• Journal of Broadcast Engineering
• /
• v.20 no.6
• /
• pp.938-949
• /
• 2015

In this paper, we propose a robust speed-limit sign recognition system which is durable to any sign changes caused by exterior damage or color contrast due to light direction. For recognition of speed-limit sign, we apply CNN which is showing an outstanding performance in pattern recognition field. However, original CNN uses multiple hidden layers to extract features and uses fully-connected method with MLP(Multi-layer perceptron) on the result. Therefore, the major demerit of conventional CNN is to require a long time for training and testing. In this paper, we apply randomly-connected classifier instead of fully-connected classifier by combining random forest with output of 2 layers of CNN. We prove that the recognition results of CNN with random forest show best performance than recognition results of CNN with SVM (Support Vector Machine) or MLP classifier when we use eight speed-limit signs of GTSRB (German Traffic Sign Recognition Benchmark).

• The Korean Journal of Community Living Science
• /
• v.24 no.2
• /
• pp.251-258
• /
• 2013

Korean oil and honey Yukwa has been paid attention as formal cake for traditional national seasons' holiday and religious service. Quality of Yukwa, however, has been maintained arbitrarily by each Yukwa manufacturer. Since even same Yukwa had severe differences in size, weight, and pattern, it has given the negative effect to the consumer. Yukwa industries need to setup the quantitative quality specifications instead of qualitative ones to maintain the uniformity of Yukwa quality. Efficient and economical inspection and process control system should be developed. In developing quality standards of Yukwa, features which can measure quality quantitatively in real time should be properly chosen. Existing quality features such as acidity, oxidization, hardness, viscosity, and texture were measured by the chemical or physical base destructive methods. Many research and developments have been performed in investigating and analyzing chemical transition states of those quality features as environment or storage condition changes. Most methods, however, require either off-line or complex treatment or time consuming process of analysis in evaluating quality features. Consumer, however, selects products mostly based on the external features such as shape, size, and color. Therefore, critical visual quality features should be chosen and the efficient real time measurement system must be developed. In this paper, computer image acquisition and processing system were developed and software modules were developed to extract the quantitative data of those features in real-time. Computer image processing system will promote in maintaining uniform quality of Yukwa and establishing quality standards of Yukwa.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.12
• /
• pp.6069-6091
• /
• 2017

Augmented Reality (AR) overlays virtual information on real world data, such as displaying useful information on videos/images of a scene. This paper presents an Enhanced AR (EAR) system that displays useful statistical players' information on captured images of a sports game. We focus on the situation where the input image is degraded by strong sunlight. Proposed EAR system consists of an image enhancement technique to improve the accuracy of subsequent player and face detection. The image enhancement is followed by player and face detection, face recognition, and players' statistics display. First, an algorithm based on multi-scale retinex is proposed for image enhancement. Then, to detect players' and faces', we use adaptive boosting and Haar features for feature extraction and classification. The player face recognition algorithm uses boosted linear discriminant analysis to select features and nearest neighbor classifier for classification. The system can be adjusted to work in different types of sports where the input is an image and the desired output is display of information nearby the recognized players. Simulations are carried out on 2096 different images that contain players in diverse conditions. Proposed EAR system demonstrates the great potential of computer vision based approaches to develop AR applications.

• Journal of Korea Society of Industrial Information Systems
• /
• v.13 no.4
• /
• pp.145-154
• /
• 2008

In this paper, we propose the pet robot control system using hand gesture recognition in image sequences acquired from a camera affixed to the pet robot. The proposed system consists of 4 steps; hand detection, feature extraction, gesture recognition and robot control. The hand region is first detected from the input images using the skin color model in HSI color space and connected component analysis. Next, the hand shape and motion features from the image sequences are extracted. Then we consider the hand shape for classification of meaning gestures. Thereafter the hand gesture is recognized by using HMMs (hidden markov models) which have the input as the quantized symbol sequence by the hand motion. Finally the pet robot is controlled by a order corresponding to the recognized hand gesture. We defined four commands of sit down, stand up, lie flat and shake hands for control of pet robot. And we show that user is able to control of pet robot through proposed system in the experiment.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.4
• /
• pp.299-307
• /
• 2003

