• Journal of Korea Multimedia Society
• /
• v.10 no.2
• /
• pp.179-186
• /
• 2007

This paper proposes a novel method for face detection method using Zernike moments. To detect the faces in an image, local regions in multiscale sliding windows are classified into face and non-face by a neural network, and input features of the neural network consist of Zernike moments. Feature dimension is reduced as the reconstruction capability of orthogonal moment. In addition, because the magnitude of Zernike moment is invariant to rotation, a tilted human face can be detected. Even so the detection rate of the proposed method about head on face is less than experiments using intensity features, the result of our method about rotated faces is more robust. If the additional compensation and features are utilized, the proposed scheme may be best suited for the later stage of classification.

• Journal of Korea Society of Industrial Information Systems
• /
• v.7 no.3
• /
• pp.23-31
• /
• 2002

In this paper we propose a new feature vector for recognition of the facial expression based on Gibbs distributions which are well suited for representing the spatial continuity. The extracted feature vectors are invariant under translation rotation, and scale of an facial expression imege. The Algorithm for recognition of a facial expression contains two parts： the extraction of feature vector and the recognition process. The extraction of feature vector are comprised of modified 2-D conditional moments based on estimated Gibbs distribution for an facial image. In the facial expression recognition phase, we use discrete left-right HMM which is widely used in pattern recognition. In order to evaluate the performance of the proposed scheme, experiments for recognition of four universal expression (anger, fear, happiness, surprise) was conducted with facial image sequences on Workstation. Experiment results reveal that the proposed scheme has high recognition rate over 95%.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2003.10a
• /
• pp.164-169
• /
• 2003

The purpose of this study is to develop a practical image inspect ion system that could recognize it correctly, endowing flexibility to the productive field, although the same object for work will be changed in the size and rotated. In this experiment, it selected a fighter, rotating the direction from 30$^{\circ}$ to 45 simultaneously while changing the size from 1/4 to 1/16, as an object inspection without using another hardware for exclusive image processing. The invariant moments, Hu has suggested, was used as feature vector moment descriptor. As a result of the experiment, the image inspect ion system developed from this research was operated in real-time regardless of the chance of size and rotation for the object inspection, and it maintained the correspondent rates steadily above from 94％ to 96％. Accordingly, it is considered as the flexibility can be considerably endowed to the factory automat ion when the image inspect ion system developed from this research is applied to the product ive field.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.10 no.5
• /
• pp.265-272
• /
• 2015

This paper presents an improved feature extraction method to achieve a good performance in the detection of splicing forged images. Strong edges caused by the image splicing destroy the statistical dependencies between parent and child subbands in the wavelet domain. We analyze the co-occurrence probability matrix of parent and child subbands in the wavelet domain, and calculate the statistical moments from two-dimensional characteristic function of the co-occurrence matrix. The extracted features are used as the input of SVM classifier. Experimental results show that the proposed method obtains a good performance with a small number of features compared to the existing methods.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.76-85
• /
• 2011

In this paper, we propose a texture feature-based language identification using Gabor feature and wavelet-domain BDIP (block difference of inverse probabilities) and BVLC (block variance of local correlation coefficients) features. In the proposed method, Gabor and wavelet transforms are first applied to a test image. The wavelet subbands are next denoised by Donoho's soft-thresholding. The magnitude operator is then applied to the Gabor image and the BDIP and BVLC operators to the wavelet subbands. Moments for Gabor magnitude image and each subband of BDIP and BVLC are computed and fused into a feature vector. In classification, the WPCA (whitened principal component analysis) classifier, which is usually adopted in the face identification, searches the training feature vector most similar to the test feature vector. Experimental results show that the proposed method yields excellent language identification with rather low feature dimension for a document image DB.

