• The Journal of the Acoustical Society of Korea
• /
• v.21 no.7
• /
• pp.641-647
• /
• 2002

In this paper, we propose the reduction method of the number of parameters in the segmental-feature HMM using trend quantization method. The proposed method shares the trend information of the polynomial trajectories by quantization. The trajectory is obtained by the sequence of feature vectors of speech signals and can be divided by trend and location information. The trend indicates the variation of consequent frame features, while the location points to the positional difference of the trajectories. Since the trend occupies the large portion of SFHMM, if the trend is shared, the number of parameters maybe decreases. To exploit the proposed system the experiments are performed on TIMIT corpus. The experimental results show that the performance of the proposed system is roughly similar to that of previous system. Therefore, the proposed system can be considered one of parameter reduction method.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.1
• /
• pp.100-103
• /
• 1997

In this paper, we analyze the time delayed effect of speech feature. Here, the time delayed effect means that the current feature vector of speech is under the influence of the previous feature vectors. In this paper, we use a set of LPC driven cepstal coefficients and evaluate the time delayed effect of cepstrum with the performance of the speech recognition system. For the experiments, we used the speech database consisting of 22 words which uttered by 50 male speakers. The speech database uttered by 25 male speakers was used for training, and the other set was used for testing. The experimental results show that the time delayed effect is large in the lower orders of feature vector but small in the higher orders.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2036-2038
• /
• 2001

In this paper, we propose the neural network based emotion recognition method for intelligently recognizing the human's emotion using vision system. In the proposed method, human's emotion is divided into four emotion (surprise, anger, happiness, sadness). Also, we use R,G,B(red, green, blue) color image data and the gray image data to get the highly trust rate of feature point extraction. For this, we propose an algorithm to extract four feature points (eyebrow, eye, nose, mouth) from the face image acquired by the color CCD camera and find some feature vectors from those. And then we apply back-prapagation algorithm to the secondary feature vector(position and distance among the feature points). Finally, we show the practical application possibility of the proposed method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.2098-2114
• /
• 2021

Light intensity variation is one of the key factors which affect the accuracy of vehicle face re-identification, so in order to improve the robustness of vehicle face features to light intensity variation, a Nonnegative Matrix Factorization model with the constraint of image acquisition time difference is proposed. First, the original features vectors of all pairs of positive samples which are used for training are placed in two original feature matrices respectively, where the same columns of the two matrices represent the same vehicle; Then, the new features obtained after decomposition are divided into stable and variable features proportionally, where the constraints of intra-class similarity and inter-class difference are imposed on the stable feature, and the constraint of image acquisition time difference is imposed on the variable feature; At last, vehicle face matching is achieved through calculating the cosine distance of stable features. Experimental results show that the average False Reject Rate and the average False Accept Rate of the proposed algorithm can be reduced to 0.14 and 0.11 respectively on five different datasets, and even sometimes under the large difference of light intensities, the vehicle face image can be still recognized accurately, which verifies that the extracted features have good robustness to light variation.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.5
• /
• pp.69-78
• /
• 2005

It is crucial to compute the Euclidean distance between two vectors efficiently in high dimensional space for multimedia information retrieval. In this paper, we propose an effective method for approximating the Euclidean distance between two high-dimensional vectors. For this approximation, a previous method, which simply employs norms of two vectors, has been proposed. This method, however, ignores the angle between two vectors in approximation, and thus suffers from large approximation errors. Our method introduces an additional vector called a reference vector for estimating the angle between the two vectors, and approximates the Euclidean distance accurately by using the estimated angle. This makes the approximation errors reduced significantly compared with the previous method. Also, we formally prove that the value approximated by our method is always smaller than the actual Euclidean distance. This implies that our method does not incur any false dismissal in multimedia information retrieval. Finally, we verify the superiority of the proposed method via performance evaluation with extensive experiments.

• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.2
• /
• pp.7-14
• /
• 2002

This paper proposes a camera motion estimation technique using special relations of motion vectors of geometrically symmetrical triple points of two consecutive views of single camera. The proposed technique uses camera-induced motion vectors and their relations other than feature points and epioplar constraints. As contrast to the time consuming iterations or numerical methods in the calculation of E-matrix or F-matrix induced by epipolar constraints, the proposed technique calculates camera motion parameters such as panning, tilting, rolling, and zooming at once by applying the proposed linear equation sets to the motion vectors. And by devised background discriminants, it effectively reflects only the background region into the calculation of motion parameters, thus making the calculation more accurate and fast enough to accommodate MPEG-4 requirements. Experimental results on various types of sequences show the validity and the broad applicability of the proposed technique.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.2 s.308
• /
• pp.1-11
• /
• 2006

In this paper, we propose the novel video retrieval algorithm using non-parametric based motion classification in the shot-based video indexing structure. The proposed system firstly gets the key frame and motion information from each shot segmented by scene change detection method, and then extracts visual features and non-parametric based motion information from them. Finally, we construct real-time retrieval system supporting similarity comparison of these spatio-temporal features. After the normalized motion vector fields is created from MPEG compressed stream, the extraction of non-parametric based motion feature is effectively achieved by discretizing each normalized motion vectors into various angle bins, and considering a mean, a variance, and a direction of these bins. We use the edge-based spatial descriptor to extract the visual feature in key frames. Experimental evidence shows that our algorithm outperforms other video retrieval methods for image indexing and retrieval. To index the feature vectors, we use R*-tree structures.

• Journal of the Korean Society for information Management
• /
• v.22 no.3 s.57
• /
• pp.261-287
• /
• 2005

The purpose of this paper is to explore the ways to improve the performance of SVM (Support Vector Machines) text classifier using inter-document similarities. SVMs are powerful machine learning systems, which are considered as the state-of-the-art technique for automatic document classification. In this paper text categorization via SVMs approach based on feature representation with document vectors is suggested. In this approach, document vectors instead of index terms are used as features, and vector similarities instead of term weights are used as feature values. Experiments show that SVM classifier with document vector features can improve the document classification performance. For the sake of run-time efficiency, two methods are developed: One is to select document vector features, and the other is to use category centroid vector features instead. Experiments on these two methods show that we can get improved performance with small vector feature set than the performance of conventional methods with index term features.

• The Journal of the Korea Contents Association
• /
• v.8 no.1
• /
• pp.236-245
• /
• 2008

Robust face recognition under various illumination environments is very difficult and needs to be accomplished for successful commercialization. In this paper, we propose an efficient illumination preprocessing method for face recognition. illumination preprocessing algorithm based on anisotropic smoothing is well known to be effective among illumination normalization methods but deteriorates the intensity contrast of the original image, and incurs less sharp edges. The proposed method in this paper improves the previous anisotropic smoothing based illumination normalization method so that it increases the intensity contrast and enhances the edges while diminishing effects of illumination. Due to the result of these improvements, face images preprocessed by the proposed illumination preprocessing method becomes to have more distinctive feature vectors(Gabor feature vectors). Through experiments of face recognition using Gabor jet similarity, the effectiveness of the proposed illumination preprocessing method is verified.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.271-278
• /
• 2004

In this paper, we propose a content-based audio genre classification algorithm that automatically classifies the query audio into five genres such as Classic, Hiphop, Jazz, Rock, Speech using digital sign processing approach. From the 20 seconds query audio file, the audio signal is segmented into 23ms frame with non-overlapped hamming window and 54 dimensional feature vectors, including Spectral Centroid, Rolloff, Flux, LPC, MFCC, is extracted from each query audio. For the classification algorithm, k-NN, Gaussian, GMM classifier is used. In order to choose optimum features from the 54 dimension feature vectors, SFS(Sequential Forward Selection) method is applied to draw 10 dimension optimum features and these are used for the genre classification algorithm. From the experimental result, we can verify the superior performance of the proposed method that provides near 90% success rate for the genre classification which means 10%∼20% improvements over the previous methods. For the case of actual user system environment, feature vector is extracted from the random interval of the query audio and it shows overall 80% success rate except extreme cases of beginning and ending portion of the query audio file.