• Journal of Korea Society of Industrial Information Systems
• /
• v.9 no.2
• /
• pp.32-43
• /
• 2004

In this paper, a system which can effectively recognize the plate image extracted from camera set on a moving car is proposed. To extract car licence plate from moving vehicles, multiple candidates are maintained based on the strong vertical edges which are found in the region of car licence plate. A candidate region is selected among them based on the ratio of background and characters. We also make a comparative study of recognition performance between support vector machines and modular neural networks. The experimental results lead us to the conclusion that the former is superior to the latter. For a better recognition rate, a simple method combining the support vector machine with modular neural network where the output of the latter is used as the input of the former is suggested and evaluated. As we expected, the hybrid one shows the best result among those three methods we have mentioned.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.4
• /
• pp.350-357
• /
• 1991

A speech recognition system based on a neural network, which can be used for telephon number services was tested. Because in Korea two different cardinal number systems, a koreanic one and a sinokoreanic one, are in use, it is necessary that the used systems is able to recognize 22 discret words. The structure of the neural network used had two layers, also a structure with 3 layers, one hidden layreformed of each 11, 22 and 44 hidden units was tested. During the learning phase of the system the so called BP-algorithm (back propagation) was applied. The process of learning can e influenced by using a different learning factor and also by the method of learning(for instance random or cycle). The optimal rate of speaker independent recognition by using a 2 layer neural network was 96%. A drop of recognition was observed by overtraining. This phenomen appeared more clearly if a 3 layer neural network was used. These phenomens are described in this paper in more detail. Especially the influence of the construction of the neural network and the several states during the learning phase are examined.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.4
• /
• pp.40-49
• /
• 1994

In this paper, we propose methods for improving the performance of word recognition system. The ray stratey of the first method is to apply the inertia to the feature vector sequences of speech signal to stabilize the transitions between VQ cdoes. The second method is generating the new observation probabilities using the transition matrix of VQ codes as weights at the observation probability of the output symbol, so as to take into account the time relation between neighboring frames in DHMM. By applying the inertia to the feature vector sequences, we can reduce the overlapping of probability distribution of the response paths for each word and stabilize state transitions in the HMM. By using the transition matrix of VQ codes as weights in conventional DHMM. we can divide the probability distribution of feature vectors more and more, and restrict the feature distribution to a suitable region so that the performance of recognition system can improve. To evaluate the performance of the proposed methods, we carried out experiments for 50 DDD area names. As a result, the proposed methods improved the recognition rate by $4.2\%$ in the speaker-dependent test and $12.45\%$ in the speaker-independent test, respectively, compared with the conventional DHMM.

• Journal of the Korea Computer Industry Society
• /
• v.5 no.4
• /
• pp.491-502
• /
• 2004

In this paper, we propose a HMM model using FSVQ(First Section VQ), fuzzy theory and doubly spectral feature, as study on the isolated word recognition system of speaker-independent. In the proposed paper, LPC cepstrum coefficients and regression coefficients of LPC cepstrum as doubly spectral feature be used. And, training data are divided several section and first section is generated codebook of VQ, and then is obtained multi-observation sequences by order of large propabilistic values based on fuzzy nile from the codebook of the first section. Thereafter, this observation sequences of first section is trained and is recognized a word to be obtained highest probaility by same concept. Besides the speech recognition experiments of proposed method, we experiment the other methods under the equivalent environment of data and conditions. In the whole experiment, it is proved that the proposed method is superior to the others in recognition rate.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.6
• /
• pp.805-814
• /
• 2013

This paper proposes a robust hand segmentation method using view-invariant characteristic of a wrist-mounted camera, and deals with a hand shape recognition system based on segmented hand information. We actively utilize the advantage of the proposed camera device that provides view-invariant images physically, and segment hand region using a Bayesian rule based on adaptive histograms. We construct HSV histograms from RGB histograms, and update HSV histograms using hand region information from a current image. We also propose a user adaptation method by which hand models gradually approach user-dependent models from user-independent models as the user uses the system. The proposed method was evaluated using 16 Korean manual alphabet, and we obtained increases of 27.91% in recognition success rate.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.10
• /
• pp.1920-1926
• /
• 2006

