• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.4
• /
• pp.714-725
• /
• 1997

This paper proposes an image compression method using the wavelet transform and bit-plane coding of wavelet coefficients. The hierarchical application of wavelet transform to an image produces one low resoluation(the subband with lowest frequency) image and several high frequency subbands. In the proposed method, the low resolution image is compressed by a lossless method at 8 bits per each coefficient. However, the high frequency subbands are decomposed into 8 bit planes. With an adptive block coding method, the decomposed bit planes are effectively compressed using localized edge information in each bit plane. In addition, the propsoed method can control bit rates by selectively eliminating lessimportant subbands of low significant bit planes. Experimental results show that the proposed scheme has better performance in the peak signal to noise ratio (PSNR) and compression rate than conventional image coding methods using the wavelet transform and vector quantization.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.2
• /
• pp.96-100
• /
• 2006

Kim et al. Proposed Normalized Confidence Measure (NCM) [1-2] and it was successfully used for rejecting mis-recognized words in isolated word recognition. However their experiments were performed on the fixed word speech recognition. In this Paper we apply NCM to the domain of vocabulary independent speech recognition (VISP) and shows the rejection Performance of NCM in VISP. Specialty we Propose vector quantization (VQ) based method for overcoming the problem of unseen triphones. It is because NCM uses the statistics of triphone confidence in the case of triphone-based normalization. According to speech recognition experiments Phone-based normalization method shows better results than RLJC[3] and also triphone-based normalization approach. This results are different with those of Kim et al [1-2]. Concludingly the Phone-based normalization shows robust Performance in VISP domain.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.3A
• /
• pp.111-118
• /
• 2003

The transmit adaptive array requires the forward link channel information for evaluating the optimum transmit weight vector in which a feedback channel provides transmitter with the forward link channel information. The larger transmit adaptive array is, the higher required rate of feedback channel is. Therefore we consider the system that the N-transmit antenna system is expanded to the 2N-transmit antenna system, while the feedback channel is maintained as that of N-transmit antenna system. The increase of the number of antennas can produce the additional diversity gain, however the insufficient feedback bits assigned to each antenna aggravates the quantization error. In this paper, we propose the transmit antenna selection in order to improve the performance of transmit adaptive array having an insufficient feedback channel information. The effective method to transmit the weight vector is also introduced. System performances are investigated for the case of N=4 corresponding to the antenna selection diversity schemes on the flat fading channel and the multipath fading channel. The simulation results show that the proposed scheme can improve the system performance by 1 dB when the N is expanded to the 2N, while the feedback channel is restricted to that of N-transmit antenna system.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.5
• /
• pp.54-63
• /
• 2000

We present a multi-resolution block matching algorithm (BMA) for fast motion estimation At the coarsest level, a motion vector (MV) having minimum matching error is chosen via a full search, and a MV with minimum matching error is concurrently found among the MVs of the spatially adjacent blocks Here, to examine the spatial MVs accurately, we propose an efficient method for searching full resolution MV s without MV quantization even at the coarsest level The chosen two MV s are used as the initial search centers at the middle level At the middle level, the local search is performed within much smaller search area around each search center If the method used at the coarsest level is adopted here, the local searches can be done at integer-pel accuracy A MV having minimum matching error is selected within the local search areas, and then the final level search is performed around this initial search center Since the local searches are performed at integer-pel accuracy at the middle level, the local search at the finest level does not take an effect on the overall performance So we can skip the final level search without performance degradation, thereby the search speed increases Simulation results show that in comparison with full search BMA, the proposed BMA without the final level search achieves a speed-up factor over 200 with minor PSNR degradation of 02dB at most, under a normal MPEG2 coding environment Furthermore, our scheme IS also suitable for hardware implementation due to regular data-flow.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1996.10a
• /
• pp.239-242
• /
• 1996

