• Journal of Drive and Control
• /
• v.20 no.4
• /
• pp.92-99
• /
• 2023

Autonomous vehicles should recognize and respond to the specified speed to drive in compliance with regulations. To recognize the specified speed, the most representative method is to read the numbers of the signs by recognizing the speed signs in the front camera image. This study proposes a method that utilizes YOLO-Labeling-Labeling-EfficientNet. The sign box is first recognized with YOLO, and the numeric digit is extracted according to the pixel value from the recognized box through two labeling stages. After that, the number of each digit is recognized using EfficientNet (CNN) learned with the virtual environment dataset produced directly. In addition, we estimated the depth of information from the height value of the recognized sign through regression analysis. We verified the proposed algorithm using the virtual racing environment and GTSRB, and proved its real-time performance and efficient recognition performance.

• ETRI Journal
• /
• v.40 no.4
• /
• pp.435-445
• /
• 2018

This paper proposes a human-like sign-language learning method that uses a deep-learning technique. Inspired by the fact that humans can learn sign language from just a set of pictures in a book, in the proposed method, the input data are pre-processed into an image. In addition, the network is partially pre-trained to imitate the preliminarily obtained knowledge of humans. The learning process is implemented with a well-known network, that is, a convolutional neural network. Twelve sign actions are learned in 10 situations, and can be recognized with an accuracy of 99% in scenarios with low-cost equipment and limited data. The results show that the system is highly practical, as well as accurate and robust.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.22 no.3
• /
• pp.50-59
• /
• 2014

This paper proposes a method of localization of vehicle especially the horizontal position for the purpose of recognizing the driving lane. Through tracking road signs, the relative position between the vehicle and the sign is calculated and the absolute position is obtained using the known information from the regulation for installation. The proposed method uses Kalman filter for road sign tracking and analyzes the motion using the pinhole camera model. In order to classify the road sign, ORB(Oriented fast and Rotated BRIEF) features from the input image and DB are matched. From the absolute position of the vehicle, the driving lane is recognized. The Experiments are performed on videos from the highway driving and the results shows that the proposed method is able to compensate the common GPS localization errors.

• The Journal of the Korea Contents Association
• /
• v.5 no.2
• /
• pp.157-164
• /
• 2005

The function of image in visual communication is increasing by development of information. It pursuits not only direct and concrete reappearance of information but also infinite possibility of image expression by image. It is also course of future image communication. Therefore, in this paper, if the images which pour out of rapid present society are communication means, it is formed to a point of view that improvement in function of communication will be performed excellently to interaction among consumers by recognizing meaning action process of methods of visual sign about user information processing which perceive Image of visual information.

• Archives of design research
• /
• v.13 no.3
• /
• pp.261-270
• /
• 2000

In general, sign is the way of communication directing human beings with their daily activities particularly in urban circumstances. And sign planning is designing and installing signboards systematically in urban environment. Generally, the range of application in space sign is pretty wide, and it may safely be say that the attractiveness of the city image is considerably decided upon the sign system. The subject of this study investigates the meaning and the role of sign system applying on human environment, and disirable design direction cope with the constant change of city space. The present study doesn't specifically deals with the basic function of signboards only, but with the problems and solution corresponding with sign system as structual element in city environment.

• Journal of Computing Science and Engineering
• /
• v.10 no.3
• /
• pp.95-101
• /
• 2016

In this study, we propose a new system for constructing parallel corpora for sign languages, which are generally under-resourced in comparison to spoken languages. In order to achieve scalability and accessibility regarding data collection and corpus construction, our system utilizes deep learning-based techniques and predicts depth information to perform pose estimation on hand information obtainable from video recordings by a single RGB camera. These estimated poses are then transcribed into expressions in SignWriting. We evaluate the accuracy of hand tracking and hand pose estimation modules of our system quantitatively, using the American Sign Language Image Dataset and the American Sign Language Lexicon Video Dataset. The evaluation results show that our transcription system has a high potential to be successfully employed in constructing a sizable sign language corpus using various types of video resources.

