• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.9
• /
• pp.3186-3203
• /
• 2021

In this paper, a multi-scale local difference directional number (MLDDN) pattern is proposed for pig identification. Firstly, the color images of individual pig are converted into grey images by the most significant bits (MSB) quantization, which makes the grey values have better discrimination. Then, Gabor amplitude and phase responses on different scales are obtained by convoluting the grey images with Gabor masks. Next, by calculating the main difference of local edge directions instead of traditionally edge information, the directional numbers of Gabor amplitude and phase responses are encoded. Finally, the block histograms of the encoded images are concatenated on each scale, and the maximum pooling is adopted on different scales to avoid the high feature dimension. Experimental results on two pigsties show that MLDDN impressively outperforms the other widely used local descriptors.

• International Journal of Control, Automation, and Systems
• /
• v.1 no.1
• /
• pp.119-126
• /
• 2003

The problem of tracking moving objects in a video stream is discussed in this pa-per. We discussed the popular technique of optical flow for moving object detection. Optical flow finds the velocity vectors at each pixel in the entire video scene. However, optical flow based methods require complex computations and are sensitive to noise. In this paper, we proposed a new method based on the Hough transform and on voting accumulation for improving the accuracy and reducing the computation time. Further, we applied the Boo-lean based edge detector for edge detection. Edge detection and segmentation are used to extract the moving objects in the image sequences and reduce the computation time of the CHT. The Boolean based edge detector provides accurate and very thin edges. The difference of the two edge maps with thin edges gives better localization of moving objects. The simulation results show that the proposed method improves the accuracy of finding the optical flow vectors and more accurately extracts moving objects' information. The process of edge detection and segmentation accurately find the location and areas of the real moving objects, and hence extracting moving information is very easy and accurate. The Combinatorial Hough Transform and voting accumulation based optical flow measures optical flow vectors accurately. The direction of moving objects is also accurately measured.

• The Journal of the Korea Contents Association
• /
• v.5 no.2
• /
• pp.221-228
• /
• 2005

The paper proposes the improved error diffusion halftoning system to enhance the edges using the spatial perceptual characteristics of the human visual system. The proposed method computes a spatial variation(SV), which is the difference between a pixel luminance and the average of its $3{\times}3$ neighborhood pixels' luminances weighted according to the spatial positioning. Information of edge enhancement(IEE) Is computed using the SV and the local average luminance. The IEE is added to the quantizer's input pixel and feeds into the halftoning quantizer. The quantizer produces the halftone image having the enhanced edge. The performance of the proposed method is compared with conventional methods by measuring the edge correlation. The halftone images by using the proposed method show better quality due to the enhanced edge. And the detailed edge is preserved in the halftone images by using the proposed method.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.26 no.4
• /
• pp.644-652
• /
• 2002

Increasing demands for Electric Resistance Welded pipes of high quality with thick wall require c lose investigations in edge deformation by slitting, strip deformation during break down farming, and difference of circumferential length. In order to obtain good quality of a welding zone, it is necessary to predict the edge shape of the initial strip. The modeling of the multi-pass thick tube roll forming process with rigid plastic finite element method ultra the edge shape prediction of an initial strip with 2nd-degree polynomial regression method are presented. Edge shapes of initial strip have been analyzed by the finite element method and designed by the regression method to satisfy the requirements in target fin pass. It is concluded that the proposed edge design method results in optimal edge shapes sat string the design requirements.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.5
• /
• pp.556-566
• /
• 2001

This paper proposes a motion-adaptive de-interlacing algorithm based on EBMF(Edge Based Median Filter) and AMPDF(Adaptive Minimum Pixel Difference Fillet). To compensate 'motion missing'error, which is an important factor in motion-adaptive methods, we used AMPDF which estimates an accurate value using different thresholds after classifying the input image to 4 classes. To efficiently interpolate the moving diagonal edge, we also used EBMF which selects a candidate pixel according to the edge information. Finally, we, to increase the performance, adopted an adaptive interpolation after classifying the input image to moving region, stationary region, and boundary region. Simulation results showed that the proposed method provides better performance than the existing methods.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.5
• /
• pp.143-150
• /
• 2009

