• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.10b
• /
• pp.1425-1428
• /
• 2000

본 논문에서는 빠르고 정확하게 기후를 예측, 분석하기 위해 웨이브렛 변환을 통해 Data의 특징을 추출하고 이를 신경망의 입력값으로 사용하는 기상예측시스템은 제안하였다. 또한 학습이 잘되지 않는 패턴에 대한 집중적인 학습을 수행할 수 있는 Epsilon Descending 학습방법을 사용하여 정확도를 상승시켰다. 예측실험결과 웨이브렛 변환을 데이터의 전처리 과정에 삽입한 제안 기상예측시스템이 기존의 신경망만을 통한 기상예측시스템에 비해 예측능력면에서 훨씬 더 우수함을 보였다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.5
• /
• pp.464-473
• /
• 2001

Since DCT algorithm divides an image into blocks uniformly in both the spatial domain and the frequency domain, it has a weak point that it can not reflect HVS(Human Visual System) efficiently To avoid this problem, we propose a new algorithm, which combines only the merits of DCT and wavelet transform. The proposed algorithm uses the high compaction efficiency of DCT, and applies wavelet transform mode to DCT coefficients, so that the algorithm can utilize interband and intraband correlations of wavelet simultaneously After that, the proposed algorithm quantizes each coefficient based on the characteristic of each coefficient's band. In terms of coding method, the quantized coefficients of important DCT coefficients have symmetrical distribution, the bigger that value Is, the smaller occurrence probability is. Using the characteristic, we propose a new still image coding algorithm of symmetric and bidirectional tree structure with simple algorithm and fast decoding time. Comparing the proposed method with JPEG, the proposed method yields better image quality both objectively and subjectively at the same bit rate.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.12B
• /
• pp.2369-2381
• /
• 1999

In this paper, we propose an iterative algorithm for reducing the blocking artifact in block transform-coded images by using a wavelet transform. In the proposed method, an image is considered as a set of one-dimensional horizontal and vertical signals and one-dimensional wavelet transform is utilized in which the mother wavelet is the first order derivative of a Gaussian like function. The blocking artifact is reduced by removing the blocking component, that causes the variance at the block boundary position in the first scale wavelet domain to be abnormally higher than those at the other positions, using a minimum mean square error (MMSE) filter in the wavelet domain. This filter minimizes the MSE between the ideal blocking component-free signal and the restored signal in the neighborhood of block boundaries in the wavelet domain. It also uses local variance in the wavelet domain for pixel adaptive processing. The filtering and the projection onto a convex set of quantization constraint are iteratively performed in alternating fashion. Experimental results show that the proposed method yields not only a PSNR improvement of about 0.56-1.07 dB, but also subjective quality nearly free of the blocking artifact and edge blur.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.12
• /
• pp.2313-2327
• /
• 1994

As the communication environment evolves, there is an increasing need for multiresolution image coding. To meet this need, the entrophy constratined vector quantizer(ECVQ) for coding of image pyramids by spline wavelet transform is introduced in this paper. This paper proposes a new scheme for image compression taking into account psychovisual feature both in the space and frequency domains : this proposed method involves two steps. First we use spline wavelet transform in order to obtain a set of biorthogonal subclasses of images ; the original image is decomposed at different scale using a pyramidal algorithm architecture. The decomposition is along the vertical and horizontal directions and maintains constant the number of pixels required the image. Second, according to Shannon's rate distortion theory, the wavelet coefficients are vectored quantized using a multi-resolution ECVQ(entropy-constrained vector quantizer) codebook. The simulation results showed that the proposed method could achieve higher quality LENA image improved by about 2.0 dB than that of the ECVQ using other wavelet at 0.5 bpp and, by about 0.5 dB at 1.0 bpp, and reduce the block effect and the edge degradation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.477-480
• /
• 2006

To represent the accurate feature of signal and system, many researches have been done in many fields of basic and engineering science which led a great development of modem society. Even until currently, in order to acquire useful information from signals at high speed, many methods and transforms have been processed. In these methods, the Fourier transform which represents signal as the combination of the frequency component has been applied to the most fields. But as transform not to consider time information, the Fourier transform does not provide time information of the time and presents only overall features of signals. The wavelet transform, which is proposed to overcome this problem and recently expands the range of the application, presents time-frequency localization and many kinds of the wavelet can be applied according to the environment of application. In this paper, we detect the features of signals using the function which is considered as the wavelet and do research for filtering locally in the wavelet plane.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.4 no.2
• /
• pp.389-395
• /
• 2000