• Journal of Korea Multimedia Society
• /
• v.8 no.6
• /
• pp.768-775
• /
• 2005

For sign languages are main communication means among hearing-impaired people, there are communication difficulties between speaking-oriented people and sign-language-oriented people. Automated sign-language recognition may resolve these communication problems. In sign languages, finger spelling is used to spell names and words that are not listed in the dictionary. There have been research activities for gesture and posture recognition using glove-based devices. However, these devices are often expensive, cumbersome, and inadequate for recognizing elaborate finger spelling. Use of colored patches or gloves also cause uneasiness. In this paper, a vision-based finger spelling recognition system is introduced. In our method, captured hand region images were separated from the background using a skin detection algorithm assuming that there are no skin-colored objects in the background. Then, hand postures were recognized using a two-dimensional grid analysis method. Our recognition system is not sensitive to the size or the rotation of the input posture images. By optimizing the weights of the posture features using a genetic algorithm, our system achieved high accuracy that matches other systems using devices or colored gloves. We applied our posture recognition system for detecting Korean Sign Language, achieving better than $93\%$ accuracy.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.8
• /
• pp.325-330
• /
• 2022

This paper conducts the collection and experiment of datasets for deep learning research on sign language such as sign language recognition, sign language translation, and sign language segmentation for Korean sign language. There exist difficulties for deep learning research of sign language. First, it is difficult to recognize sign languages since they contain multiple modalities including hand movements, hand directions, and facial expressions. Second, it is the absence of training data to conduct deep learning research. Currently, KETI dataset is the only known dataset for Korean sign language for deep learning. Sign language datasets for deep learning research are classified into two categories: Isolated sign language and Continuous sign language. Although several foreign sign language datasets have been collected over time. they are also insufficient for deep learning research of sign language. Therefore, we attempted to collect a large-scale Korean sign language dataset and evaluate it using a baseline model named TSPNet which has the performance of SOTA in the field of sign language translation. The collected dataset consists of a total of 11,402 image and text. Our experimental result with the baseline model using the dataset shows BLEU-4 score 3.63, which would be used as a basic performance of a baseline model for Korean sign language dataset. We hope that our experience of collecting Korean sign language dataset helps facilitate further research directions on Korean sign language.

• ETRI Journal
• /
• v.36 no.1
• /
• pp.12-21
• /
• 2014

In this paper, we propose a new digital blind in-phase/quadrature-phase (I/Q) mismatch compensation technique for image rejection in a direct-conversion receiver (DCR). The proposed image-rejection circuit adopts DC offset cancellation and a sign-sign least mean squares (LMS) algorithm with a unique step size adaptation both for a fast and precise I/Q mismatch estimation. In addition, several performance-optimizing design considerations related to accuracy, speed, and hardware simplicity are discussed. The implementation of the proposed circuit in an FPGA results in an image-rejection ratio (IRR) of 65 dB, which is the best performance with modulated signals, along with an adaptation time of 0.9 seconds, which is a tenfold increase in the compensation speed as compared to previously reported circuits. The proposed technique will be a promising solution in the area of image rejection to increase both the speed and accuracy of future DCRs.

• Journal of Korea Multimedia Society
• /
• v.15 no.3
• /
• pp.312-322
• /
• 2012

The paper presents an approach for recognizing the broken area of the traffic signs. The method is based on the Recognition System for Traffic Signs (RSTS). This paper describes an approach to using the location histogram matching for the broken traffic signs recognition, after the general process of the image detection and image categorization. The recognition proceeds by using the SIFT matching to adjust the acquired image to a standard position, then the histogram bin will be compared preprocessed image with reference image, and finally output the location and percents value of the broken area. And between the processing, some preprocessing like the blurring is added in the paper to improve the performance. And after the reorganization, the program can operate with the GPS for traffic signs maintenance. Experimental results verified that our scheme have a relatively high recognition rate and a good performance in general situation.