• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.2
• /
• pp.522-539
• /
• 2021

In order to solve the problems of the existing audio fingerprint method when extracting audio fingerprints from long speech segments, such as too large fingerprint dimension, poor robustness, and low retrieval accuracy and efficiency, a robust audio fingerprint retrieval method based on feature dimension reduction and feature combination is proposed. Firstly, the Mel-frequency cepstral coefficient (MFCC) and linear prediction cepstrum coefficient (LPCC) of the original speech are extracted respectively, and the MFCC feature matrix and LPCC feature matrix are combined. Secondly, the feature dimension reduction method based on information entropy is used for column dimension reduction, and the feature matrix after dimension reduction is used for row dimension reduction based on energy feature dimension reduction method. Finally, the audio fingerprint is constructed by using the feature combination matrix after dimension reduction. When speech's user retrieval, the normalized Hamming distance algorithm is used for matching retrieval. Experiment results show that the proposed method has smaller audio fingerprint dimension and better robustness for long speech segments, and has higher retrieval efficiency while maintaining a higher recall rate and precision rate.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.4
• /
• pp.1648-1672
• /
• 2020

There are several types of image registration in the sense of stitching separated images that overlap each other. One of these is feature-based registration by a common feature descriptor. In this study, we generate a mosaic of images using feature-based registration for drone aerial images. As a feature descriptor, we apply the scale-invariant feature transform descriptor. In order to investigate the authenticity of the feature points and to have the mapping function, we employ the sample consensus method; we consider the sensed image's inherent characteristic such as the geometric congruence between the feature points of the images to propose a novel hypothesis estimation of the mapping function of the stitching via some optimally chosen initial candidate inliers in the sample consensus method. Based on the experimental results, we show the efficiency of the proposed method compared with benchmark methodologies of random sampling consensus method (RANSAC); the well-ordering property defined in the context and the extensive stitching examples have supported the utility. Moreover, the sample consensus scheme proposed in this study is uncomplicated and robust, and some fatal miss stitching by RANSAC is remarkably reduced in the measure of the pixel difference.

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.643-646
• /
• 1999

In this paper, we propose a feature extraction method based on Bhattacharyya distance for multiclass problems. The Bhattacharyya distance provides a valuable information in determining the effectiveness of a feature set and has been used as separability measure for feature selection. Recently, a feature extraction algorithm hat been proposed for two normally distributed classes based on Bhattacharyya distance. In this paper, we propose to expand the previous approach to multiclass cases. Experiment results show that the proposed method compares favorably with the conventional methods.

• Journal of information and communication convergence engineering
• /
• v.21 no.1
• /
• pp.82-89
• /
• 2023

Various machine-learning models may yield high predictive power for massive time series for time series prediction. However, these models are prone to instability in terms of computational cost because of the high dimensionality of the feature space and nonoptimized hyperparameter settings. Considering the potential risk that model training with a high-dimensional feature set can be time-consuming, we evaluate a feature-importance-based feature selection method to derive a tradeoff between predictive power and computational cost for time series prediction. We used two machine learning techniques for performance evaluation to generate prediction models from a retail sales dataset. First, we ranked the features using impurity- and Local Interpretable Model-agnostic Explanations (LIME) -based feature importance measures in the prediction models. Then, the recursive feature elimination method was applied to eliminate unimportant features sequentially. Consequently, we obtained a subset of features that could lead to reduced model training time while preserving acceptable model performance.

• Fisheries and Aquatic Sciences
• /
• v.4 no.1
• /
• pp.1-9
• /
• 2001

This paper describes a procedure extracting feature vector of a target cell more precisely in the case of identifying specified cell. The classification of object type is based on feature vector such as area, complexity, centroid, rotation angle, effective diameter, perimeter, width and height of the object So, the feature vector plays very important role in classifying objects. Because the feature vectors is affected by noises and holes, it is necessary to remove noises contaminated in original image to get feature vector extraction exactly. In this paper, we propose the following method to do to get feature vector extraction exactly. First, by Otsu's optimal threshold selection method and morphological filters such as cleaning, filling and opening filters, we separate objects from background an get rid of isolated particles. After the labeling step by 4-adjacent neighborhood, the labeled image is filtered by the area filter. From this area-filtered image, feature vector such as area, complexity, centroid, rotation angle, effective diameter, the perimeter based on chain code and the width and height based on rotation matrix are extracted. To prove the effectiveness, the proposed method is applied for yeast Zygosaccharomyces rouxn. It is also shown that the experimental results from the proposed method is more efficient in measuring feature vectors than from only Otsu's optimal threshold detection method.

