• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.3
• /
• pp.241-246
• /
• 2016

Nowadays many people have an interest in facial expression and the behavior of people. These are human-robot interaction (HRI) researchers utilize digital image processing, pattern recognition and machine learning for their studies. Facial feature point detector algorithms are very important for face recognition, gaze tracking, expression, and emotion recognition. In this paper, a cascade facial feature point detector is used for finding facial feature points such as the eyes, nose and mouth. However, the detector has difficulty extracting the feature points from several images, because images have different conditions such as size, color, brightness, etc. Therefore, in this paper, we propose an algorithm using a modified cascade facial feature point detector using a convolutional neural network. The structure of the convolution neural network is based on LeNet-5 of Yann LeCun. For input data of the convolutional neural network, outputs from a cascade facial feature point detector that have color and gray images were used. The images were resized to $32{\times}32$. In addition, the gray images were made into the YUV format. The gray and color images are the basis for the convolution neural network. Then, we classified about 1,200 testing images that show subjects. This research found that the proposed method is more accurate than a cascade facial feature point detector, because the algorithm provides modified results from the cascade facial feature point detector.

• The Journal of the Korea Contents Association
• /
• v.12 no.12
• /
• pp.63-70
• /
• 2012

In medical image processing field, object recognition is usually processed based on region segmentation algorithm. Region segmentation in the computing field is carried out by computerized processing of various input information such as brightness, shape, and pattern analysis. If the information mentioned does not make sense, however, many limitations could occur with region segmentation during computer processing. Therefore, this paper suggests effective region segmentation method based on R2-map information within the magnetic resonance (MR) theory. In this study, the experiment had been conducted using images including the liver region and by setting up feature points of R2-map as seed points for 2D region growing and final boundary correction to enable region segmentation even when the border line was not clear. As a result, an average area difference of 7.5%, which was higher than the accuracy of conventional exist region segmentation algorithm, was obtained.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.4
• /
• pp.107-114
• /
• 2008

In this paper, we constructed a speech emotion recognition system that classifies four emotions - neutral, happy, sad, and anger from speech based on male/female gender discrimination. At first, the proposed system distinguish between male and female from a queried speech, then the system performance can be improved by using separate optimized feature vectors for each gender for the emotion classification. As a emotion feature vector, this paper adopts ZCPA(Zero Crossings with Peak Amplitudes) which is well known for its noise-robustic characteristic from the speech recognition area and the features are optimized using SFS method. For a pattern classification of emotion, k-NN and SVM classifiers are compared experimentally. From the computer simulation results, the proposed system was proven to be highly efficient for speech emotion classification about 85.3% regarding four emotion states. This might promise the use the proposed system in various applications such as call-center, humanoid robots, ubiquitous, and etc.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.7
• /
• pp.71-78
• /
• 2017

There are several algorithms to classify emotion, such as Support-vector-machine (SVM), Bayesian decision rule, etc. However, many researchers have insisted that these methods have minor problems. Therefore, in this paper, we propose a novel method for emotion recognition based on Electroencephalogram (EEG) signal using the Gradient method which was proposed by Han. We also utilize a database for emotion analysis using physiological signals (DEAP) to obtain objective data. And we acquire four channel brainwaves, including Fz (${\alpha}$), Fp2 (${\beta}$), F3 (${\alpha}$), F4 (${\alpha}$) which are selected in previous study. We use 4 features which are power spectral density (PSD) of the above channels. According to performance evaluation (4-fold cross validation), we could get 85% accuracy in valence axis and 87.5% in arousal. It is 5-7% higher than existing method's.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.4
• /
• pp.340-345
• /
• 2018

The Compared to general sentences, the Equation uses a complex structure and various characters and symbols, so that it is not possible to input all the character sets by simply inputting a keyboard. Therefore, the editor is implemented in a text editor such as Hangul or Word. In order to express the Equation properly, it is necessary to have the learner information which can be meaningful to interpret the syntax. Even if a character is input, it can be represented by another expression depending on the relationship between the size and the position. In other words, the form of the expression is expressed as a tree model considering the relationship between characters and symbols such as the position and size to be expressed. As a field of character recognition application, a technique of recognizing characters or symbols(code) has been widely known, but a method of inputting and interpreting a Equation requires a more complicated analysis process than a general text. In this paper, we have implemented a Equation recognizer that recognizes characters in expressions and quickly analyzes the position and size of expressions.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.10a
• /
• pp.88-95
• /
• 2012

