• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1140-1145
• /
• 2003

Image normalization is one of the important areas in pattern recognition. Also, log-polar images are useful in the sense that their image data size is reduced dramatically comparing with conventional images and it is possible to develop faster pattern recognition algorithms. Especially, the log-polar image is very similar with the structure of human eyes. However, there are almost no researches on pattern recognition using the log-polar images while a number of researches on visual tracking have been executed. We propose an image normalization technique of log-polar images using momentums applicable for affine-invariant pattern recognition. We handle basic distortions of an image including translation, rotation, scaling, and skew of a log-polar image. The algorithm is experimented in a PC-based real-time vision system successfully.

• The Journal of the Acoustical Society of Korea
• /
• 제23권1E호
• /
• pp.10-15
• /
• 2004

In performing speech conversion from a source speaker to a target speaker, it is important that the pitch contour of the source speakers utterance be converted into that of the target speaker, because pitch contour of a speech utterance plays an important role in expressing speaker's individuality and meaning of the utterance. This paper describes statistical algorithms of pitch contour conversion for Korean language. Pitch contour conversions are investigated at two 1 evels of prosodic phrases: intonational phrase and accentual phrase. The basic algorithm is a Gaussian normalization [7] in intonational phrase. The first presented algorithm is combined with a declination-line of pitch contour in an intonational phrase. The second one is Gaussian normalization within accentual phrases to compensate for local pitch variations. Experimental results show that the algorithm of Gaussian normalization within accentual phrases is significantly more accurate than the other two algorithms in intonational phrase.

• 한국통신학회논문지
• /
• 제21권5호
• /
• pp.1345-1359
• /
• 1996

This paper presents a floating point arithmetic unit (FPAU) for supescalar microprocessor that executes fifteen operations such as addition, subtraction, data format converting, and compare operation using two pipelined arithmetic paths and new rounding and normalization scheme. By using two pipelined arithmetic paths, each aritchmetic operation can be assigned into appropriate arithmetic path which high speed operation is possible. The proposed normalization an rouding scheme enables the FPAU to execute roundig operation in parallel with normalization and to reduce timing delay of post-normalization. And by predicting leading one position of results using input operands, leading one detection(LOD) operation to normalize results in the conventional arithmetic unit can be eliminated. Because the FPAU can execuate fifteen single-precision or double-precision floating-point arithmetic operations through three-stage pipelined datapath and support IEEE standard 754, it has appropriate structure which can be ingegrated into superscalar microprocessor.

• 음성과학
• /
• 제13권1호
• /
• pp.129-139
• /
• 2006

In this paper, we propose two effective energy feature normalization methods for robust speech recognition in noisy environments. In the first method, we estimate the noise energy and remove it from the noisy speech energy. In the second method, we propose a modified algorithm for the Log-energy Dynamic Range Normalization (ERN) method. In the ERN method, the log energy of the training data in a clean environment is transformed into the log energy in noisy environments. If the minimum log energy of the test data is outside of a pre-defined range, the log energy of the test data is also transformed. Since the ERN method has several weaknesses, we propose a modified transform scheme designed to reduce the residual mismatch that it produces. In the evaluation conducted on the Aurora2.0 database, we obtained a significant performance improvement.

• The Journal of the Acoustical Society of Korea
• /
• 제16권3E호
• /
• pp.14-18
• /
• 1997

One fo the major problems in speech recognition is the mismatch between training and testing environments. Recently, SNR normalization technique, which normalizes the dynamic range of frequency channels in mel-scaled filterbank, was proposed[1]. While it showed improved robustness against additive noise, it requires a reliable speech detection mechanism and several adaptation parameters to be optimized. In this paper, we propose a modified SNR normalization technique. In this technique, we take simply the maximum of filterbank output and predetermined masking constant for each frequency band. According to the speaker-independent isolated word recognition in car noise environments, proposed modification yields better recognition performance that the original SNR normalization method, with rather reduced complexity.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2013년도 춘계 학술논문 발표대회
• /
• pp.142-143
• /
• 2013

Green building certifications and environmental assessments are extensively implemented and studied to decrease the environmental impact during the life cycle of buildings. However, most of them are not appropriate to assess the environmental performance during the construction phase due to the difference of environmental factors. To develop an environmental index of construction projects, normalization should be conducted to compare the relative impact of each factor. As a first step, this study deduced normalization references of 4 environmental factors : noise, waste, greenhouse gas, and dust.

• 스마트미디어저널
• /
• 제8권4호
• /
• pp.64-71
• /
• 2019

The performance of an OMR (Optical Music Recognition) system is usually determined by the characterizing features of the input music score images. Low resolution is one of the main factors leading to degraded image quality. In this paper, we handle the low-resolution problem using the super-resolution technique. We propose the use of a deep neural network with instance normalization to improve the quality of music score images. We apply instance normalization which has proven to be beneficial in single image enhancement. It works better than batch normalization, which shows the effectiveness of shifting the mean and variance of deep features at the instance level. The proposed method provides an end-to-end mapping technique between the high and low-resolution images respectively. New images are then created, in which the resolution is four times higher than the resolution of the original images. Our model has been evaluated with the dataset "DeepScores" and shows that it outperforms other existing methods.

• 한국멀티미디어학회논문지
• /
• 제25권4호
• /
• pp.568-574
• /
• 2022

In this paper, direction normalization and CNN deep learning are used to develop a more reliable license plate recognition system. The existing license plate recognition system consists of three main modules: license plate detection module, character segmentation module, and character recognition module. The proposed system minimizes recognition error by adding a direction normalization module when a detected license plate is inclined. Experimental results show the superiority of the proposed method in comparison to the previous system.

• Communications for Statistical Applications and Methods
• /
• 제31권1호
• /
• pp.105-127
• /
• 2024

We propose recurrent neural network (RNN) methods for forecasting realized volatility (RV). The data are RVs of ten major stock price indices, four from the US, and six from the EU. Forecasts are made for relative ratio of adjacent RVs instead of the RV itself in order to avoid the out-of-scale issue. Forecasts of RV ratios distribution are first constructed from which those of RVs are computed which are shown to be better than forecasts constructed directly from RV. The apparent asymmetry of RV ratio is addressed by the Piecewise Min-max (PM) normalization. The serial dependence of the ratio data renders us to consider two architectures, long short-term memory (LSTM) and gated recurrent unit (GRU). The hyperparameters of LSTM and GRU are tuned by the nested cross validation. The RNN forecast with the PM normalization and ratio transformation is shown to outperform other forecasts by other RNN models and by benchmarking models of the AR model, the support vector machine (SVM), the deep neural network (DNN), and the convolutional neural network (CNN).

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2011년도 추계학술대회
• /
• pp.1-2
• /
• 2011