in achieving better results. In this challenge, our solutions garnered 11th place among 1,316 teams. Our performance was 0.95037 MAP@3, only 0.4% lower than the winner. It demonstrates that our method is very competitive. The source code for this competition is published at: https://github.com/ngxbac/Kaggle-QuickDraw.

• 한국산학기술학회논문지
• /
• 제7권6호
• /
• pp.1160-1166
• /
• 2006

혼잡한 현대의 교통 상황에서 교통질서를 유지하기 위해 차량에 대한 정보를 아는 것은 매우 중요한 일이다. 본 논문은 차량의 정보를 아는데 있어서 가장 중요한 차량 번호판을 인식하는 새로운 기법을 소개한다. 제안하는 기법은 물체를 분류하는데 있어서 다른 방법보다 우수하다고 알려진 SVM을 이용한다. 번호판 영역을 찾는데는 이중분류 SVM을 이용하고 번호판 문자 인식에서는 다중 분류 SVM을 이용한다. 여러 단계의 영상처리 과정과 인식 과정을 거쳐서 실시간에 처리할 수 있는 시스템으로 여러 종류의 차량 번호판에 대한 인식도 가능하게 한다. 제안한 기법을 이용한 실제적 환경에서의 영상과 인식에 대한 실험결과를 통하여 성능을 입증하였다.