• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.10
• /
• pp.2632-2649
• /
• 2012

Most approaches to human action recognition is limited due to the use of simple action datasets under controlled environments or focus on excessively localized features without sufficiently exploring the spatio-temporal information. This paper proposed a framework for recognizing realistic human actions. Specifically, a new action representation is proposed based on computing a rich set of descriptors from keypoint trajectories. To obtain efficient and compact representations for actions, we develop a feature fusion method to combine spatial-temporal local motion descriptors by the movement of the camera which is detected by the distribution of spatio-temporal interest points in the clips. A new topic model called Markov Semantic Model is proposed for semantic feature selection which relies on the different kinds of dependencies between words produced by "syntactic " and "semantic" constraints. The informative features are selected collaboratively based on the different types of dependencies between words produced by short range and long range constraints. Building on the nonlinear SVMs, we validate this proposed hierarchical framework on several realistic action datasets.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.1
• /
• pp.160-164
• /
• 2005

The process of recognizing a vehicle involves detection of the vehicle, recognition of the vehicle model, and identification of the vehicle. The process of vehicle identification involves identification of the vehicle itself, such as by recognition of the license plate on the vehicle. In this paper the method involves the use of a beam splitter to divide incident rays into two directions, a transmitted beam and a reflected beam of different light intensities, and synthesizing two captured images using CCD devices from each beam, thus producing fluctuation-free images of a wide dynamic range even when the subject is moving. A prototype license plate recognition system was also developed using the experimental sensing device. The system achieved a 98.7% recognition rate on 466 images of moving vehicles, which demonstrates its effectiveness as a license plate recognition system.

• Speech Sciences
• /
• v.13 no.1
• /
• pp.129-139
• /
• 2006

In this paper, we propose two effective energy feature normalization methods for robust speech recognition in noisy environments. In the first method, we estimate the noise energy and remove it from the noisy speech energy. In the second method, we propose a modified algorithm for the Log-energy Dynamic Range Normalization (ERN) method. In the ERN method, the log energy of the training data in a clean environment is transformed into the log energy in noisy environments. If the minimum log energy of the test data is outside of a pre-defined range, the log energy of the test data is also transformed. Since the ERN method has several weaknesses, we propose a modified transform scheme designed to reduce the residual mismatch that it produces. In the evaluation conducted on the Aurora2.0 database, we obtained a significant performance improvement.

• Current Optics and Photonics
• /
• v.4 no.5
• /
• pp.421-427
• /
• 2020

A novel privacy-protection device to prevent visual hacking is realized by using a directional backlight and facial recognition. The proposed method is able to overcome the limitations of previous privacy-protection methods that simply restrict the viewing angle to a narrow range. The accuracy of user tracking is accomplished by the combination of a time-of-flight sensor and facial recognition with no restriction of detection range. In addition, an experimental demonstration is provided to verify the proposed scheme.

• Proceedings of the ESK Conference
• /
• 1995.04a
• /
• pp.124-133
• /
• 1995

A field study was conducted to assess the preferred height and the range of discomfort recognition of school desks and chairs for students from elementary school to high school. For this study 43 male subjects and 44 female subjects in Taejon area were surveyed. The result shows that the preferred height of chairs is about 1.7cm higher than the popliteal sitting height, while the preferred height of desks shows no significant difference with the elbow sitting height which is known to be the ergonomically proper desk height. The threshold value between comfort and discomfort recognition of chair height is 1.88cm below the most prefeered height and 1.79cm about it. The threshold value between comfort and discomfort recognition of desk height is 1.76cm below the most prefeered height and 2.62cm about it.

• Journal of the Ergonomics Society of Korea
• /
• v.14 no.2
• /
• pp.41-50
• /
• 1995

A field study was conducted to assess the preferred height and the range of discomfort recognition of school desks and chairs for students from elementary school to high school. For this study 43 male subjects and 44 female subjects in Taejon metropolitan area were surveyed. The result showed that the preferred height of chairs were found to be about 1.7cm higher than the popliteal sitting height, while the preferred height of desks showed no significant difference with the elbow sitting height which is known to be the ergonomically proper desk height. The threshold value between comfort and discomfort recognition of chair heigth was 1.88cm below the most preferred height and 1.79cm above it. The threshold value between comfort and discomfort recognition of desk height was 1.76cm below the most preferred height and 2.62cm above it.

• Speech Sciences
• /
• v.9 no.4
• /
• pp.253-263
• /
• 2002

In this paper, we propose new algorithm of speaker recognition which identifies the speaker using the information obtained by the intensive speech feature analysis such as pitch, intensity, duration, and formant, which are crucial parameters of individual voice, for candidates of high percentage of wrong recognition in the existing speaker recognition algorithm. For testing the power of discrimination of individual parameter, DTW (Dynamic Time Warping) is used. We newly set the range of threshold which affects the power of discrimination in speech verification such that the candidates in the new range of threshold are finally discriminated in the next stage of sound parameter analysis. In the speaker verification test by using voice DB which consists of secret words of 25 males and 25 females of 8 kHz 16 bit, the algorithm we propose shows about 1% of performance improvement to the existing algorithm.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.5 no.1
• /
• pp.103-110
• /
• 2011

In this paper, we propose a gaze recognition interface for smart wheelchair. The gaze recognition interface is a user interface which recognize the commands using the gaze recognition and avoid the detected obstacles by sensing the distance through range sensors on the way to driving. Smart wheelchair is composed of gaze recognition and tracking module, user interface module, obstacle detector, motor control module, and range sensor module. The interface in this paper uses a camera with built-in infra red filter and 2 LED light sources to see what direction the pupils turn to and can send command codes to control the system, thus it doesn't need any correction process per each person. The results of the experiment showed that the proposed interface can control the system exactly by recognizing user's gaze direction.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.2
• /
• pp.208-213
• /
• 2010

Generally, the mal factor for speech recognition is the background noise in speech recognition. The noise is the reason to reduce the speech recognition performance. Owing to the fact, the place to recognize is very important. To improve the recognition performance from the sound having noise, we implemented the noise filtered Wiener filter at the signal process step which adopted the FIR filter. In FIR filter, it deal with the filtered speech signal which is appropriate frequency range of human speech frequency range. Therefore, we make the recognition system distinguish between noise and speech sound from the incoming speech signal.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.2
• /
• pp.135-140
• /
• 2012

The mirror neuron system in the cerebrum, which are handled by visual information-based imitative learning. When we observe the observer's range of mirror neuron system, we can assume intention of performance through progress of neural activation as specific range, in include of partially hidden range. It is goal of our paper that imitative learning is applied to 3D vision-based intelligent system. We have experiment as stereo camera-based restoration about acquired 3D image our previous research Using Optical flow, unscented Kalman filter. At this point, 3D input image is sequential continuous image as including of partially hidden range. We used Hidden Markov Model to perform the intention recognition about performance as result of restoration-based hidden range. The dynamic inference function about sequential input data have compatible properties such as hand gesture recognition include of hidden range. In this paper, for proposed intention recognition, we already had a simulation about object outline and feature extraction in the previous research, we generated temporal continuous feature vector about feature extraction and when we apply to Hidden Markov Model, make a result of simulation about hand gesture classification according to intention pattern. We got the result of hand gesture classification as value of posterior probability, and proved the accuracy outstandingness through the result.