• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.1
• /
• pp.23-28
• /
• 2013

The process of a feature matching for two different spatial data sets is similar to the process of classification as a binary class such as matching or non-matching. In this paper, we calculated a threshold by applying an equal error rate (EER) which is widely used in biometrics that classification is a main topic into spatial data sets. In a process of discriminating what's a matching or what's not, a precision and a recall is changed and a trade-off appears between these indexes because the number of matching pairs is changed when a threshold is changed progressively. This trade-off point is EER, that is, threshold. To the result of applying this method into training data, a threshold is estimated at 0.802 of a value of shape similarity. By applying the estimated threshold into test data, F-measure that is a evaluation index of matching method is highly value, 0.940. Therefore we confirmed that an accurate threshold is calculated by EER without person intervention and this is appropriate to matching different spatial data sets.

• Journal of KIISE:Software and Applications
• /
• v.31 no.6
• /
• pp.808-816
• /
• 2004

This paper proposes the method of implementation of practical online face verification system based on multiple feature combination and a similarity space. The main issue in face verification is to deal with the variability in appearance. It seems difficult to solve this issue by using a single feature. Therefore, combination of mutually complementary features is necessary to cope with various changes in appearance. From this point of view, we describe the feature extraction approaches based on multiple principal component analysis and edge distribution. These features are projected on a new intra-person/extra-person similarity space that consists of several simple similarity measures, and are finally evaluated by a support vector machine. From the experiments on a realistic and large database, an equal error rate of 0.029 is achieved, which is a sufficiently practical level for many real- world applications.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.2
• /
• pp.137-142
• /
• 2020

Many studies based on I-vector have been conducted in a variety of environments, from text-dependent short-utterance to text-independent long-utterance. In this paper, we propose a speaker verification system employing a combination of I-vector with Probabilistic Linear Discriminant Analysis (PLDA) and speaker embedding of Long Short Term Memory (LSTM) with attention mechanism in far-field and noisy environments. The LSTM model's Equal Error Rate (EER) is 15.52 % and the Attention-LSTM model is 8.46 %, improving by 7.06 %. We show that the proposed method solves the problem of the existing extraction process which defines embedding as a heuristic. The EER of the I-vector/PLDA without combining is 6.18 % that shows the best performance. And combined with attention-LSTM based embedding is 2.57 % that is 3.61 % less than the baseline system, and which improves performance by 58.41 %.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.1
• /
• pp.42-47
• /
• 2003

This paper proposes the method to generate new test data using the sample shift of the start frame for SPRT(sequential probability ratio test) in speaker verification. The SPRT method is a effective algorithm that can reduce the test computational complexity. However, in making the decision procedure, SPRT can be executed on the assumption that the input samples are usually to be i.i.d. (Independent and Identically Distributed) samples from a probability density function (pdf), also it's not suitable method to apply for the short utterance. The proposed method can achieve SPRT regardless of the utterance length of the test data because it is method to generate the new test data through the sample shift of start frame. Also, the correlation property of data to be considered in the SPRT method can be effectively removed by employing the principal component analysis. Experimental results show that the proposed method increased the computational complexity of data for sample shift a little, but it has a good performance result more than a conventional method above the average 0.7% in EER (equal error rate).

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.447-453
• /
• 2020

In this paper, we propose a system to extract effective speaker representations from a speech signal using a deep learning method. Based on the fact that speech signal contains identity unrelated information such as text content, emotion, background noise, and so on, we perform a training such that the extracted features only represent speaker-related information but do not represent speaker-unrelated information. Specifically, we propose an auto-encoder based disentanglement method that outputs both speaker-related and speaker-unrelated embeddings using effective loss functions. To further improve the reconstruction performance in the decoding process, we also introduce a discriminator popularly used in Generative Adversarial Network (GAN) structure. Since improving the decoding capability is helpful for preserving speaker information and disentanglement, it results in the improvement of speaker verification performance. Experimental results demonstrate the effectiveness of our proposed method by improving Equal Error Rate (EER) on benchmark dataset, Voxceleb1.