본 논문에서는 BP(Back Propagation)에 비해서 빠른 학습시간과 다른 경쟁학습 신경회로망 알고리즘에 비해서 비교적 우수한 성능으로 패턴인식 등에 많이 이용되고 있는 LVQ(Learning Vector Quantization) 알고리즘의 성능을 향상시키기 위한 방법을 논의하고자 한다. 일반적으로 LVQ는 음(negative)의 학습을 하기 때문에 초기 가중치가 제대로 설정되지 않으면 발산할 수 있다는 단점이 있으며, 경쟁학습 계열의 신경망이기 때문에 출력 층의 뉴런 수에 따라 성능에 큰 영향을 받는다고 알려져 있다.[1]. 지도학습 형태를 지닌 LVQ의 경우에 학습패턴이 n개의 클래스를 가지고, 각 클래스 별로 학습패턴의 수가 같은 경우에 일반적으로 전체 출력뉴런에 대해서 (출력뉴런수/n)개의 뉴런을 각 클래스의 목표(desired) 클러스터로 할당하여 학습을 수행하는데, 본 논문에서는 각 클래스에 동일한 수의 출력뉴런을 할당하지 않고, 학습데이터에서 각 클래스의 분산을 추정하여 각 클래스의 분산을 추정분산에 비례하게 목표 출력뉴런을 할당하고, 초기 가중치도 추정분산에 비례하게 각 클래스의 초기 임의 위치 입력백터를 사용하여 학습을 수행하는 방법을 제안한다. 본 논문에서 제안하는 방법은 분류하고자 하는 데이터에 대해서 필요한 최적의 출력뉴런 수를 찾는 것이 아니라 이미 결정되어 있는 출력뉴런 수에 대해서 각 클래스에 할당할 출력 뉴런 수를 데이터의 추정분산에 의해서 결정하는 것으로, 추정분산이 크면 상대적으로 많은 출력 뉴런을 할당하고 작으면 상대적으로 적은 출력뉴런을 할당하고 초기 가중치도 마찬가지 방법으로 결정하며, 이렇게 하면 정해진 출력뉴런 개수 안에서 각 클래스 별로 분류의 어려움에 따라서 출력뉴런을 할당하기 때문에 미학습 뉴런이 줄어들게 되어 성능의 향상을 기대할 수 있으며, 실험적으로 제안된 방법이 더 나은 성능을 보임을 확인했다.initially they expected a more practical program about planting than programs that teach community design. Many people are active in their own towns to create better environments and communities. The network system "Alpha Green-Net" is functional to support graduates of the course. In the future these educational programs for citizens will becomes very important. Other cities are starting to have their own progrms, but they are still very short term. "Alpha Green-Net" is in the process of growing. Many members are very keen to develop their own abilities. In the future these NPOs should become independent. To help these NPOs become independent and active the educational programs should consider and teach about how to do this more in the future.단하였는데 그 결과, 좌측 촉각엽에서 제4형의 신경연접이 퇴행성 변화를 나타내었다. 그러므로 촉각의 지각신경세포는 뇌의 같은 족 촉각엽에 뻗어와 제4형 신경연접을 형성한다고 결론되었다.$/ 값이 210 $\mu\textrm{g}$/$m\ell$로서 효과적인 저해 활성을 나타내었다 따라서, 본 연구에서 빈

• Journal of Intelligence and Information Systems
• /
• v.15 no.2
• /
• pp.49-59
• /
• 2009

Contents-based image retrieval methods are in general more objective and effective than text-based image retrieval algorithms since they use color and texture in search and avoid annotating all images for search. SIM(Self-organizing Image browsing Map) is one of contents-based image retrieval algorithms that uses only browsable mapping results obtained by SOM(Self Organizing Map). However, SOM may have an error in selecting the right BMU in learning phase if there are similar nodes with distorted color information due to the intensity of light or objects' movements in the image. Such images may be mapped into other grouping nodes thus the search rate could be decreased by this effect. In this paper, we propose an improved SIM that uses HSV color model in extracting image features with color quantization. In order to avoid unexpected learning error mentioned above, our SOM consists of two layers. In learning phase, SOM layer 1 has the color feature vectors as input. After learning SOM Layer 1, the connection weights of this layer become the input of SOM Layer 2 and re-learning occurs. With this multi-layered SOM learning, we can avoid mapping errors among similar nodes of different color information. In search, we put the query image vector into SOM layer 2 and select nodes of SOM layer 1 that connects with chosen BMU of SOM layer 2. In experiment, we verified that the proposed SIM was better than the original SIM and avoid mapping error effectively.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.2
• /
• pp.60-69
• /
• 1998