• MALSORI
• /
• no.67
• /
• pp.167-180
• /
• 2008

This paper describes a novel spectral envelope conversion method based on Gaussian mixture model (GMM). The core of this paper is rearranging source feature vectors in input space to the transformed feature vectors in feature space for the better modeling of GMM of source and target features. The quality of statistical modeling is dependent on the distribution and the dimension of data. The proposed method transforms both of the distribution and dimension of data and gives us the chance to model the same data with different configuration. Because the converted feature vectors should be on the input space, only source feature vectors are rearranged in the feature space and target feature vectors remain unchanged for the joint pdf of source and target features using KPCA. The experimental result shows that the proposed method outperforms the conventional GMM-based conversion method in various training environment.

• MALSORI
• /
• no.63
• /
• pp.125-137
• /
• 2007

Recently, many techniques have been proposed to improve the noise robustness for speaker verification. In this paper, we consider the feature recombination technique in multi-band approach. In the conventional feature recombination for speaker verification, to compute the likelihoods of speaker models or universal background model, whole feature components are used. This computation method is not effective in a view point of multi-band approach. To deal with non-effectiveness of the conventional feature recombination technique, we introduce a subband likelihood computation, and propose a modified feature recombination using subband likelihoods. In decision step of speaker verification system in noise environments, a few very low likelihood scores of a speaker model or universal background model cause speaker verification system to make wrong decision. To overcome this problem, a reliable feature selection method is proposed. The low likelihood scores of unreliable feature are substituted by likelihood scores of the adaptive noise model. In here, this adaptive noise model is estimated by maximum a posteriori adaptation technique using noise features directly obtained from noisy test speech. The proposed method using subband-based reliable feature selection obtains better performance than conventional feature recombination system. The error reduction rate is more than 31 % compared with the feature recombination-based speaker verification system.

• Journal of electromagnetic engineering and science
• /
• v.18 no.3
• /
• pp.206-211
• /
• 2018

In this paper, we proposed a two-level feature vector fusion technique to improve the performance of target classification. The proposed method combines feature vectors of the early-time region and late-time region in the first-level fusion. In the second-level fusion, we combine the monostatic and bistatic features obtained in the first level. The radar cross section (RCS) of the 3D full-scale model is obtained using the electromagnetic analysis tool FEKO, and then, the feature vector of the target is extracted from it. The feature vector based on the waveform structure is used as the feature vector of the early-time region, while the resonance frequency extracted using the evolutionary programming-based CLEAN algorithm is used as the feature vector of the late-time region. The study results show that the two-level fusion method is better than the one-level fusion method.

• Journal of Korea Multimedia Society
• /
• v.11 no.6
• /
• pp.777-786
• /
• 2008

Human face avatar is important information in nowadays, such as describing real people in virtual world. In this paper, we have presented a face avatar creation and warping algorithm by using face feature analysis method, in order to detect face feature, we utilized local mean method based on facial feature appearance and face geometric information. Then detect facial candidates by using it's character in $YC_bC_r$ color space. Meanwhile, we also defined the rules which are based on face geometric information to limit searching range. For analyzing face feature, we used face feature points to describe their feature, and analyzed geometry relationship of these feature points to create the face avatar. Then we have carried out simulation on PC and embed mobile device such as PDA and mobile phone to evaluate efficiency of the proposed algorithm. From the simulation results, we can confirm that our proposed algorithm will have an outstanding performance and it's execution speed can also be acceptable.

• ETRI Journal
• /
• v.24 no.6
• /
• pp.469-472
• /
• 2002

Speaker adaptation techniques are generally used to reduce speaker differences in speech recognition. In this work, we focus on the features fitted to a linear regression-based speaker adaptation. These are obtained by feature transformation based on independent component analysis (ICA), and the feature transformation matrices are estimated from the training data and adaptation data. Since the adaptation data is not sufficient to reliably estimate the ICA-based feature transformation matrix, it is necessary to adjust the ICA-based feature transformation matrix estimated from a new speaker utterance. To cope with this problem, we propose a smoothing method through a linear interpolation between the speaker-independent (SI) feature transformation matrix and the speaker-dependent (SD) feature transformation matrix. From our experiments, we observed that the proposed method is more effective in the mismatched case. In the mismatched case, the adaptation performance is improved because the smoothed feature transformation matrix makes speaker adaptation using noisy speech more robust.