• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.6
• /
• pp.1946-1963
• /
• 2014

Most background subtraction methods focus on dynamic and complex scenes without considering robustness against noise. This paper proposes a background subtraction algorithm based on dictionary learning and sparse coding for handling low light conditions. The proposed method formulates background modeling as the linear and sparse combination of atoms in the dictionary. The background subtraction is considered as the difference between sparse representations of the current frame and the background model. Assuming that the projection of the noise over the dictionary is irregular and random guarantees the adaptability of the approach in large noisy scenes. Experimental results divided in simulated large noise and realistic low light conditions show the promising robustness of the proposed approach compared with other competing methods.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2007.08b
• /
• pp.1185-1188
• /
• 2007

The address discharge characteristics by the various scan-low and common-bias voltages are investigated based on measured address discharge time lags and $V_t$ close-curve analysis. The scan-low voltages are changed under the same voltage difference between the X and Y electrodes during an address period. As the voltage difference between the scan and address electrodes is increased during an address period, the address discharge time lag is shortened but the background luminance is increased. It is found that the improved address discharge characteristics is caused by the effect of the higher external applied voltage during an address period than the accumulated wall charges during a reset period and the high background luminance can be prevented by applying an address-bias voltage during a rising-ramp period and low reset voltage.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2000.05a
• /
• pp.352-355
• /
• 2000

In this paper, we propose an adaptive thresholding for edge detection. first, we got histograms for background image and image with moving object, respectively. Then we make difference histogram between histograms of background and object image. A thresholding value is decided using gradient of peak to peak in the difference histogram. The experimentation is processed using a moving car in the road. The result is that edge is detected well regardless of the brightness.

• Journal of the Korea Convergence Society
• /
• v.8 no.7
• /
• pp.7-13
• /
• 2017

Robot performances in public places are conducted for the purpose of promoting robot technology and inducing interest in events, exhibitions, and streets instead of dedicated stages. This paper extracts robot images in real time from a robot operation in front of a green chroma key cloth, and synthesizes them on various stage images. A simple and robust method for extracting a foreground robot from a chroma key background without a user's preset is proposed. After increasing the color difference between the background and the foreground, this method automatically removes the background based on the histogram of the difference information, thereby eliminating the need for a user's preset. The simulation shows 98.8% of foreground extraction rate and experimental results demonstrate that the robots can effectively be extracted from the background.

• Journal of Internet Computing and Services
• /
• v.7 no.4
• /
• pp.33-43
• /
• 2006

This paper proposes a method to extract coronary arteries effectively in the angiography, In general. DSA(Digital Subtraction Angiography) is a well-established technique for the visualization of coronary arteries, DSA involves the subtraction of a mask image, an image of a heart before the injection of contrast medium, from a live image, However, this technique is sensitive to the movement of background and can cause wrong detection due to the variance of background intensity between two images. Therefore, this paper solves the structural problem resulted from background movement by selecting an image which has the least difference of movement through the similarity analysis of background texture, and it extracts only the blood vessels effectively through local intensity correction of the selected images, Experimental results show that the proposed method has the lower false-detection rate and higher accuracy rate than existing methods.

• The Journal of Korean Academy of Prosthodontics
• /
• v.16 no.1
• /
• pp.38-44
• /
• 1978

Color is an important factor in dental esthetics. Application of natural tooth color will not fail to produce pleasing results. But a standardized method of shade matching has not been adopted. If we are to overcome the color matching problem in dentistry, an understanding of the nature of color and light is essential. The purpose of this study was to compare the effects of different light sources and different background colors on the ability of observers to correctly match shades of artifical teeth. And observation was made to determine if the time spent in making a shade match was a factor in the correctness of the response. A test method was devised and 50 individuals made observations which were recorded and analyzed. $X^2$-test gave results indicating that the time factor had no effect on the response made. An analysis of variance showed the following effects significant at the five percent level; (1) light source (2) background color (3) subject. The following conclusions can be drawn from this study; (1) The time spent in making shade selection is not a factor in the correctness of the selections. (2) The light source used is an important factor in matching tooth shade; and there is no significant difference between the light sources in shade matching. (3) Under the conditions of this study, the greatest accuracy in shade matching was obtained on the brown background.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.1
• /
• pp.52-54
• /
• 2015

In this paper we propose a new background motion compensation method which can be applicable to moving object detection with a moving monocular camera. To estimate the background motion, a series of image warpings are carried out for each pair of the corresponding patches, defined by the fixed-size lattice, based on the motion information extracted from the feature points surrounded by the patches and the estimated camera motion. Experiment results proved that the proposed has approximately 50% faster in execution time and 8dB higher in PSNR comparing to a conventional method.

• Proceedings of the IEEK Conference
• /
• 2004.08c
• /
• pp.823-826
• /
• 2004

In this paper, A tracking of the moving objects using normalized hue distribution in HSI color model was proposed. Moving objects are detected by using difference image method and integral projection method to background image and objects image only with hue area. Hue information of the detected moving area are normalized by 24 levels from $0^{\circ}$ to $3600^{\circ}A$ distance in between normalized levels with a hue distribution chart of the normalized moving objects is used for the identity distinction feature parameters of the moving objects. To examine proposed method in this paper, image of moving cars are obtained by setting up three cameras at different places every 1 km on outer motorway. The simulation results of identity distinction show that it is possible to distinct the identity a distance in between normalization levels of a hue distribution chart without background.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2004.05b
• /
• pp.591-594
• /
• 2004

In this paper, The identity distinction of the moving objects using distance among hue normalization levels was proposed. Moving objects are detected by using difference image method and integral projection method to background image and objects image only with hue area. Hue information of the detected moving area are normalized by 24 levels from 0$^{\circ}$ to 360$^{\circ}$. A distance in between normalized levels with a hue distribution chart of the normalized moving objects is used for the identity distinction feature parameters of the moving objects. To examine proposed method in this paper, image of moving cars are obtained by setting up three cameras at different places every 1 km on outer motorway. The simulation results of identity distinction show that it is possible to distinct the identity a distance in between normalization levels of a hue distribution chart without background.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.5
• /
• pp.149-156
• /
• 2019

The existing subtract image based intrusion detection system for CCTV digital images has a problem that it can not distinguish intruders from moving backgrounds that exist in the natural environment. In this paper, we tried to solve the problems of existing system by designing real - time intrusion detection system for CCTV digital image by combining subtract image based intrusion detection method and background learning artificial neural network technology. Our proposed system consists of three steps: subtract image based intrusion detection, background artificial neural network learning stage, and background artificial neural network evaluation stage. The final intrusion detection result is a combination of result of the subtract image based intrusion detection and the final intrusion detection result of the background artificial neural network. The step of subtract image based intrusion detection is a step of determining the occurrence of intrusion by obtaining a difference image between the background cumulative average image and the current frame image. In the background artificial neural network learning, the background is learned in a situation in which no intrusion occurs, and it is learned by dividing into a detection window unit set by the user. In the background artificial neural network evaluation, the learned background artificial neural network is used to produce background recognition or intrusion detection in the detection window unit. The proposed background learning intrusion detection system is able to detect intrusion more precisely than existing subtract image based intrusion detection system and adaptively execute machine learning on the background so that it can be operated as highly practical intrusion detection system.