• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1996.06c
• /
• pp.773-779
• /
• 1996

Dried oak mushroom have complex and various visual features. Grading and sorting of dried oak mushrooms has been done by the human expert. Though actions involved in human grading looked simple, a decision making underneath the simple action comes from the result of the complex neural processing of the visual image. Through processing details involved in human visual recognition has not been fully investigated yet, it might say human can recognize objects via one of three ways such as extracting specific features or just image itself without extracting those features or in a combined manner. In most cases, extracting some special quantitative features from the camera image requires complex algorithms and processing of the gray level image requires the heavy computing load. This fact can be worse especially in dealing with nonuniform, irregular and fuzzy shaped agricultural products, resulting in poor performance because of the sensitiveness to the crisp criteria or specific ules set up by algorithms. Also restriction of the real time processing often forces to use binary segmentation but in that case some important information of the object can be lost. In this paper, the neuro net based real time recognition algorithm was proposed without extracting any visual feature but using only the directly captured raw gray images. Specially formated adaptable size of grids was proposed for the network input. The compensation of illumination was also done to accomodate the variable lighting environment. The proposed grading scheme showed very successful results.

• Journal of KIISE
• /
• v.43 no.11
• /
• pp.1298-1306
• /
• 2016

Backlight has a major factor in power consumption of TFT-LCDs which are most popular in portable devices. There have been a lot of attempts to achieve power savings by backlight dimming. At the same time, the researches have shown image compensation due to decreased brightness of a displayed image. However, existing image compensation methods such as histogram equalization have some limits in completely satisfying the human visual system (HVS)-awareness. This paper proposes an enhanced dimming technique to obtain both power saving and HVS-awareness by combining pixel compensation and histogram specification for TFT-LCDs. This method executes a search algorithm and an automation algorithm employing simplified calculations for fast image processing. Experimental results showed that the proposed method achieved significant improvement in visual satisfaction per power saving over existing backlight dimming.

• Proceedings of the KIEE Conference
• /
• 2006.04a
• /
• pp.15-17
• /
• 2006

This paper presents a new global intensity compensation method for extracting moving object in a visual surveillance system by compensating time variant intensity changes of background region. The method that compensates a little changes of intensity due to time variant illumination change and automatic gain control of camera is called global intensity compensation. The proposed method expresses global intensity change with a mapping table to describe complex form of intensity change while the previous method models this global intensity change with a simple function as a straight line. The proposed method builds the mapping table by calculating the cross histogram between two images and then by selecting an initial point for generating the mapping table by using Hough transform applied to the cross histogram image. Then starting from the initial point, the mapping table is generated according to the proposed algorithm based on the assumption that reflects the characteristic of global intensity change. Experimental results show that the proposed method makes the compensation error much smaller than the previous GIC method

• 한국정보디스플레이학회:학술대회논문집
• /
• 2007.08a
• /
• pp.810-813
• /
• 2007

Recently, mobile video communication is getting more and more popular. Visual quality and computational complexity are primary factors affecting performance of video communication. Frame rate up-conversion (FRC) is necessary for achieving high visual quality in mobile projection displays. In this paper, a FRC method using motion compensation based on block matching algorithm (BMA) with adaptive block size is proposed. In order to improve the accuracy of the estimated motion vectors, the motion vector refinement technique is proposed. Experiment results indicate that the proposed technique exhibits better performance with lower hardware complexity compared to the conventional methods.

• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.7
• /
• pp.841-847
• /
• 1999

For successful assembly of flexible parts, informations about their deformation as well as possible misalignments between the holes and their mating parts are essential. Such informations can be acquired from visual sensors. For robotic assembly, the corrective assembly motion to compensate for such misalignments has to be determined from the measured informations. However, this may not be simply derived from the measured misalignment alone because the part deformation progressively occurs during misalignment compensation. Based on the analysis of flexible parts assembly process, this paper presents a neural net-based inference system that can infer the complex relationship between the corrective motion and the measured information of parts deformation and misalignments. And it verifies the performance of the implemented inference system. The results show that the proposed neural net-based misalignment compensation algorithm Is effective in compensating for the lateral misalignment, and that it can be extended to the assembly tasks under more general conditions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.8
• /
• pp.1423-1443
• /
• 2011

Background compensation plays an important role in detecting and isolating object motion in visual tracking. Here, we propose a Genetic Hough Transform, which combines the Hough Transform and Genetic Algorithm, as a method for eliminating background motion. Our method can handle cases in which the background may contain only a few, if any, feature points. These points can be used to estimate the motion between two successive frames. In addition to dealing with featureless backgrounds, our method can successfully handle motion blur. Experimental comparisons of the results obtained using the proposed method with other methods show that the proposed approach yields a satisfactory estimate of background motion.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.10
• /
• pp.1696-1702
• /
• 2008