The passport is not only an officially proven document in order to identify the nationalities of travelers, but also request for protections of travelers. Since the overseas trips have been increased, the uses of forged or modulated passports are also now rapidly increasing. The forged or modulated passports are mainly used by international criminal organization or offenders, who are restricted by immigration control, in order to avoid under the radar and conceal their identities. The purpose of biometric authentication technology is to define one's unique identities through the comparative analysis one's unique finger prints, iris, sweat gland, blood vessel, palm pattern, vein distribution, voice, and etc. We have been studying about applicable and possibilities of the biometric authentication technology for overseas travel without passports. In hence, we have been also collected various of technical references of using biometric authentication, and have been analyzed what is the best biometric to be alternatively used instead of passports.

• Journal of KIISE
• /
• v.42 no.11
• /
• pp.1372-1379
• /
• 2015

This paper presents an analysis of feature extraction methods used for distinguishing the speech of patients with cleft palates and people with normal palates. This research is a basic study on the development of a software system for automatic recognition and restoration of speech disorders, in pursuit of improving the welfare of speech disabled persons. Monosyllable voice data for experiments were collected for three groups: normal speech, cleft palate speech, and simulated clef palate speech. The data consists of 14 basic Korean consonants, 5 complex consonants, and 7 vowels. Feature extractions are performed using three well-known methods: LPC, MFCC, and PLP. The pattern recognition process is executed using the acoustic model GMM. From our experiments, we concluded that the MFCC method is generally the most effective way to identify speech distortions. These results may contribute to the automatic detection and correction of the distorted speech of cleft palate patients, along with the development of an identification tool for levels of speech distortion.

• Journal of KIISE
• /
• v.44 no.7
• /
• pp.668-673
• /
• 2017

Deep neural networks have shown remarkable performance in various fields of pattern recognition such as voice recognition, image recognition and object detection. However, underlying mechanisms of the network have not been fully revealed. In this paper, we focused on empirical analysis of the network parameters. The Faster R-CNN(region-based convolutional neural network) was used as a baseline network of our work and three important parameters were analyzed: the dropout ratio which prevents the overfitting of the neural network, the size of the anchor boxes and the activation function. We also compared the performance of dropout and batch normalization. The network performed favorably when the dropout ratio was 0.3 and the size of the anchor box had not shown notable relation to the performance of the network. The result showed that batch normalization can't entirely substitute the dropout method. The used leaky ReLU(rectified linear unit) with a negative domain slope of 0.02 showed comparably good performance.

• The Journal of the Korea Contents Association
• /
• v.6 no.1
• /
• pp.31-40
• /
• 2006

In this paper, we propose a gait recognition method based on gait silhouette sequences. Features of gait are affected by the variation of gait direction. Therefore, we synthesize silhouettes to canonical form by using planar homography in order to reduce the effect of the variation of gait direction. The planar homography is estimated with only the information which exist within the gait sequences without complicate operations such as camera calibration. Even though gait silhouettes are generated from an individual person, fragments beyond common characteristics exist because of errors caused by inaccuracy of background subtraction algorithm. In this paper, we use the Principal Component Analysis to analyze the deviated characteristics of each individual person. PCA used in this paper, however, is not same as the traditional strategy used in pattern classification. We use PCA as a criterion to analyze the amount of deviation from common characteristic. Experimental results show that the proposed method is robust to the variation of gait direction and improves separability of test-data groups.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.41 no.12
• /
• pp.1011-1017
• /
• 2013

The human voice is the most natural means of communication. The need for speech recognition technology is increasing gradually to increase the ease of human and machine interface. The function of the avionics equipment is getting various and complicated in consequence of the growth of digital technology development, so that the load of pilots in the fighter aircraft must become increased since they don't concentrate only the attack function, but also operate the complicated avionics equipments. Accordingly, if speech recognition technology is applied to the aircraft cockpit as regards the operating the avionics equipments, pilots can spend their time and effort on the mission of fighter aircraft. In this paper, the cockpit voice command system applicable to the fighter aircraft has been developed and the function and the performance of the system verified.