There have been many studies on speaker normalization which aims to minimize the effects of speaker's vocal tract length on the recognition performance of the speaker independent speech recognition system. In this paper, we propose a simple vector quantizer based linear warping speaker normalization method based on the observation that the vector quantizer can be successfully used for speaker verification. For this purpose, we firstly generate an optimal codebook which will be used as the basis of the speaker normalization, and then the warping factor of the unknown speaker will be extracted by comparing the feature vectors and the codebook. Finally, the extracted warping factor is used to linearly warp the Mel scale filter bank adopted in the course of MFCC calculation. To test the performance of the proposed method, a series of recognition experiments are conducted on discrete HMM with thirteen mono-syllabic Korean number utterances. The results showed that about 29% of word error rate can be reduced, and that the proposed warping factor extraction method is useful due to its simplicity compared to other line search warping methods.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.12
• /
• pp.129-137
• /
• 2013

As the usage of computer based systems continues to increase in our normal life, there are constant efforts to enhance the accessibility of information for handicapped people. For this, it is essential to develop new interface ways for physical disabled peoples by means of human-computer interface (HCI) or human-machine interface (HMI). In this paper, we developed HMI using electromyogram (EMG) and electrooculogram (EOG) for people with physical disabilities. Developed system is composed of two modules, hardware module for signal sensing and software module for feature extraction and pattern classification. To maximize ease of use, only two skin contact electrodes are attached on both ends of brow, and EOG and EMG are measured simultaneously through these two electrodes. From measured signal, nine kinds of command patterns are extracted and defined using signal processing and pattern classification method. Through Java based real-time monitoring program, developed system showed 92.52% of command recognition rate. In addition, to show the capability of the developed system on real applications, five different types of commands are used to control ER1 robot. The results show that developed system can be applied to disabled person with quadriplegia as a novel interface way.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.2
• /
• pp.81-88
• /
• 2018

Spectrum sensing, the key technology of the cognitive radio networks, is used by a secondary user to determine the frequency state of a primary user. The energy detection in the spectrum sensing determines the presence or absence of a primary user according to the intensity of the allocated channel signal. Since this technique simply uses the strength of the signal for spectrum sensing, it is difficult to detect the signal of a primary user in the low SNR band. In this paper, we propose a way to combine spectrum sensing and support vector machine using wavelet packet decomposition to overcome performance degradation in low SNR band. In our proposed scheme, the sensing signals were extracted by wavelet packet decomposition and then used as training data and test data for support vector machine. The simulation results of the proposed scheme are compared with the energy detection using the AUC of the ROC curve and the accuracy according to the SNR band. With simulation results, we demonstrate that the proposed scheme show better determining performance than one of energy detection in the low SNR band.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.1
• /
• pp.73-82
• /
• 2010

Door is an important object to understand given environment and it could be used to distinguish with corridors and rooms. Doors are widely used natural landmark in mobile robotics for localization and navigation. However, almost algorithm for door recognition with camera is difficult real-time application because feature extraction and matching have heavy computation complexity. This paper proposes a method to recognize a door in corridor. First, we extract distinguished lines which have high possibility to comprise of door using Hough transformation. Then, we detect candidate of door region by applying previously extracted lines to first-stage visual fuzzy system. Finally, door regions are determined by verifying knob region in candidate of door region suing second-stage visual fuzzy system.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.4
• /
• pp.15-22
• /
• 2011

Principal component analysis (PCA) is a well-known method for dimensionality reduction and feature extraction while maintaining most of the variation in data. Although PCA has been applied in many areas successfully, it is sensitive to outliers and only valid for Gaussian distributions. Several variants of PCA have been proposed to resolve noise sensitivity and, among the variants, improved robust fuzzy PCA (RF-PCA2) demonstrated promising results. RF-PCA, however, is still a linear algorithm that cannot accommodate non-Gaussian distributions. In this paper, a non-linear algorithm that combines RF-PCA2 and kernel PCA (K-PCA), called improved robust kernel fuzzy PCA (RKF-PCA2), is introduced. The kernel methods make it to accommodate non-Gaussian distributions. RKF-PCA2 inherits noise robustness from RF-PCA2 and non-linearity from K-PCA. RKF-PCA2 outperforms previous methods in handling non-Gaussian distributions in a noise robust way. Experimental results also support this.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.10
• /
• pp.93-100
• /
• 2011

The necessity of research on extracting information of face and facial components in animation characters have been increasing since they can effectively express the emotion and personality of characters. In this paper, we introduce a method to extract face and facial components of animation characters by defining a mesh model adequate for characters and by using dominant colors. The suggested algorithm first generates a mesh model for animation characters, and extracts dominant colors for face and facial components by adapting the mesh model to the face of a model character. Then, using the dominant colors, we extract candidate areas of the face and facial components from input images and verify if the extracted areas are real face or facial components by means of color similarity measure. The experimental results show that our method can reliably detect face and facial components of animation characters.