In this paper, we present a spatial domain error concealment method to recover a lost block in intra-coded frames. The edge directions of the lost block are estimated by the difference values of the border pixels of the accurately received blocks. The lost block is interpolated according to the estimated edge directions. Our algorithm can adaptively recover a lost block according to the estimated edge direction. The distances between pixels are used as weights for interpolation. In spite of the low computational cost, the proposed method outperforms the previous methods in objective and subjective qualities.

• Journal of Korean Society of Steel Construction
• /
• v.12 no.2 s.45
• /
• pp.221-230
• /
• 2000

Checking the stability of anisotropic plates with free edges, it is impossible that buckling loads and modes are found via existing classical methods about various loads and boundary conditions. For solving this problems. finite difference method(FDM) is used to analyze the buckling behaviors for arbitrary boundary conditions. Using FDM, it is difficult to treat the fictitious points on free edges. So, this paper analyzes buckling behaviors of analytic models with one edge free and the other edges clamped and with opposite two edges free and other two edges clamped. The various buckling loads and mode characteristics through numerical results are given for buckling behaviors of anisotropic plates on free edges.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.4
• /
• pp.72-80
• /
• 1996

In this paper, variable windowing mean filter to remove speckle noise and a measure to detect thin edge in ultrasonic images are proposed. Because ultrasonic images are corrupted by speckle noise showing a granular appearance, good edge detection is difficult. As a result, noise removing filter is needed in preprocessing stage. The speckle noise removing filter is based on mean filter whose window size is changed by the ratio of standard deviation to mean for image signal and noise signal in local area. And the measure expressed the difference of means between tow windows is used for detecting thin edge in filtered image. Results show that variable windowing mean filter removes speckle noise effectively, and proposed measure is useful in detecting thin edge.

• 제어로봇시스템학회:학술대회논문집
• /
• 1995.10a
• /
• pp.236-239
• /
• 1995

It is useful to simulate the human visual function for the purpose of image-processing. In this study, the hardware of the spatial filter with the sensitivity of lateral inhibition is realized by the combination of optical parts with electronic circuits. The diffused film with the characteristics of Gaussian type is prepared as a spatial filter. An object's image is convoluted with the spatial filter. From the difference of the convoluted images, the zero-cross position is detected at video rate. The edge of object is extracted in real-time by the use of this equipment. The resolution of edge changes with the value of the standard deviation of diffused film. In addition, it is possible to extract a directional edge selectively when the spatial filter with directional selectivity is used instead of Gaussian type of spatial filter.

• The Korean Journal of Zoology
• /
• v.3 no.1
• /
• pp.13-18
• /
• 1960

1. Author has surveyed the frequency, geographic variation and micro-geographic variation of the elytral pattern types and the elytral edge of the population of lady-beetle, Harmonia axyridis Pallace which was collected in Seoul and the other 6 localities in Korea. 2. The number of specimen collected were 3.051 in which succinea occupied 88.32 % : Axyridis, 1.00% : spectabilis, 6.145 : and Conspicua , 4.545. 3. Of all 84.80% were found to have elytral edge. 4. There was a little difference in compositional proportation of the above four types to population and in the frequency of elytral edge between the population of west seaside and that of inland of Korea. 5. An interesting micro-geographic variation was observed in Dae-Chun, a beach located on west seaside of south Korea. In this locality , the Succinea occupied 45.23% and 27.805 were found to be provided with elytral edge in the specimen collected in pine trees ( Pinus thunbergii Parlatore), while in the specimen collected in burley field, oak, willow etc. 92.00% were Succinea and 90.93% were found to have elytral edge.