• Journal of the Korea Society of Computer and Information
• /
• v.16 no.4
• /
• pp.1-13
• /
• 2011

In this paper, we propose a gesture recognition system to recognize motions using the shape information of MHI (Motion History Image). The system acquires MHI to provide information on motions from images with input and extracts the gradient images from such MHI for each X and Y coordinate. It extracts the shape information by applying the shape context to each gradient image and uses the extracted pattern information values as the feature values. It recognizes motions by learning and classifying the obtained feature values with a SVM (Support Vector Machine) classifier. The suggested system is able to recognize the motions for multiple people as well as to recognize the direction of movements by using the shape information of MHI. In addition, it shows a high ratio of recognition with a simple method to extract features.

• Journal of Internet Computing and Services
• /
• v.11 no.1
• /
• pp.129-141
• /
• 2010

In this paper, we present a wearable intelligent device based on multi-sensor for monitoring human activity. In order to recognize multiple activities, we developed activity recognition algorithms utilizing an image sensor and a 3-axis accelerometer sensor. We proposed a grid?based optical flow method and used a SVM classifier to analyze data acquired from multi-sensor. We used the direction and the magnitude of motion vectors extracted from the image sensor. We computed the correlation between axes and the magnitude of the FFT with data extracted from the 3-axis accelerometer sensor. In the experimental results, we showed that the accuracy of activity recognition based on the only image sensor, the only 3-axis accelerometer sensor, and the proposed multi-sensor method was 55.57%, 89.97%, and 89.97% respectively.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.10c
• /
• pp.263-266
• /
• 2007

We introduce a vision-based hand gesture recognition fer understanding musical time and patterns without extra special devices. We suggest a simple and reliable vision-based hand gesture recognition having two features First, the motion-direction code is proposed, which is a quantized code for motion directions. Second, the conducting feature point (CFP) where the point of sudden motion changes is also proposed. The proposed hand gesture recognition system extracts the human hand region by segmenting the depth information generated by stereo matching of image sequences. And then, it follows the motion of the center of the gravity(COG) of the extracted hand region and generates the gesture features such as CFP and the direction-code finally, we obtain the current timing pattern of beat and tempo of the playing music. The experimental results on the test data set show that the musical time pattern and tempo recognition rate is over 86.42% for the motion histogram matching, and 79.75% fer the CFP tracking only.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.2
• /
• pp.61-74
• /
• 2012

In this paper, we propose a illumination-robust face recognition system using MCS-LBP and 2D-PCA algorithm. A binary pattern transform which has been used in the field of the face recognition and facial expression, has a characteristic of robust to illumination. Thus, this paper propose MCS-LBP which is more robust to illumination than previous LBP, and face recognition system fusing 2D-PCA algorithm. The performance evaluation of proposed system was performed by using various binary pattern images and well-known face recognition features such as PCA, LDA, 2D-PCA and ULBP histogram of gabor images. In the process of performance evaluation, we used a YaleB face database, an extended YaleB face database, and a CMU-PIE face database that are constructed under varying lighting condition, and the proposed system which consists of MCS-LBP image and 2D-PCA feature show the best recognition accuracy.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.521-525
• /
• 2009

In this paper, we introduce fire detection system and software learning algorithm that recognize fire patterns. Flame patterns means that periodical and consistent pattern about general conception of fire, and to process it with the definition. Learning algorithm for flame pattern recognition that we propose is the method which is faster and more exactly than existing algorithm. Also, we trying to elicit the method through experiment result and by applying it, we show the validity of an early fire warning system.

• Proceedings of the KIEE Conference
• /
• 2006.07e
• /
• pp.55-56
• /
• 2006

In prevention and diagnostic system of GIS, pattern classification is focused on the detection of unnatural patterns in PD(Partial discharge) image data. Fractals have been used extensively to provide a description and to model mathematically many of the naturally occurring complex shapes, such as coastlines, mountain ranges, clouds, etc., and have also received increased attention in the field of image processing, for purposes of segmentation and recognition of regions and objects present in natural scenes. Among the numerous fractal features that could be defined and used for image data, fractal dimension and lacunarity have been found to be useful for recognition purposes Partial discharge(PD) occuring in GIS system is a very complex phenomenon, and more so are the shapes of the various 2-d patterns obtained during routine tests and measurements. It has been fairly well established that these pattern shapes and underlying defects causing PD have a 1:1 correspondence, and therefore methods to describe and qunatify these pattern shapes must be explored, before recognition systems based on them could be developed. The computed fractal features(fractal dimension and lacunarity) for standard library of PD data were analyzed and found to possess fairly reasonable pattern discriminating abilities. This new approach appears promising, and further research is essential before any long-term predictions can be made.

• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.2
• /
• pp.60-67
• /
• 2007

This paper describes the development of on-line computer vision laboratories to teach the detailed image processing and pattern recognition techniques. The computer vision laboratories include distant image acquisition method, basic image processing and pattern recognition methods lens and light, and communication. This study introduces a case study that teaches computer vision in distance learning. environment. It shows a schematic of a distant teaming workstation and contents of laboratories with image processing examples. The study focus more on the contents of the vision Labs rather than internet application method. The study proposes the ways to improve the on-line computer vision laboratories and includes the further research perspectives.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.3
• /
• pp.576-586
• /
• 1996

Original binary image can be reconstructed by morphological bymorphological skeleton(MS) image. And then, the information of MS image points can be applied to a pattern recognition andimage communication. But if we apply MS to a pattern recognition and image communication, there are two problems. That is to say, binary MS processing times is long and skeleton points of MS are high redundancy. And then, to solve these problems, this paper proposes DGMS. After simulating by the proposed method to $256{\times}256$ binary image which is GIRL, we reduce processing time and skeleton points about 1.5~6.5% comparing with the result of GMS method.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.1
• /
• pp.402-410
• /
• 2017

For many years, researchers in face description area have been representing and recognizing faces based on different methods that include subspace discriminant analysis, statistical learning and non-statistics based approach etc. But still automatic face recognition remains an interesting but challenging problem. This paper presents a novel and efficient face image representation method based on Optimized Local Ternary Pattern (OLTP) texture features. The face image is divided into several regions from which the OLTP texture feature distributions are extracted and concatenated into a feature vector that can act as face descriptor. The recognition is performed using nearest neighbor classification method with Chi-square distance as a similarity measure. Extensive experimental results on Yale B, ORL and AR face databases show that OLTP consistently performs much better than other well recognized texture models for face recognition.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.8
• /
• pp.1136-1141
• /
• 2022

Researches of face recognition on masked faces have been increasingly important due to the COVID-19 pandemic. To realize a stable and practical recognition performance, large amount of facial image data should be acquired for the purpose of training. However, it is difficult for the researchers to obtain masked face images for each human subject. This paper proposes a novel method to synthesize a face image and a virtual mask pattern. In this method, a pair of masked face image and unmasked face image, that are from a single human subject, is fed into a convolutional autoencoder as training data. This allows learning the geometric relationship between face and mask. In the inference step, for a unseen face image, the learned convolutional autoencoder generates a synthetic face image with a mask pattern. The proposed method is able to rapidly generate realistic masked face images. Also, it could be practical when compared to methods which rely on facial feature point detection.