• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1319-1323
• /
• 2004

In this paper, a problem of Thai sign language recognition using a neural network is considered. The paper addresses the problem in classifying certain signs conveying quantitative meaning, e.g., large or small. By treating those signs corresponding to different quantities as derived from different classes, the recognition error rate of the standard multi-layer Perceptron increases if the precision in recognizing different quantities is increased. This is due the fact that, to increase the quantitative recognition precision of those signs, the number of (increasingly similar) classes must also be increased. This leads to an increase in false classification. The problem is due to misinterpreting the amount of quantity the quantitative signs convey. In this paper, instead of treating those signs conveying quantitative attribute of the same quantity type (such as 'size' or 'amount') as derived from different classes, here they are considered instances of the same class. Those signs of the same quantity type are then further divided into different subclasses according to the level of quantity each sign is associated with. By using this two-level classification, false classification among main gesture classes is made independent to the level of precision needed in recognizing different quantitative levels. Moreover, precision of quantitative level classification can be made higher during the recognition phase, as compared to that used in the training phase. A standard multi-layer Perceptron with a back propagation learning algorithm was adapted in the study to implement this two-level classification of quantitative gesture signs. Experimental results obtained using an electronic glove measurement of hand postures are included.

• Journal of the East Asian Society of Dietary Life
• /
• v.11 no.6
• /
• pp.446-454
• /
• 2001

With the rapid expansion of the economy, consumers' interest in health has also grown and the consumption of health foods is also growing at a rapid rate. However, because of the lack of understanding and Information about health foods, there is growing discontentment societally and in relation to the consumers' individual health. This study was conducted to get consumers to use the health food soundly and provide useful information to consumer behavior researchers of health food by researching consumers' past consumption experience and recognition of health foods. 662 people over the age of 20 in the Seoul area were sampled for this study. Through the results of this study, it was revealed that 71.5% of the respondents said they consumed health foods in the past year. The people surveyed said they thought they were health on the whole(3.72) and were slightly concerned (3.30) with their health. Lastly. the results of the studying the recognition of health food, respondents believe that health foods help to maintenance of good health(3.63) recover from fatigue(3.59), prevent of disease(3.32). They also believe that it is not harmful to the body(2.85) but were concerned about additives(3.24) and side effects(3.24) The study also found consumers to think that health foods are expensive(4.03) but is not of the highest quality(2.84) and that the dosage is not exact(2.84). In addition. they believe the labeling to be accurate(2.89), the ads to be exaggerated(3.88). information about the products to be lacking(3.71) and finally refund or exchange to be difficult(3.85).

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.1
• /
• pp.17-23
• /
• 2005

In this paper, we propose face recognition method using embedded data in super states segmentalized that is specification region exist to face region, hair, forehead, eyes, ears, nose, mouth, and chin. Proposed method defines super states that is specification area in normalized size (92×112), and embedded data that is extract internal factor in super states segmentalized achieve face recognition by PCA algorithm. Proposed method can receive specification data that is less in proposed image's size (92×112) because do orignal image to learn embedded data not to do all loaming. And Showed face recognition rate in image of 92×112 size averagely 99.05%, step 1 99.05%, step 2 98.93%, step 3 98.54%, step 4 97.85%. Therefore, method that is proposed through an experiment showed that the processing speed improves as well as reduce existing face image's information.

• Journal of Korea Multimedia Society
• /
• v.13 no.4
• /
• pp.504-511
• /
• 2010

In this paper, we propose the face region recognition system for City-Security CCTV(Closed Circuit Television) using hippocampal neural network which is modelling of human brain's hippocampus. This system is composed of feature extraction, learning and recognition part. The feature extraction part is constructed using PCA(Principal Component Analysis) and LDA(Linear Discriminants Analysis). In the learning part, it can label the features of the image-data which are inputted according to the order of hippocampal neuron structure to reaction-pattern according to the adjustment of a good impression in a dentate gyrus and remove the noise through the auto-associative memory in the CA3 region. In the CA1 region receiving the information of the CA3, it can make long-term memory learned by neuron. Experiments confirm the each recognition rate, that are shape change and light change. The experimental results show that we can compare a feature extraction and learning method proposed in this paper of any other methods, and we can confirm that the proposed method is superior to existing methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.8
• /
• pp.1478-1489
• /
• 2006