• The Journal of the Acoustical Society of Korea
• /
• v.33 no.5
• /
• pp.282-290
• /
• 2014

Though there have been advances in the numerical analysis of the acoustic scattering by smooth objects, numerical analysis of the acoustic scattering by the objects that are partially exposed on the interface are still rare. In determining the backscattering amplitude by a partially buried cylinder on a seabed, reverberation by the interface changes the feature of the scattering form function. Current study adopted the Method of moments (MoM) to provide the numerical analysis on the backscattering amplitude for a partially buried cylinder on a flat interface. Suggested numerical analysis showed the good agreements with the measurements and the analytic solution obtained by the Kirchhoff approximation. Numerical analysis described in the current study can be applied to the backscattering problem of any shape of the objects partially imbedded on a seabed by combining the reverberation from the seabed with the scattered wave from the objects.

• Wind and Structures
• /
• v.18 no.6
• /
• pp.651-668
• /
• 2014

Wind tunnel tests are conducted to investigate the wind loads on vertical fixed-roof cylindrical tanks with a very low aspect ratio of 0.275, which is a typical ratio for practical tanks with a volume of $100,000m^3$. Both the flat-roof tank and the dome-roof tank are investigated in present study. The first four moments of the measured wind pressure, including the mean and normalized deviation pressure, kurtosis and skewness of the pressure signal, are obtained to study the feature of the wind loads. It is shown that the wind loads are closely related to the behavior of flow around the structure. For either tank, the mean wind pressures on the cylinder are positive on the windward area and negative on the sides and the wake area, and the mean wind pressures on the whole roof are negative. The roof configurations have no considerable influence on the mean pressure distributions of cylindrical wall in general. Highly non-Gaussian feature is found in either tank. Conditional sampling technique, envelope method, and the proper orthogonal decomposition (POD) analysis are employed to investigate the characteristics of wind loads on the cylinder in more detail. It is shown that the patterns of wind pressure obtained from conditional sampling are similar to the mean pressure patterns.An instantaneous pressure coefficient can present a wide range from the maximum value to the minimum value. The quasi-steady assumption is not valid for structures considered in this paper according to the POD analysis.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.14 no.2
• /
• pp.119-127
• /
• 2004

Butterfly valves are popularly used in service in the industrial and water works pipeline systems with large diameter because of its lightweight, simple structure and the rapidity of its manipulation. Sometimes cavitation can occur. resulting in noise, vibration and rapid deterioration of the valve trim, and do not allow further operation. Thus, the monitoring of cavitation is of economic interest and is very importance in industry. This paper proposes a condition monitoring scheme using statistical feature evaluation and support vector machine (SVM) to detect the cavitation conditions of butterfly valve which used as a flow control valve at the pumping stations. The stationary features of vibration signals are extracted from statistical moments. The SVMs are trained, and then classify normal and cavitation conditions of control valves. The SVMs with the reorganized feature vectors can distinguish the class of the untrained and untested data. The classification validity of this method is examined by various signals that are acquired from butterfly valves in the pumping stations and compared the classification success rate with those of self-organizing feature map neural network.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.6
• /
• pp.1636-1645
• /
• 1996

In this paper we proposed a new scheme for conditional two dimensional (2-D)moment-based classification of patterns on the basis of Gibbs random fields which are will suited for representing spatial continuity that is the characteristic of the most images. This implementation contains two parts: feature extraction and pattern classification. First of all, we extract feature vector which consists of conditional 2-D moments on the basis of estimated Gibbs parameter. Note that the extracted feature vectors are invariant under translation, rotation, size of patterns the corresponding template pattern. In order to evaluate the performance of the proposed scheme, classification experiments with training document sets of characters have been carried out on 486 66Mhz PC. Experiments reveal that the proposed scheme has high classification rate over 94%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.10
• /
• pp.2409-2416
• /
• 2014

In this paper, an automatic recognition algorithm for linearly modulated signals like PSK, QAM under noncoherent asynchronous condition is proposed. Frequency, phase, and amplitude characteristics of digitally modulated signals are changed periodically. By using this characteristics, cyclic moments and higher order cumulants based features are utilized for the modulation recognition. Hierarchial decision tree method is used for high speed signal processing and totally 4 feature extraction parameters are used for modulation recognition. In the condition where the symbol number is 4,096, the recognition accuracy of the proposed algorithm is more than 95% at SNR 15dB. Also the proposed algorithm is effective to classify the signal which has carrier frequency and phase offset.