• Journal of the Korea Society of Computer and Information
• /
• v.16 no.3
• /
• pp.99-107
• /
• 2011

The feature extraction of asterias amurensis by using patterns is difficult to extract all the concave and convex features of asterias amurensis nor classify concave and convex. Concave and convex as important structural features of asterias amurensis are the features which should be found and the classification of concave and convex is also necessary for the recognition of asterias amurensis later. Accordingly, this study suggests the technique to extract the features of concave and convex, the main features of asterias amurensis. This technique classifies the concave and convex features by using the multi-directional linear scanning and form the candidate groups of the concave and convex feature points and decide the feature points of the candidate groups and apply convex hull algorithm to the extracted feature points. The suggested technique efficiently extracts the concave and convex features, the main features of asterias amurensis by dividing them. Accordingly, it is expected to contribute to the studies on the recognition of asterias amurensis in the future.

• Convergence Security Journal
• /
• v.14 no.5
• /
• pp.49-56
• /
• 2014

In this paper, we proposed a method for representing local facial features based on LDP (Local Directional Pattern). To represent both PFF (Permanent Facial Features) and TFF (Transient Facial Features) effectively, the proposed method configure local facial feature vectors based on overlapped blocks for each facial feature in the forms of various size and shape. There are three advantages - it take advantages of geometric feature based method; it shows robustness about detection error using movement characteristics of each facial feature; and it shows reduced sampling error because maintain spatial information caused by block size variability. Proposed method shows better classification accuracy and reduced amount of calculation than existing methods.

• The KSFM Journal of Fluid Machinery
• /
• v.8 no.4 s.31
• /
• pp.14-19
• /
• 2005

Average Bi-directional flow tube was suggested to measure single and two phase flow rate. Its working principle is similar with Pilot tube, however, it makes it possible to eliminate the cooling system which is normally needed to prevent from flashing in the pressure impulse line of Pilot tube when it is used in the depressurization condition. 3-dimensional steady state flow analyses using FLUENT 5.4 code were performed to validate the application of the average bi-directional flow tube in case of water and air flow. In this study, sensitivity studies have been performed to optimize the design features of the average bi-directional flow tube which can be applied for the various experimental conditions. For Re numbers above 1000, the k values are nearly constant regardless of the Re numbers and flow types and calculation results and experimental data coincides quite well. The current FLUENT calculation results suggest that linearity of the k values in various design features of the average BDFT is highly promising, which means that it is quite reasonable to select the typical design of the average BDFT for the convenience of the experimental conditions.

• 유체기계공업학회:학술대회논문집
• /
• 2004.12a
• /
• pp.180-186
• /
• 2004

Average Bi-directional flow tube was suggested to measure single and two phase flow rate. Its working principle is similar with Pilot tube, however, it makes it possible to eliminate the cooling system which is normally needed to prevent from flashing in the pressure impulse line of Pilot tube when it is used in the depressurization condition. 3-dimensional steady state flow analyses using FLUENT 5.4 code were performed to validate the application of the averagebi-directional flow tube in case of water and air flow In this study, sensitivity studies have been performed to optimize the design features of the average hi-directional flow tube which can be applied for the various experimental conditions. For Re numbers above 1000, the k values are nearly constant regardless of the Re numbers and flow types and calculation results and experimental data coincides quite well. The current FLUENT calculation results suggest that linearity of the k values in various design features of the average BDFT is highly promising, which means that it is quite reasonable to select the typical design of the average BDFT for the convenience of the experimental conditions.

• Journal of the Korea Computer Graphics Society
• /
• v.4 no.1
• /
• pp.1-10
• /
• 1998

The idea of level-of-detail based on multiresolution model is gaining popularity as a natural means of handling the complexity regarding the realtime rendering of virtual environments. To generate an effective multiresolution model, we should capture the prominent visual features in the process of simplifying original complex model. In this paper, we incorporate view dependent features such as silhouette features and backface features, to the generation process of multiresolution model. To capture the view directional parameter, we propose multiresolution view sphere. View sphere maps the directional relationship between object surface and the view. Using the view sphere, coherence in the directional space is mapped into spatial coherence in the view sphere. View sphere is generated in multiresolution fashion to simplify the object. To access multiresolution view sphere efficiently, we devise quad tree for the view sphere. We also devise a mechanism for realtime simplification process using proposed view sphere. Using proposed mechanism, regenerating simplified model in realtime is effectively done in the order of number of rendered vertices.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.2
• /
• pp.78-86
• /
• 1993

