• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.1
• /
• pp.50-63
• /
• 1995

In this paper, we propose a face recognition method using a neuro-fuzzy algorithm. In the preprocessing step, we extract the face part from the background image by tracking face boundaries. Then based on the a priori knowledge of human faces we extract the features such as widths of eyes and mouth, and distances from eye to nose and nose to mouth. In the recognition step. We use a neuro-fuzzy algorithm that employs a fuzzy membership function and modified error backpropagation algorithm. The former absorbs the variation of feature values and the latter shows good learning efficiency. Computer simulation results with 20 persons show that the proposed method gives higher recognition rate than the conventional ones.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.4E
• /
• pp.21-27
• /
• 1996

In this paper, we propose a discriminative training algorithm for the stochastic segment model (SSM) in continuous speech recognition. As the SSM is usually trained by maximum likelihood estimation (MLE), a discriminative training algorithm is required to improve the recognition performance. Since the SSM does not assume the conditional independence of observation sequence as is done in hidden Markov models (HMMs), the search space for decoding an unknown input utterance is increased considerably. To reduce the computational complexity and starch space amount in an iterative training algorithm for discriminative SSMs, a hybrid architecture of SSMs and HMMs is programming using HMMs. Given the segment boundaries, the parameters of the SSM are discriminatively trained by the minimum error classification criterion based on a generalized probabilistic descent (GPD) method. With the discriminative training of the SSM, the word error rate is reduced by 17% compared with the MLE-trained SSM in speaker-independent continuous speech recognition.

• International Journal of Internet, Broadcasting and Communication
• /
• v.7 no.2
• /
• pp.51-55
• /
• 2015

This paper proposes an algorithm for risk situation recognition using facial expression. The proposed method recognitions the surprise and fear expression among human's various emotional expression for recognizing dangerous situation. The proposed method firstly extracts the facial region using Harr-like technique from input, detects eye region and lip region from the extracted face. And then, the method applies Uniform LBP to each region, detects facial expression, and recognizes dangerous situation. The proposed method is evaluated for MUCT database image and web cam input. The proposed method produces good results of facial expression and discriminates dangerous situation well and the average recognition rate is 91.05%.

• International journal of advanced smart convergence
• /
• v.9 no.3
• /
• pp.85-96
• /
• 2020

It is important to extract salient object image and to solve the invariance problem for image recognition. In this paper we propose a new hybrid algorithm for invariance and improved classification performance in image recognition, whose algorithm is combined by FT(Frequency-tuned Salient Region Detection) algorithm, Guided filter, Zernike moments, and a simple artificial neural network (Multi-layer Perceptron). The conventional FT algorithm is used to extract initial salient object image, the guided filtering to preserve edge details, Zernike moments to solve invariance problem, and a classification to recognize the extracted image. For guided filtering, guided filter is used, and Multi-layer Perceptron which is a simple artificial neural networks is introduced for classification. Experimental results show that this algorithm can achieve a superior performance in the process of extracting salient object image and invariant moment feature. And the results show that the algorithm can also classifies the extracted object image with improved recognition rate.

• Speech Sciences
• /
• v.7 no.2
• /
• pp.235-244
• /
• 2000

This paper was focused on realizing the text-independent speaker recognizer using the VQ and GMM algorithm and studying the characteristics of the speaker recognizers that adopt these two algorithms. Because it was difficult ascertain the effect two algorithms have on the speaker recognizer theoretically, we performed the recognition experiments using various parameters and, as the result of the experiments, we could show that GMM algorithm had better recognition performance than VQ algorithm as following. The GMM showed better performance with small training data, and it also showed just a little difference of recognition rate as the kind of feature vectors and the length of input data vary. The GMM showed good recognition performance than the VQ on the whole.

• Speech Sciences
• /
• v.14 no.4
• /
• pp.131-144
• /
• 2007

In an effort to improve the performance of mel frequency cepstral coefficients (MFCC), we investigate the effects of varying the parameters for the filter banks and their associated windows on speech recognition rates. Specifically, the mel and bark scales are combined with various types of filter bank windows. Comparison and evaluation of the suggested methods are performed by two independent ways of speech recognition and the Fisher discriminant objective function. It is shown that the Hanning window based on the bark scale yields 28.1% relative performance improvements over the triangular window with the mel scale in speech recognition error rate. Further work on incorporating PCA and/or LDA would be desirable as a postprocessor to MFCC extraction.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 1998.10a
• /
• pp.137-141
• /
• 1998

Todays the efficient management of container has not been realized in container terminal, because of the excessive quantity of container transported and manual system. For the efficient and automated management of container in terminal, the automated container identifier recognition system in terminal is a significant problem. However, the identifier recognition rate is decreased owing to the difficulty of image preprocessing caused the refraction of container surface, the change of weather and the damaged identifier characters. Therefore, this paper proposes more accurate system for container identifier recognition as suggestion of Line-Scan Proper Region Detect for stronger preprocessing against external noisy element and Moment Back-Propagation Neural Network to recognize identifier.

• KIEE International Transactions on Electrophysics and Applications
• /
• v.5C no.2
• /
• pp.63-66
• /
• 2005

This paper describes analysis and pattern recognition techniques for Partial Discharge(PD) signals in Gas Insulated Switchgears (GIS). Detection of PD signals is one of the most important factors in the predictive maintenance of GIS. One of the methods of detection is electro magnetic wave detection within the Ultra High Frequency (UHF) band (300MHz $\~$ 3GHz). In this paper, PD activity simulation is generated using three types of artificial defects, which were detected by a UHF PD sensor installed in the GIS. The detected PD signals were performed on three-dimensional phi-q-n analysis. Finally, parameters were calculated and an Artificial Neural Network (ANN) was applied for PD pattern recognition. As a result, it was possible to discriminate and classify the defects.

• Journal of International Society for Simulation Surgery
• /
• v.3 no.2
• /
• pp.46-48
• /
• 2016

Purpose In face reocognition area, estimating occlusion in face images is on the rise. In this paper, we propose a new face recognition algorithm based on dual sparse representation to solve this problem. Method Each face image is partitioned into several pieces and sparse representation is implemented in each part. Then, some parts that have large sparse concentration index are combined and sparse representation is performed one more time. Each test sample is classified by using the final sparse coefficient where correlation between the test sample and training sample is applied. Results The recognition rate of the proposed algorithm is higher than that of the basic sparse representation classification. Conclusion The proposed method can be applied in real life which needs to identify someone exactly whether the person disguises his face or not.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.8
• /
• pp.756-760
• /
• 2010

In this paper, a new method to recognize various motions of fighting with an aid of HMM is proposed. There are four kinds of fighting motion such as hook, jab, uppercut, and straight as the fighting motion. The motion graph is generalized to define each motion in motion data and the new 3D-chain code is used to convert motion data to motion graphs. The recognition experiment has been performed with HMM algorithm on motion graphs. The motion data is captured by a motion capture system developed in this study and by five actors. Experimental results are given with relatively high recognition rate of at least 85%.