• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.1
• /
• pp.127-135
• /
• 1995

The diffusion neural network forms a Gaussian distribution by transferring an excitation to the surround. A DOG(difference of two Gaussians) is obtained by the diffusion neural network. This type of the DOG, which can detect the intensity changes of an image, has the same shape as a LOG(Laplacian of a Gaussian:${\Delta}^2$G) and narrow band pass characteristics. In this paper we show that another type of the DOG which has a very narrow Gaussian for the excitatory and a very wide Gaussian for the inhibitory, can be formed by the diffusion process of this network, This type of the DOG has a wide band width in spatial frequency domain and can be used efficiently in detecting special type of edges.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.1
• /
• pp.90-98
• /
• 1993

A Gaussian is formed by diffusing a spot excitation. In this paper, a diffusion neural network model is derived from the diffusion equation. And it is shown that a difference of two Gaussians(DOG) may have the same shape as a Laplacian of Gaussian(LOG), A neural network model executing a DOG convolution by diffusing an external excitation is proposed. By this model intensity changes of image may be detected. This model may be implemented economically because each neuron has only four fixed-valued synapes.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.7
• /
• pp.163-172
• /
• 1996

Recently, it was reported that gaussian distribution and difference of two gaussians (DOG) to have band pass characteristics can be generated by simple iterative processes of the diffusion networks. In this paper, we propose method of improved implementation of a diffusion filter which can reduce total runing time, and operate by simple algorithm in contrast to the latest diffusion filter. We rebuild the diffusion network to a difference network which can generate DOG independently. Different filter characteristics are obtained just by each diffusion process and difference process. Quantitative analysis shows that the center frequency and the selectivity of each filter channel can be varied independently. Also, it would requires smaller amount of hardwares than conventioanl method to build a filter bank.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.1
• /
• pp.103-110
• /
• 2015

In this paper, we propose a deblurring method using 1/4 selective filter. Deblurring methods require a lot of processing time for deblurring. In order to enhance execution speed, we propose a novel 1/4 selective filter. The proposed 1/4 selective filter restores major edge, but it distorts minor edge and texture. To solve this problem, we apply 1/4 selective filter to restore major edge and DOG(Difference of Gaussian) filter to restore minor edge and texture. Experimental results show that the proposed method removes the blur effectively.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.11
• /
• pp.2478-2484
• /
• 2010

In this paper, real-time detection methods for Panorama system Key-Points offers. A recent study in PANORAMA system real-time area navigation or DVR to apply such research has recently been actively. The detection of the Key-Point is the most important elements that make up a Panorama system. Not affected by contrast, scale, Orientation must be detected Key-Point. Existing research methods are difficult to use in real-time Because it takes a lot of computation time. Therefore, this paper propose BLOG(BitRate Laplacian Of Gaussian)method for faster time Key-Point Detecting and Through various experiments to detect the Speed, Computation, detection performance is compared against.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.1
• /
• pp.120-126
• /
• 1995

The diffusion neural network can be cfficiently applied to the Gaussian processing. For example, a difference of two Gaussians(DOG) is performed by this network with ease. In this paper, we model a neural network to perform the function /t(.del.${\Delta}^{2}$G) by using the diffusion neural network. This model is used to detect the edges of moving target in image. By this model not only moving target is separated from stationary background but also their trajectories are obtained using accumulated past information in the diffusion neural network. Furthermore this model needs a small number of connections per cell and the connection weights are fixed-valued. Therefore its hardware can be easily implemented with simple structure.

• Journal of Korean Ophthalmic Optics Society
• /
• v.17 no.2
• /
• pp.153-158
• /
• 2012

Purpose: The purpose of this study was to evaluate the convergence accommodation to convergence (CA/C) ratio and to investigate relationships among age, accommodative amplitude and PD (interpupillary distance) of adults in their early twenties with normal binocular vision. Methods: 44 subjects (mean age, $21.75{\pm}1.16$ years) with healthy eyes were examined. The CA/C ratios were measured by using the difference of Gaussian (DOG) target with retinoscopy. Results: The mean CA/C ratio was $0.052{\pm}0.017$ D/$\Delta$. A moderate negative correction was present between CA/C ratio and age (r = -0.50, p = 0.0005), and a highly positive correction was found between CA/C ratio and accommodative amplitude (r = 0.79, p<0.0001). There was no relation between PD and CA/C ratio. Conclusions: The CA/C ratio presented was mean value for adults in their early twenties with healthy eye between 19 and 25 years of age. There was a high correlation between accommodative amplitude and CA/C ratio. Therefore, the CA/C ratio will be useful basic information for comparison in age, gender and binocular anomalies with similar data from other countries.