This paper proposes a voltage compensation device direct control strategy to realize the distributed, autonomous voltage control of the distribution system, which based on voltage data collected from customers of the remote site under the ubiquitous-based distribution system. In the proposed method, The ULTC and the SVR(Step Voltage Regulator)s compensate autonomously the voltage for self-compensation area based on the voltage data furnished from the ubiquitous device of customers. Also, the SVRs overcome the limit of single-operation of ULTC by the interlocking operation with the ULTC and enhance the voltage compensation capability for the customer. In particular, an optimization design method and a fuzzy design method are compared to determine the effective control method of the voltage compensator under the ubiquitous-based on-line operation environments. In fuzzy method, the tap of voltage compensator is defined as output member. Finally, the proposed two methods are implemented in Visual C++ MFC, the effectiveness is proved by simulation based on the worst virtual voltage data. Also, an optimal voltage compensation strategy is determined under on-line environments based on analyzed results.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.1095-1096
• /
• 2008

By adding height compensation to the usual 3 points skew adjustment device, an improved functional skew adjustment device is implemented in this paper. The proposed skew adjustment device is for traverse which will be adapted to BD and HD player system requiring more accuracy. and It can adjust not only R/T skew but also height. The system is composed of personal computer, control box, kinematic mechanism device and bar-code reader device. Application programs are implemented by visual basic.

• The Journal of Korean Academy of Orthopedic Manual Physical Therapy
• /
• v.13 no.2
• /
• pp.31-44
• /
• 2007

The purposes of this study were to examine the normal lumbar proprioception and identify the effect of vision and proprioception on lumbar movement accuracy through measuring a reposition error in visual and non-visual conditions and to provide the basic data for use of vision when rehabilitation program is applied. The subjects of this study were 39 healthy university students who have average physical activity level. They were measured the ability to reproduce the target position(50% of maximal range of motion) of flexion, extension, dominant and non-dominant side flexion in visual and non-visual conditions. Movement accuracy was assessed by reposition error(differences between intended and actual positions) that is calculated by the average of absolute value of 3 repeated measures at each directions. The data were analysed by paired samples t-test, independent samples t-test, and repeated measures ANOVA. The results were as follows : 1. Movement accuracy of flexion, extension, dominant side flexion, and non-dominant side flexion was increased in visual condition. 2. There were no differences in the lumbar movement accuracy between sexes in visual and non-visual conditions. 3. In non-visual condition, the movement in coronal plane(dominant and non dominant side flexion) is more accurate than that in sagittal plane(flexion and extension). 4. In non-visual condition, there were no differences in the lumbar movement accuracy between dominant and non-dominant side flexion. In conclusion, this study demonstrates that the movement is more accurate when the visual information input is available than proprioception is only available. When proprioception is decreased by injury or disease, it disturbs the control of posture and movement. In this case, human controls the posture and movement by using visual compensation. However it is impossible to prevent an injury or trauma because most of injuries occur in an unexpected situation. For this reason, it is important to improve the proprioception. Therefore, proprioceptive training or exercise which improve the ability to control of posture and movement is performed an appropriate control of permission or interception of the visual information input to prevent an excessive visual compensation.

• Journal of the Optical Society of Korea
• /
• v.18 no.1
• /
• pp.89-94
• /
• 2014

It is established that the perceived image contrast is affected by surround luminance. In order to get the same perceived image contrast, the optimum surround compensation ratios for those surround conditions is needed. Much research has been performed for dark, dim, and average surrounds. In this study, a wide range of surround luminance from dark up to $2087cd/m^2$ was considered. Using magnitude estimation method, the change in perceived brightness of six test stimuli was measured under seven surround conditions; dark, dim, 2 levels of average, bright, and 2 levels of over-bright surrounds. To drive the perceived image contrast from the perceived brightness, two different definitions of contrast were tested. Their calculated results were compared with the visual data of our previous work. And to conclude, the perceived contrast compensation ratios were 1:1.11:1.2 for average, dim and dark surrounds. These were close to CIECAM02 model (1:1.17:1.31). Besides, for average, bright, over-bright1 and over-bright2 surrounds the ratios 1:1.17:1.42:1.69 were determined. For intermediate or more extreme surround conditions, the compensation ratio was obtained from the linear interpolation or extrapolation.