Digital Watermarking is a research area which aims at hiding secret information in digital multimedia content such as images, audio, and video. In this paper, we propose a new watermarking method with visually recognizable symbols into the digital images using wavelet transform, spread spectrum method and multilevel threshold value in considering the wavelet coefficients. The information of watermark can be extracted by subtracting wavelet coefficients with the original image and the watermarked image. The results of this experiment show that the proposed algorithm was superior to other similar watermarking algorithms. We showed Watermarking algorithm in JPEG lossy compression, resizing, LSB(Least Significant Bit) masking, and filtering.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.47 no.1
• /
• pp.7-16
• /
• 2010

Face recognition of face images is an active subject in the area of computer pattern recognition, which has a wide range of potential. Automatic extraction of face image of the feature points is an important step during automatic face recognition. Whether correctly extract the facial feature has a direct influence to the face recognition. In this paper, a new method of facial feature extraction based on Discrete Wavelet Transform is proposed. Firstly, get the face image by using PC Camera. Secondly, decompose the face image using discrete wavelet transform. Finally, we use the horizontal direction, vertical direction projection method to extract the features of human face. According to the results of the features of human face, we can achieve face recognition. The result show that this method could extract feature points of human face quickly and accurately. This system not only can detect the face feature points with great accuracy, but also more robust than the tradition method to locate facial feature image.

• Journal of the Institute of Electronics Engineers of Korea TE
• /
• v.39 no.4
• /
• pp.363-369
• /
• 2002

In this paper, it could improved on the arbitrary nonlinear function learning approximation which have the wavelet neural network based on Adaptive Neuro-Fuzzy Inference System(ANFIS) and the multi-resolution Analysis(MRA) of the wavelet transform. ANFIS structure is composed of a bell type fuzzy membership function, and the wavelet neural network structure become composed of the forward algorithm and the backpropagation neural network algorithm. This wavelet composition has a single size, and it is used the backpropagation algorithm for learning of the wavelet neural network based on ANFIS. It is confirmed to be improved the wavelet base number decrease and the convergence speed performances of the wavelet neural network based on ANFIS Model which is using the wavelet translation parameter learning and bell type membership function of ANFIS than the conventional algorithm from 1 dimension and 2 dimension functions.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.697-700
• /
• 2000

워터마크의 실현방법은 크게 두 가지로 나누어지는데, 하나는 공간영역에서 처리방법이고 다른 하나는 주파수영역에서 처리방법이다. 초기에는 공간영역에서 처리가 많이 연구되었으나 공간영역에서의 워터마크 삽입방법은 주로 least significant bit(LSB)을 조작하기 때문에 주파수영역의 방법보다 각종 신호처리에 의해 워터마크가 쉽게 없어지는 단점이 생긴다. 따라서 현재는 그런 단점들을 잘 극복할 수 있는 방법으로 주파수 영역에서의 워터마크 삽입 방법이 많이 쓰인다. 본 논문에서는 디지털 영상을 위한 다해상도 이산 웨이브렛 변환을 사용한 워터마킹 방법을 제안하였다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 1998.04a
• /
• pp.95-99
• /
• 1998

본 논문에서는 웨이브렛 변환을 이용한 영상 부호화에서 입력 영상의 통계적 성질에 관계없이 부호화 결과에 범용성을 갖는 새로운 벡터 양자화기 설계법을 제안한다. 제안하는 벡터 양자화기에서는 대표벡터를 생성하기 위한 학습계열로 난수에 영상의 상관과 에지성분을 첨가한 모사 영상을 사용한다. 제안한 방식에 의해 설계된 벡터양자화기와 코드북 생성에 이용하는 학습계열에 부호화 대상이 되는 영상과 같은 실제의 영상을 사용한 종래방식으로 설계된 벡터양자화기와 부호화 성능을 비교하여 종래방식의 문제점을 명확하게 밝힌다.