• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.821-824
• /
• 1999

In distributed arithmetic-based architecture for an inner product between two length-N vectors, the size of the ROM increases exponentially with N. Moreover, the ROMs are generally the bottleneck of speed, especially when their sire is large. In this paper, a ROM size reduction technique for DA (Distributed Arithmetic) is proposed. The proposed method is based on modified OBC (Offset Binary Coding) and control circuit reduction technique. By simulations, it is shown that the use of the proposed technique can result in reduction in the number of gates up to 50%.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.1
• /
• pp.70-74
• /
• 2008

In the field of camera motion research, it is widely held that the position (movement) and pose (rotation) of cameras are correlated and cannot be independently separated. A new equation based on inner product is proposed here to independently separate the position and pose. It is proved that the position and pose are not correlated and the equation is applied to estimation of the camera exterior parameters using a real image and 3D data.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.25 no.5
• /
• pp.375-381
• /
• 2007

A novel method to register images onto 3D data, such as 3D point cloud, 3D vectors, and 3D surfaces, is proposed. The proposed method estimates the exterior orientation of a camera with respective to the 3D data though fitting pairs of the normal vectors of two planes passing a focal point and 2D and 3D lines extracted from an image and the 3D data, respectively. The fitting condition is that the angle between each pair of the normal vectors has to be zero. This condition can be represented as a numerical formula using the inner product of the normal vectors. This paper demonstrates the proposed method can estimate the exterior orientation for the image registration as simulation tests.

• The KIPS Transactions:PartB
• /
• v.11B no.6
• /
• pp.735-742
• /
• 2004

We present a new use of common graphics hardware to perform a faster artificial neural network. And we examine the use of GPU enhances the time performance of the image processing system using neural network, In the case of parallel computation of multiple input sets, the vector-matrix products become matrix-matrix multiplications. As a result, we can fully utilize the parallelism of GPU. Sigmoid operation and bias term addition are also implemented using pixel shader on GPU. Our preliminary result shows a performance enhancement of about thirty times faster using ATI RADEON 9800 XT board.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.87-88
• /
• 2023

본 논문에서는 COVID-19 팬데믹으로 인해 사회적 거리두기 및 규제조치가 시행되면서 다양한 분야에서 큰 영향을 가져왔다. 변화된 홈트레이닝 분야는 운동기구를 구비하여 개인운동을 통해 건강을 유지하고 있으나 전문적인 교육을 받지 않은 홈트레닝으로 부상 위험에 노출 되고 있다. 요가는 호흡운동과 명상을 지향하는 운동으로 요가의 효과를 얻기 위해 올바른 움직임과 자세가 중요 하다. 본 논문에서는 실시간으로 입력된 영상 프레임을 OpenCV와 MediaPipe를 통해 추출된 주요좌표 값을 벡터 내적공식을 대입, 코사인2법칙을 통해 요가의 올바른 자세를 분석하여 종합적인 정보를 제공하는 요가교정 모델이다.

• Annual Conference of KIPS
• /
• 2008.11a
• /
• pp.782-784
• /
• 2008

급속하게 확산된 비즈니스 웹 사이트로 인해 웹상에 상품의 정보가 기하급수적으로 증가하여 정보 과부하 문제가 발생하였다. 이를 극복하기 위해 내용 기반 추천 시스템, 협업 필터링 추천 시스템 등의 개인화 추천 시스템이 발전했으나 사용자의 성향과 아이템의 성향을 반영하지 못하고 있다. 본 연구에서는 웹상에서 사용자의 행동을 관찰하여 상품의 구매경로와 판매의 상관관계에 따라 각 사용자의 성향과 그룹의 성향, 아이템의 성향을 측정한 뒤 벡터의 내적을 이용하여 사용자의 성향에 가장 적합한 상품의 유사도를 계산하고 추천하는 시스템을 제안한다.

• Journal of KIISE:Software and Applications
• /
• v.29 no.3
• /
• pp.167-179
• /
• 2002

In this paper, we propose a new acoustic model for characterizing segmental features and an algorithm based upon a general framework of hidden Markov models (HMMs) in order to compensate the weakness of HMM assumptions. The segmental features are represented as a trajectory of observed vector sequences by a polynomial regression function because the single frame feature cannot represent the temporal dynamics of speech signals effectively. To apply the segmental features to pattern classification, we adopted segmental HMM(SHMM) which is known as the effective method to represent the trend of speech signals. SHMM separates observation probability of the given state into extra- and intra-segmental variations that show the long-term and short-term variabilities, respectively. To consider the segmental characteristics in acoustic model, we present segmental-feature HMM(SFHMM) by modifying the SHMM. The SFHMM therefore represents the external- and internal-variation as the observation probability of the trajectory in a given state and trajectory estimation error for the given segment, respectively. We conducted several experiments on the TIMIT database to establish the effectiveness of the proposed method and the characteristics of the segmental features. From the experimental results, we conclude that the proposed method is valuable, if its number of parameters is greater than that of conventional HMM, in the flexible and informative feature representation and the performance improvement.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.1
• /
• pp.31-39
• /
• 1995

In this paper, we have constructed phoneme discriminant filters [PDF] according to the linear discriminant function. These discriminant filters do not follow the heuristic rules by the experts but the mathematical methods in iterative learning. Proposed system. is based on the piecewise linear classifier and error correction learning method. The segmentation of speech and the classification of phoneme are carried out simutaneously by the PDF. Because each of them operates independently, some speech intervals may have multiple outputs. Therefore, we introduce the unified coefficients by the output unification process. But sometimes the output has a region which shows no response, or insensitive. So we propose time windows and median filters to remove such problems. We have trained this system with the 549 monosyllables uttered 3 times by 3 male speakers. After we detect the endpoint of speech signal using threshold value and zero crossing rate, the vowels and consonants are separated by the PDF, and then selected phoneme passes through the following PDF. Finally this system unifies the outputs for competitive region or insensitive area using time window and median filter.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.6 s.44
• /
• pp.269-277
• /
• 2006

We propose a new expert system for recovering the broken fragments of relics into an original form using computer graphics and image processing. This paper presents a system with an application to tombstones objects of flat plane with letters carved in for assembling the fragments by placing their respective fragments in the right position. The matching process contains three sub-processes: aligning the front and letters of an object, identifying the matching directions, and determining the detailed matching positions. We apply least squares fitting, vector inner product, and geometric and RGB errors to the matching process. It turned out that 2-D translations via fragments-alignment enable us to save the computational load significantly. Based on experimental results from the damaged cultural fragments, the performance of the proposed method is illustrated.

• Journal of Korean Society for Geospatial Information Science
• /
• v.14 no.4 s.38
• /
• pp.71-77
• /
• 2006

Support Vector Machine (SVM) which has roots in a statistical learning theory is a training algorithm based on structural risk minimization. Generally, SVM algorithm uses the kernel for determining a linearly non-separable boundary and classifying the data. But, classical kernels can not apply to effectively the hyperspectral image classification because it measures similarity using vector's dot-product or euclidian distance. So, This paper proposes the spectral similarity kernel to solve this problem. The spectral similariy kernel that calculate both vector's euclidian and angle distance is a local kernel, it can effectively consider a reflectance property of hyperspectral image. For validating our algorithm, SVM which used polynomial kernel, RBF kernel and proposed kernel was applied to land cover classification in Hyperion image. It appears that SVM classifier using spectral similarity kernel has the most outstanding result in qualitative and spatial estimation.