• The Journal of Engineering Geology
• /
• v.20 no.4
• /
• pp.371-380
• /
• 2010

A three-dimensional finite element analysis was performed to predict the location of a fault zone ahead of a tunnel face based on convergence displacement. Geometrical models for the numerical analysis were developed based on the possible geometric intersection between the fault zone and the tunnel. Fifteen fault models were generated from combinations of faults with five different strikes (at $15^{\circ}$ intervals) and three dips (vertical, $45^{\circ}$ and $-45^{\circ}$) relative to the tunnel route. The displacements on the crown and side walls were calculated and analyzed using a vector orientation approach. As a result, nine representative prediction charts were developed, showing location and orientation of the fault zone based on convergence displacement.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.9
• /
• pp.5446-5451
• /
• 2014

Because there are some mistakes by hand in processing electronic maps using a navigation terminal, this paper proposes an automatic offline recognition for traffic signs, which are considered ingredient navigation information. Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA), which have been used widely in the field of 2D face recognition as computer vision and pattern recognition applications, was used to recognize traffic signs. First, using PCA, a high-dimensional 2D image data was projected to a low-dimensional feature vector. The LDA maximized the between scatter matrix and minimized the within scatter matrix using the low-dimensional feature vector obtained from PCA. The extracted traffic signs under a real-world road environment were recognized successfully with a 92.3% recognition rate using the 40 feature vectors created by the proposed algorithm.

• Journal of KIISE:Software and Applications
• /
• v.29 no.11
• /
• pp.818-825
• /
• 2002

Depth information is one of the most important factor for the recognition of a digital face image. Range images are very useful, when comparing one face with other faces, because of implicating depth information. As the processing for the whole fare produces a lot of calculations and data, face images ran be represented in terms of a vector of feature descriptors for a local area. In this paper, depth areas of a 3 dimensional(3D) face image were extracted by the contour line from some depth value. These were resampled and stored in consecutive location in feature vector using multiple feature method. A comparison between two faces was made based on their distance in the feature space, using Euclidian distance. This paper reduced the number of index data in the database and used fewer feature vectors than other methods. Proposed algorithm can be highly recognized for using local depth information and less feature vectors or the face.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.8B
• /
• pp.1577-1585
• /
• 1999

In this paper, we propose detection methods for gradual scene changes such as dissolve, pan, and zoom. The proposal method to detect a dissolve region uses scene features based on spatial statistics of the image. The spatial statistics to define shot boundaries are derived from squared means within each local area. We also propose a method of the camera motion detection using four representative motion vectors in the background. Representative motion vectors are derived from macroblock motion vectors which are directly extracted from MPEG streams. To reduce the implementation time, we use DC sequences rather than fully decoded MPEG video. In addition, to detect the gradual scene change region precisely, we use all types of the MPEG frames(I, P, B frame). Simulation results show that the proposed detection methods perform better than existing methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.6
• /
• pp.1312-1317
• /
• 2003

This paper presents an integrated approach to unconstrained face recognition in arbitrary scenes. The front end of the system comprises of a scale and pose tolerant face detector. Scale normalization is achieved through novel combination of a skin color segmentation and log-polar mapping procedure. Principal component analysis is used with the multi-view approach proposed in[10] to handle the pose variations. For a given color input image, the detector encloses a face in a complex scene within a circular boundary and indicates the position of the nose. Next, for recognition, a radial grid mapping centered on the nose yields a feature vector within the circular boundary. As the width of the color segmented region provides an estimated size for the face, the extracted feature vector is scale normalized by the estimated size. The feature vector is input to a trained neural network classifier for face identification. The system was evaluated using a database of 20 person's faces with varying scale and pose obtained on different complex backgrounds. The performance of the face recognizer was also quite good except for sensitivity to small scale face images. The integrated system achieved average recognition rates of 87% to 92%.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.15 no.1
• /
• pp.127-136
• /
• 2002

This papers presents a practical damage detection algorithm based on damage index method that accurately assesses both the location and severity of the localized detriment in a bridge structure using only limited mode shapes. In the algorithm, the ratio of the modal vector sensitivity of an undamaged structure to that of a damaged structure is used as an indicator of damage. However, a difficulty arises when the damaged element is located at a node of mode where the amplitude of medal vector is close to zero, leading the singularity of the ratio (i.e., division-by-zero). This singularity problem is overcome by introducing a parameter denoted a sensitivity filter, a function of mode shape of the structure, in modal vector sensitivity. Using this concept, an improvement can be considerably achieved in the estimation of both degree of severity and location of damage. To verify the proposed algorithm, its numerical implementations are conducted for a simply supported beam and a 2-span continuous beam.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.4
• /
• pp.545-549
• /
• 2009

Microarray data sets could contain thousands of gene expression levels and have been considered as an important source from which meaningful patterns could be extracted for further analysis in biological studies. It is sometimes necessary to retrieve out specific genes or samples of analyst's interest in an effective way. This paper is concerned with a method to make use of fuzzy signature set in order to filter out genes or samples which satisfy complicated constraints as well as simple ones. Fuzzy signatures are an extension of vector valued fuzzy sets, in which elements of the vector are allowed to have a vector. Fuzzy signature sets are similar to fuzzy signatures except that their leaf elements are fuzzy sets defined on the interval [0,1]. This paper introduces an extension of fuzzy signature sets which specifies aggregation operators at each internal node and comparison operators for aggregation. It also shows how to use the extended fuzzy signature sets in microarray data retrieval and some examples of its usage.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.6
• /
• pp.705-711
• /
• 2011

This paper proposes an effective algorithm of license plate recognition for industrial applications. By applying Canny edge detection on a vehicle image, it is possible to find a connected rectangular, which is a strong candidate for license plate. The color information of license plate separates plates into white and green. Then, OTSU binary image processing and foreground neighbor pixel propagation algorithm CLNF will be applied to each license plates to reduce noise except numbers and letters. Finally, through labeling, numbers and letters will be extracted from the license plate. Letter and number regions, separated from the plate, pass through mesh method and thinning process for extracting feature vectors by X-Y projection method. The extracted feature vectors are compared with the pre-learned weighting values by backpropagation neural network to execute final recognition process. The experiment results show that the proposed license plate recognition algorithm works effectively.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.2
• /
• pp.338-343
• /
• 2004

In Block Matching Algorithm (BMA), a search pattern has a very important affect on the search time and the output quality. In this paper, we propose the HDS( Half Diamond Search) pattern based on the cross center-biased distribution property of a motion vector. At lust, the 4 points in the above, below, left, and right around the search center is calculated to decide the point of the MBD (Minimum Block Distortion). And an above point of the MBD is checked to calculate the SAD. If the SAD is less than the previous MBD, this process is repeated. Otherwise, the left and right points of MBD are calculated to decide the points that have the MBD between two points. These processes are repeated to the predicted direction for motion estimation. Experiments show that the speedup improvement of the proposed algorithm can be up to 23% while maintaining similar image quality.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.9
• /
• pp.4455-4461
• /
• 2013

This paper investigates the diagnosis performance of Artificial Neural Network (ANN) depending on the structure and the input vector type of ANN, which has been used to detect the partial discharge to lead to the electric machinery deterioration. The diagnosis performance of one hidden layer and two hidden layer in ANN are compared. The performance using the 2048 time-series data and the performance using the feature input vector are compared. For measuring the partial discharge signal, the tip-to-plate, the sphere-to-sphere, the tip-to-tip, the tip-to-sphere and the sphere-to-plate electrodes are used respectively. For ANN's learning, Matlab and C-code program are used. For evaluating the diagnosis performance of ANNs, the simulation studies are performed.