A nonlinear method for directional information processing is introduced, along with an application of directional feature enhancement. In this method, an input is convolved with a 2-D ong, norrow kernel, which is rotated through 360 degree, continuously or discretely in a large number of steps. An output is given by some function of the convolution results. Linear features that are aligned with the kernel are enhanced, otherwise, removed or suppressed. The method presented is insensitive to variation in the dimension of linear features to be processed and preserves a good enhancement capability even for an image characterized by low contrast and spatially varying brightness in noisy backgroung. Effects of the kernel legnth and width on the performance are discussed. A possible hybrid optical-electronic implementation is also discussed.

• Proceedings of the KIEE Conference
• /
• 2007.04a
• /
• pp.6-8
• /
• 2007

In this paper, We propose reasoning system for object recognition and space classification using not only visual features but also contextual information. It is necessary to perceive object and classify space in real environments for mobile robot. especially vision based. Several visual features such as texture, SIFT. color are used for object recognition. Because of sensor uncertainty and object occlusion. there are many difficulties in vision-based perception. To show the validities of our reasoning system. experimental results will be illustrated. where object and space are inferred by bi -directional rules even with partial and uncertain information. And the system is combined with top-down and bottom-up approach.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.3
• /
• pp.129-138
• /
• 2013

This paper is a study on Dual Tree Complex Wavelet Transform, which improved directional information for efficient image processing. Dual Tree Complex Wavelet Transform satisfies characteristics of shift invariance, and includes 6 directional information, which is more than previous Discrete Wavelet Transform. However, in images of buildings, there are many horizontal and vertical edge components. Therefore, all the high-frequency components of image are not expressed by 6 directional information subbands. This paper proposes 8-directional Complex Wavelet Transform with excellent high-frequency separation features by creating horizontal vertical($0^{\circ}$, $90^{\circ}$) subband besides 6 directional information subband of previous Dual Tree Complex Wavelet Transform. The proposed method can create and combine various directional information subbands according to features of image. Performance is evaluated by applying the method to noise removal.

• Journal of Information Processing Systems
• /
• v.14 no.1
• /
• pp.150-161
• /
• 2018

We propose a novel deep neural network model for detecting human activities in untrimmed videos. The process of human activity detection in a video involves two steps: a step to extract features that are effective in recognizing human activities in a long untrimmed video, followed by a step to detect human activities from those extracted features. To extract the rich features from video segments that could express unique patterns for each activity, we employ two different convolutional neural network models, C3D and I-ResNet. For detecting human activities from the sequence of extracted feature vectors, we use BLSTM, a bi-directional recurrent neural network model. By conducting experiments with ActivityNet 200, a large-scale benchmark dataset, we show the high performance of the proposed DeepAct model.

• Journal of KIISE:Software and Applications
• /
• v.27 no.4
• /
• pp.432-440
• /
• 2000

In this study, a new algorithm for canceling MRI artifact due to translational motion in image plane is described. Unlike the conventional iterative phase retrieval algorithm, in which there is no guarantee for the convergence, a direct method for estimating the motion is presented. In previous approaches, the motions in the x(read out) direction and the y(phase encoding) direction are estimated simultaneously. However, the features of x and y directional motions are different from each other. By analyzing their features, each x and y directional motion is canceled by different algorithms in two steps. First, it is noticed that the x directional motion corresponds to a shift of the x directional spectrum of the MRI signal, and the non-zero area of the spectrum just corresponds to the projected area of the density function on the x-axis. So the motion is estimated by tracing the edges between non-zero area and zero area of the spectrum, and the x directional motion is canceled by shifting the spectrum in inverse direction. Next, the y directional motion is canceled by using a new constraint condition, with which the motion component and the true image component can be separated. This algorithm is shown to be effective by using a phantom image with simulated motion.