• Journal of The Korean Association of Information Education
• /
• v.15 no.3
• /
• pp.517-524
• /
• 2011

This paper presents a fast blind deconvolution method that produces a deblurring result from a single image in only a few seconds. The high speed of our method is enabled by considering the Discrete Fourier Transform (DFT), and its relation to filtering and convolution, and fast computation of Moore-Penrose inverse matrix. How can we predict the behavior of an arbitrary filter, or even more to the point design a filter to achieve certain specifications. The idea is to study the frequency response of the filter. This concept leads to an useful convolution formula. A Matlab implementation of our method usually takes less than one minute to deblur an image of moderate size, while the deblurring quality is comparable.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.359-366
• /
• 2022

In this paper, we present the Korean menu-ordering Sentence Text-to-Speech (TTS) system using conformer-based FastSpeech2. Conformer is the convolution-augmented transformer, which was originally proposed in Speech Recognition. Combining two different structures, the Conformer extracts better local and global features. It comprises two half Feed Forward module at the front and the end, sandwiching the Multi-Head Self-Attention module and Convolution module. We introduce the Conformer in Korean TTS, as we know it works well in Korean Speech Recognition. For comparison between transformer-based TTS model and Conformer-based one, we train FastSpeech2 and Conformer-based FastSpeech2. We collected a phoneme-balanced data set and used this for training our models. This corpus comprises not only general conversation, but also menu-ordering conversation consisting mainly of loanwords. This data set is the solution to the current Korean TTS model's degradation in loanwords. As a result of generating a synthesized sound using ParallelWave Gan, the Conformer-based FastSpeech2 achieved superior performance of MOS 4.04. We confirm that the model performance improved when the same structure was changed from transformer to Conformer in the Korean TTS.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.67 no.1
• /
• pp.42-46
• /
• 2018

In this paper, we propose fast object detection method of the cars by applying YOLOv2(You Only Look Once version 2) and UAVs (Unmanned Aerial Vehicles) while on the highway. We operated Darknet, OpenCV, CUDA and Deep Learning Server(SDX-4185) for our simulation environment. YOLOv2 is recently developed fast object detection algorithm that can detect various scale objects as fast speed. YOLOv2 convolution network algorithm allows to calculate probability by one pass evaluation and predicts location of each cars, because object detection process has simple single network. In our result, we could find cars on the highway area as fast speed and we could apply to the real time.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.4
• /
• pp.625-634
• /
• 2006

In this paper, an efficient and fast algorithm to reduce calculation amount of FIR(Finite Impulse Responses) filtering is proposed. Proposed algorithm enables arbitrary size of parallel processing, and their structures are also easily derived. Furthermore, it is shown that the number of multiplication/sample is remarkably reduced. For theoretical improvement, numbers of sub filters are compared with those of conventional algorithm. In addition to the theoretical improvement, it is shown that number of element for hardwired implementation are reduced comparison to those of the conventional algorithm.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.6
• /
• pp.187-194
• /
• 2005

In this paper, an efficient and fast algerian to reduce calculation amount of FIR(Finite Impulse Responses) filtering is proposed. Proposed algorithm enables arbitrary size of parallel processing, and their structures are also easily derived. Furthermore, it is shown that the number of multiplication/sample is reduced, and number of instructions using MAC(Multiplication and Accumulation) processor are also reduced. For theoretical improvement numbers of sub filters are compared with those of conventional algorithm. In addition to the theoretical improvement, it is shown that number of element for hardwired implementation are reduced comparison to those of the conventional algorithm.

• Journal of Korea Multimedia Society
• /
• v.23 no.6
• /
• pp.756-764
• /
• 2020

A typical algorithm used for image analysis is the Convolutional Neural Network(CNN). R-CNN, Fast R-CNN, Faster R-CNN, etc. have been studied to improve the performance of the CNN, but they essentially require large amounts of data and high algorithmic complexity., making them inappropriate for small and medium-sized services. Therefore, in this paper, the image label prediction algorithm based on CNN with collaborative layer with low complexity, high accuracy, and small amount of data was proposed. The proposed algorithm was designed to replace the part of the neural network that is performed to predict the final label in the existing deep learning algorithm by implementing collaborative filtering as a layer. It is expected that the proposed algorithm can contribute greatly to small and medium-sized content services that is unsuitable to apply the existing deep learning algorithm with high complexity and high server cost.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.263-264
• /
• 2006

In this paper, an efficient and fast algorithm to reduce calculation amount of FIR(Finite Impulse Responses) filtering is proposed. Proposed algorithm enables arbitrary size of parallel processing, and their structures are also easily derived. Furthermore, it is shown that the number of multiplication/sample is reduced, and number of instructions using MAC(Multiplication and Accumulation) processor are also reduced. For theoretical improvement, numbers of sub filters are compared with those of conventional algorithm. In addition to the theoretical improvement, it is shown that number of element for hardwired implementation are reduced comparison to those of the conventional algorithm.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.15 no.10 s.89
• /
• pp.977-982
• /
• 2004

In this paper, a dispersive anisotropic perfectly matched layer(APML) is proposed using piecewise linear recursive convolution(PLRC) for finite difference time domain(FDTD) methods. This proposed APML can be utilized for the analysis of a nonlinear dispersive medium as absorbing boundary condition(ABC). The formulation is simple modification to the original AMPL and can be easily implemented. Also it has some advantages of the PLRC approach-fast speed, low memory cost, and easy formulation of multiple pole susceptibility. We applied this APML to 2-D propagation problems in dispersive media such as Debye and Lorentz media The results showed good absorption at boundaries.

• ETRI Journal
• /
• v.4 no.3
• /
• pp.18-29
• /
• 1982

In a block adaptive filtering procedure, the filter coefficients are adjusted once per each output block while maintaining performance comparable to that of widely used LMS adaptive filtering in which the filter coefficients are adjusted once per each output data sample. An efficient implementation of block adaptive filter is possible by means of discrete transform technique which has cyclic convolution property and fast algorithms. In this paper, the block adaptive filtering using Fermat Number Transform (FNT) is investigated to exploit the computational efficiency and less quantization effect on the performance compared with finite precision FFT realization. And this has been verified by computer simulation for several applications including adaptive channel equalizer and system identification.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.7
• /
• pp.865-870
• /
• 2018

A machine vision based industrial inspection includes defects detection and classification. Fast inspection is a fundamental problem for many applications of real-time vision systems. It requires little computation time and localizing defects robustly with high accuracy. Deep learning technique have been known not to be suitable for real-time applications. Recently a couple of fast region-based CNN algorithms for object detection are introduced, such as Faster R-CNN, and YOLOv2. We apply these methods for an industrial inspection problem. Three CNN based detection algorithms, VOV based CNN, Faster R-CNN, and YOLOv2, are experimented for defect detection on metal surface. The results for inspection time and various performance indices are compared and analysed.