• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.105.2-105
• /
• 2001

This paper studies continuous Korean Sign Language (KSL) recognition using color vision. In recognizing gesture words such as sign language, it is a very difficult to segment a continuous sign into individual sign words since the patterns are very complicated and diverse. To solve this problem, we disassemble the KSL into 18 hand motion classes according to their patterns and represent the sign words as some combination of hand motions. Observing the speed and the change of speed of hand motion and using state automata, we reject unintentional gesture motions such as preparatory motion and meaningless movement between sign words. To recognize 18 hand motion classes we adopt Hidden Markov Model (HMM). Using these methods, we recognize 5 KSL sentences and obtain 94% recognition ratio.

• Proceedings of the KSME Conference
• /
• 2003.04a
• /
• pp.935-939
• /
• 2003

The emotion recognition is one of the most significant interface technologies which make the high level of human-machine communication possible. The central nervous system stimulated by emotional stimuli affects the autonomous nervous system like a heart, blood vessel, endocrine organs, and so on. Therefore bio-signals like HRV, ECG and EEG can reflect one' emotional state. This study investigates the correlation between emotional states and bio-signals to realize the emotion recognition. This study also covers classification of human emotional states, selection of the effective bio-signal and signal processing. The experimental results presented in this paper show possibility of the emotion recognition.

• Proceedings of the KSPS conference
• /
• 2003.10a
• /
• pp.145-148
• /
• 2003

To improve the recognition performance of Korean connected digit telephone speech, in this paper, both Aurora feature extraction method that employs noise reduction 2-state Wiener filter and DWFBA method are investigated and used. CMN and MRTCN are applied to static features for channel compensation. Telephone digit speech database released by SITEC is used for recognition experiments with HTK system. Experimental results has shown that Aurora feature is slightly better than MFCC and DWFBA without channel compensation. And when channel compensation is included, Aurora feature is slightly better than DWFBA with MRTCN.

• Proceedings of the KSPS conference
• /
• 2005.04a
• /
• pp.87-90
• /
• 2005

Today's state-of the-art speech recognition systems typically use continuous distribution hidden Markov models with the mixtures of Gaussian distributions. To obtain higher recognition accuracy, the hidden Markov models typically require huge number of Gaussian distributions. Such speech recognition systems have problems that they require too much memory to run, and are too slow for large applications. Many approaches are proposed for the design of compact acoustic models. One of those models is subspace distribution clustering hidden Markov model. Subspace distribution clustering hidden Markov model can represent original full-space distributions as some combinations of a small number of subspace distribution codebooks. Therefore, how to make the codebook is an important issue in this approach. In this paper, we report some experimental results on various quantization methods to make more accurate models.

• Journal of Institute of Control, Robotics and Systems
• /
• v.4 no.6
• /
• pp.765-771
• /
• 1998

An artificial neural network(NN) technique is developed for hardware redundant sensor validation. Since the measurement space is a continuous space with many operating regions, it is difficult to train a NN to correctly detect failure in an accurate measurement system. A conventional backpropagation NN is modified to include an additional preprocessing layer that extracts classification features from scalar measurements. This feature extraction means transform the measurement space to parity space. The NN is independent of the state variable being measured, the instrument range, and the signal tolerance. This NN resembles the parity space approach to signal validation, except that analytical parity equations are unneeded and the NN pattern recognition capability is utilized for decision making.

• Journal of the Korean Society of Industry Convergence
• /
• v.18 no.4
• /
• pp.241-249
• /
• 2015

The purpose of this research is to develop the pattern recognition algorithm based on smart camera for inspection automation, and including external surface state of molding parts or optical parts. By performance verification, this development can be applied to establish for existing reflex data because inputting surface badness degree of scratch's standard specification condition directly. And it is pdssible to distinguish from schedule error of badness product and normalcy product within schedule extent after calculating the error comparing actuality measurement reflex data and standard reflex data mutually. The proposed technology cab be applied to test for masearing of the smallest 10 pixel unit. It is illustrated the relibility pf proposed technology by an experiment.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2008.06a
• /
• pp.199-204
• /
• 2008

Visual surveillance is an active topic recently in Computer Vision. Event detection and recognition is one important and useful application of visual surveillance system. In this paper, we propose a new method to recognize the entering and exiting events based on the human's movement feature and the door's state. Without sensors, the proposed approach is based on novel and simple vision method as a combination of edge detection, motion history image and geometrical characteristic of the human shape. The proposed method includes several applications such as access control in visual surveillance and computer vision fields.

• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.435-437
• /
• 2004

This paper presents a personal identification method using teeth images. The method uses images for teeth expressions of anterior and posterior occlusion state and LDA-based technique. Teeth images give merits for recognition because teeth, rigid objects, cannot be deformed at the moment of image acquisition. In the experiments, personal identification for 12 people was successful. It was shown that our method can contribute to multi-modal authentication systems.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.11
• /
• pp.1455-1463
• /
• 1995

A new automatic tracking & recognition algorithm which decides the opening & the closing states of subject's eye and isn't affected by the subject's background is proposed. And it was tested in circumstances in which subject's background was not restricted using the developed system, ATRS(Automatic Tracking & Recognition System). The significant characteristic of the ATRS is new movement detection of object that is a body in motion with accelated velocity and it doesn't need any extra hardware except a formal CCD camera and an image grabber but it works so well and so fast. The ATRS would be particularly well suited to a way of communications of patients in a hospital, who can not communicate otherwise.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.3B
• /
• pp.565-569
• /
• 2000

We compose the two-stage recurrent neural network that returns both signals of a hidden and an output layer to the hidden layer. It is tested on the basis of syllables for Korean spoken digit from /gong/to /gu. For these experiments, we adjust the neuron number of the hidden layer, the predictive order of input data and self-recurrent coefficient of the decision state layer. By the experimental results, the recognition rate of this neural network is between 91% and 97.5% in the speaker-dependent case and between 80.75% and 92% in the speaker-independent case. In the speaker-dependent case, this network shows an equivalent recognition performance to Jordan and Elman network but in the speaker-independent case, it does improved performance.