• The Journal of the Acoustical Society of Korea
• /
• v.34 no.2
• /
• pp.171-176
• /
• 2015

We present a speaker verification method by extracting i-vectors based on dominant state information of Hidden Markov Model (HMM) - Universal Background Model (UBM). Ergodic HMM is used for estimating UBM so that various characteristic of individual speaker can be effectively classified. Unlike Gaussian Mixture Model(GMM)-UBM based speaker verification system, the proposed system obtains i-vectors corresponding to each HMM state. Among them, the i-vector for feature is selected by extracting it from the specific state containing dominant state information. Relevant experiments are conducted for validating the proposed system performance using the National Institute of Standards and Technology (NIST) 2008 Speaker Recognition Evaluation (SRE) database. As a result, 12 % improvement is attained in terms of equal error rate.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.3A
• /
• pp.198-204
• /
• 2011

Acoustic communication system is a transmission technology sending sound and data simultaneously. However, data signal can be audible in this system when data is transmitted with high transmission power. The more transmission power is reduced, the more distance that can transmit data is shortened. Therefore, the study that increase the transmission distance is needed. In this paper, we would like to increase transmission distance by adapting receive diversity in acoustic communication system. We measure received performance of both proposed system and Single Input Sing Output (SISO) system according to distance with same transmission power. When SISO satisfies Bit Error Rate (BER) of $7{\times}10^{-3}$ at about 2m, Selection Combining (SC) technique satisfies 2 meters, and Equal Gain Combining (EGC) technique satisfies 4 meters.

• Smart Media Journal
• /
• v.12 no.2
• /
• pp.9-14
• /
• 2023

In this paper, we proposed a face recognition network which attempts to use more facial features awhile using smaller number of training sets. When combining the neural network together for face recognition, we want to use networks that use different part of the facial features. However, the network training chooses randomly where these facial features are obtained. Other hand, the judgment basis of the network model can be expressed as a saliency map through gradCAM. Therefore, in this paper, we use gradCAM to visualize where the trained face recognition model has made a observations and recognition judgments. Thus, the network combination can be constructed based on the different facial features used. Using this approach, we trained a network for small face recognition problem. In an simple toy face recognition example, the recognition network used in this paper improves the accuracy by 1.79% and reduces the equal error rate (EER) by 0.01788 compared to the conventional approach.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.2
• /
• pp.150-158
• /
• 2022

This paper presents the results of a sea trial for very long range spread spectrum underwater acoustic communication conducted in the East Sea in September 2021. Signals were collected through 8 vertical sensors, and the range between the transmitter and receiver was about 160 km. 30 bps Multi-Code Spread Spectrum (MCSS) method and 100 bps Chirp Spread Spectrum method were used for the transmitting signal generation. The results show that when the channel coding technique was not used in a single channel, the uncoded bit error rate was high, but when the Equal Gain Combining (EGC) diversity technique was used after frame synchronization in each receiving channel, the uncoded bit error rate was reduced to 0.1 or less.

• Journal of Information Processing Systems
• /
• v.7 no.3
• /
• pp.425-434
• /
• 2011

The success of iris recognition depends mainly on two factors: image acquisition and an iris recognition algorithm. In this study, we present a system that considers both factors and focuses on the latter. The proposed algorithm aims to find out the most efficient wavelet family and its coefficients for encoding the iris template of the experiment samples. The algorithm implemented in software performs segmentation, normalization, feature encoding, data storage, and matching. By using the Haar and Biorthogonal wavelet families at various levels feature encoding is performed by decomposing the normalized iris image. The vertical coefficient is encoded into the iris template and is stored in the database. The performance of the system is evaluated by using the number of degrees of freedom, False Reject Rate (FRR), False Accept Rate (FAR), and Equal Error Rate (EER) and the metrics show that the proposed algorithm can be employed for an iris recognition system.