This paper proposes a speech synthesis method using Fuzzy VQ, and then study how to make choice of fuzziness value which optimizes (controls) the performance of FVQ in order to obtain the synthesized speech which is closer to the original speech. When FVQ is used to synthesize a speech, analysis stage generates membership function values which represents the degree to which an input speech pattern matches each speech patterns in codebook, and synthesis stage reproduces a synthesized speech, using membership function values which is obtained in analysis stage, fuzziness value, and fuzzy-c-means operation. By comparsion of the performance of the FVQ and VQ synthesizer with simmulation, we show that, although the FVQ codebook size is half of a VQ codebook size, the performance of FVQ is almost equal to that of VQ. This results imply that, when Fuzzy VQ is used to obtain the same performance with that of VQ in speech synthesis, we can reduce by half of memory size at a codebook storage. And then we have found that, for the optimized FVQ with maximum SQNR in synthesized speech, the fuzziness value should be small when the variance of analysis frame is relatively large, while fuzziness value should be large, when it is small. As a results of comparsion of the speeches synthesized by VQ and FVQ in their spectrogram of frequency domain, we have found that spectrum bands(formant frequency and pitch frequency) of FVQ synthesized speech are closer to the original speech than those using VQ.

• Journal of Broadcast Engineering
• /
• v.11 no.1 s.30
• /
• pp.3-14
• /
• 2006

Music summarization means a technique which automatically generates the most importantand representative a part or parts ill music content. The techniques of music summarization have been studied with two categories according to summary characteristics. The first one is that the repeated part is provided as music summary and the second provides the combined segments which consist of segments with different characteristics as music summary in music content In this paper, we propose and evaluate two kinds of music summarization techniques. The algorithm using multi-level vector quantization which provides a repeated part as music summary gives fixed-length music summary is evaluated by overlapping ration between hand-made repeated parts and automatically generated summary. As results, the overlapping ratios of conventional methods are 42.2% and 47.4%, but that of proposed method with fixed-length summary is 67.1%. Optimal length music summary is evaluated by the portion of overlapping between summary and repeated part which is different length according to music content and the result shows that automatically-generated summary expresses more effective part than fixed-length summary with optimal length. The cluster-based algorithm using 2-D similarity matrix and k-means algorithm provides the combined segments as music summary. In order to evaluate this algorithm, we use MOS test consisting of two questions(How many similar segments are in summarized music? How many segments are included in same structure?) and the results show good performance.

• Korean Journal of Remote Sensing
• /
• v.14 no.2
• /
• pp.175-195
• /
• 1998

Automatic lineament extraction algorithms had been developed by various researches for geological purpose using remotely sensed data. However, most of them are designed for a certain topographic model, for instance rugged mountainous region or flat basin. Most of common topographic characteristic in Korea is a mountainous region along with alluvial plain, and consequently it is difficult to apply previous algorithms directly to this area. A new algorithm of automatic lineament extraction from remotely sensed images is developed in this study specifically for geological applications. An algorithm, named as DSTA(Dynamic Segment Tracing Algorithm), is developed to produce binary image composed of linear component and non-linear component. The proposed algorithm effectively reduces the look direction bias associated with sun's azimuth angle and the noise in the low contrast region by utilizing a dynamic sub window. This algorithm can successfully accomodate lineaments in the alluvial plain as well as mountainous region. Two additional algorithms for estimating the individual lineament vector, named as ALEHHT(Automatic Lineament Extraction by Hierarchical Hough Transform) and ALEGHT(Automatic Lineament Extraction by Generalized Hough Transform) which are merging operation steps through the Hierarchical Hough transform and Generalized Hough transform respectively, are also developed to generate geological lineaments. The merging operation proposed in this study is consisted of three parameters: the angle between two lines($\delta$$\beta$), the perpendicular distance($(d_ij)$), and the distance between midpoints of lines(dn). The test result of the developed algorithm using Landsat TM image demonstrates that lineaments in alluvial plain as well as in rugged mountain is extremely well extracted. Even the lineaments parallel to sun's azimuth angle are also well detected by this approach. Further study is, however, required to accommodate the effect of quantization interval(droh) parameter in ALEGHT for optimization.