With social interest, there hie been a lot of research on the Service Robot but now we are faced with the limitation of single platform. The alternative plan is the Ubiquitous-based Service Robot connected with a Ubiquitous network to overcome this limitation. Systems using RFID(Radio frequency Identification) and supersonic waves appeared for functions such as recognition of surroundings through Ubiquitous Sensor Networks. This was applied to the real robot and we have got good results. However, this has several limitations to applying to low power-based Sensor Network For example, if RFID uses a passive Sensor, the rate of recognition with the distance is limited. In case of supersonic waves, high power is required to drive them. Therefore, we intend to develop RSSI position recognition system on the basis of embodying a Sensor Network Module in this thesis. This RSSI position recognition system only measures RSSI of signals from each sensor nod. then converts them into distances and calculates the position. As a result, we can still use low power-based Sensor Network and overcome the limitation according to distance as planning Ad-Hoc Network.

• Journal of Korean Ophthalmic Optics Society
• /
• v.12 no.3
• /
• pp.89-91
• /
• 2007

Color vision test was conducted to elementary school students at age of 9 to 13, with total subject number of 598 which live in Gwang Ju area. 325 (54.3%) boys and 273 (45.7%) girls were subjected using Hahn Color Vision test to find out color recognition problems. 1. Ratios of color vision abnomality were 6.25% in 9 year old students, 9.2% in 10 year old students, 8.4% in 12 year old students, 7.8% in 13 year old students, which means 7.9% of the total 598 subjects had color recognition matters. 2. Red-Green dyschromatopsia was 7.8% of the total 598 subjects which includes most of subjects. None of them had green-yellow recognition problem. Full dyschromatopsia had frequency of 0.2%. 3. 10.7% of boys had color vision abnormality, while 10.7% of girls had color vision abnormality, which means that boys have color recognition problems with higher rate than girls.

• Tunnel and Underground Space
• /
• v.26 no.4
• /
• pp.253-265
• /
• 2016

In this study, travel time data collection of mine equipments was conducted in an underground mine using a reverse Radio Frequency IDentification (RFID) system. In the reverse RFID system, RFID readers and antennas are mounted on mine equipments, and RFID tags are attached to the underground mine gallery. Indoor experiments were performed to analyze how RFID reader transmission power levels affect tag readable area and tag recognition rates. The results showed that travel time measurement become precise when the reader transmission power was reduced, however tag recognition rates were reduced. The field experiments indicated that setting the reader transmission power to 28 dBm maintained the tag recognition rate while minimizing the tracking location error. In addition, the results revealed that the reverse RFID system can be used successfully in an underground mine to collect the travel time data of haulage trucks.

• Journal of KIISE:Software and Applications
• /
• v.35 no.4
• /
• pp.265-279
• /
• 2008

The idea of using hand gestures for human-computer interaction is not new and has been studied intensively during the last dorado with a significant amount of qualitative progress that, however, has been short of our expectations. This paper describes a dynamic Bayesian network or DBN based approach to both two-hand gestures and one-hand gestures. Unlike wired glove-based approaches, the success of camera-based methods depends greatly on the image processing and feature extraction results. So the proposed method of DBN-based inference is preceded by fail-safe steps of skin extraction and modeling, and motion tracking. Then a new gesture recognition model for a set of both one-hand and two-hand gestures is proposed based on the dynamic Bayesian network framework which makes it easy to represent the relationship among features and incorporate new information to a model. In an experiment with ten isolated gestures, we obtained the recognition rate upwards of 99.59% with cross validation. The proposed model and the related approach are believed to have a strong potential for successful applications to other related problems such as sign languages.

• Journal of KIISE:Software and Applications
• /
• v.37 no.9
• /
• pp.706-711
• /
• 2010

In the applications of a human speech interface, reducing the error rate in recognition is the one of the main research issues. Many previous studies attempted to correct errors using post-processing, which is dependent on a manually constructed corpus and correction patterns. We propose an automatically learnable post-processing method that is independent of the characteristics of both the domain and the speech recognizer. We divide the entire post-processing task into two steps: error detection and error correction. We consider the error detection step as a classification problem for which we apply the conditional random fields (CRFs) classifier. Furthermore, we apply transformation-based learning (TBL) to the error correction step. Our experimental results indicate that the proposed method corrects a speech recognizer's insertion, deletion, and substitution errors by 25.85%, 3.57%, and 7.42%, respectively.