This paper describes system to extract ISO codes in container image. A container ISO code recognition system for real-time processing is made of 5 core parts which are container ISO code detection and image acquisition, ISO code region extraction, individual character extraction, character recognition and database. Among them, the accuracy of ISO code extraction can affect significantly the accuracy of system recognition rate, and also the more exact extraction of ISO code is required in various weather and environment conditions. The proposed system produces binary of the ISO code's template lesions using an adaptive thresholding, extracts candidate regions containing distribution of ISO code, and recognizes ISO codes as detecting a final region through the verifications by using character distribution characteristics of ISO code among the extracted candidates. Experimental results reveal that ISO codes can be efficiently extracted by the proposed method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.12
• /
• pp.2647-2654
• /
• 2011

In this paper, the algorithm that recognizes the gesture by configuring the feature information obtained through edge orientation histogram and principal component analysis as low dimensional gesture symbol was described. Since the proposed method doesn't require a lot of computations compared to the existing geometric feature based method or appearance based methods and it can maintain high recognition rate by using the minimum information, it is very well suited for real-time system establishment. In addition, to reduce incorrect recognition or recognition errors that occur during gesture recognition, the model feature values projected in the gesture space is configured as a particular status symbol through clustering algorithm to be used as input symbol of hidden Markov models. By doing so, any input gesture will be recognized as the corresponding gesture model with highest probability.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.7
• /
• pp.1349-1354
• /
• 2017

In this paper, we propose a fast hand-gesture recognition algorithm for embedded system. Existing hand-gesture recognition algorithm has a difficulty to use in a low performance system such as embedded systems and mobile devices because of high computational complexity of contour tracing method that extracts all points of hand contour. Instead of using algorithms based on contour tracing, the proposed algorithm uses concentric-circle tracing method to estimate the abstracted contour of fingers, then classify hand-gestures by extracting features. The proposed algorithm has an average recognition rate of 95% and an average execution time of 1.29ms, which shows a maximum performance improvement of 44% compared with algorithm using the existing contour tracing method. It is confirmed that the algorithm can be used in a low performance system such as embedded systems and mobile devices.

• Journal of Broadcast Engineering
• /
• v.23 no.5
• /
• pp.598-605
• /
• 2018

Behavior awareness is a technology that recognizes human behavior through data and can be used in applications such as risk behavior through video surveillance systems. Conventional behavior recognition algorithms have been performed using the 2D camera image device or multi-mode sensor or multi-view or 3D equipment. When two-dimensional data was used, the recognition rate was low in the behavior recognition of the three-dimensional space, and other methods were difficult due to the complicated equipment configuration and the expensive additional equipment. In this paper, we propose a method of recognizing human behavior using only CCTV images without additional equipment using only RGB and depth information. First, the skeleton extraction algorithm is applied to extract points of joints and body parts. We apply the equations to transform the vector including the displacement vector and the relational vector, and study the continuous vector data through the RNN model. As a result of applying the learned model to various data sets and confirming the accuracy of the behavior recognition, the performance similar to that of the existing algorithm using the 3D information can be verified only by the 2D information.

• The Journal of the Korea Contents Association
• /
• v.18 no.4
• /
• pp.398-405
• /
• 2018

In the HCI, hand gesture recognition is attracting attention as a method for interaction and information exchange between users and devices along with the development of IT devices. In hand gesture recognition through image processing, palm region detection is a key process contributing to improvement of processing speed and recognition rate. In this paper, we propose a new method for image segmentation between the hand and wrist for palm area detection. The anatomical characteristics of the hand are used to calculate the distance between the iliac bones of the thumb and little finger, which have the widest width, by the horizontal projection histogram of the hand image, and then the palm area is detected by drawing a circle having the width as the diameter. In order to verify the superiority of this method, multiple stage template matching is used to compare and evaluate recognition performance against the four conventional methods for 10 hand gestures. Note that the literatures to offer palm area detection performance evaluation are few although there are many studies on hand gesture recognition.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.9
• /
• pp.5446-5451
• /
• 2014

Because there are some mistakes by hand in processing electronic maps using a navigation terminal, this paper proposes an automatic offline recognition for traffic signs, which are considered ingredient navigation information. Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA), which have been used widely in the field of 2D face recognition as computer vision and pattern recognition applications, was used to recognize traffic signs. First, using PCA, a high-dimensional 2D image data was projected to a low-dimensional feature vector. The LDA maximized the between scatter matrix and minimized the within scatter matrix using the low-dimensional feature vector obtained from PCA. The extracted traffic signs under a real-world road environment were recognized successfully with a 92.3% recognition rate using the 40 feature vectors created by the proposed algorithm.