• The KIPS Transactions:PartB
• /
• v.15B no.5
• /
• pp.407-412
• /
• 2008

Color segmentation is one of the most challenging problems in image processing especially in case of handling the images with cluttered background. Great amount of color segmentation methods have been developed and applied to real problems. In this paper, we suggest a new methodology. Our approach is focused on background extraction, as a complimentary operation to standard foreground object segmentation, using self-organizing feature selective property of unsupervised self-learning paradigm based on the competitive algorithm. The results of our studies show that background segmentation can be achievable in efficient manner.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.169-171
• /
• 2021

Image processing through cameras such as self-driving, CCTV, mobile phone security, and parking facilities is being used to solve many real-life problems. Simple classification is solved through image processing, but it is difficult to find images or in-image features of complexly mixed objects. To solve this feature point, we utilize deep learning techniques in classification, detection, and segmentation of image data so that we can think and judge closely. Of course, the results are better than just image processing, but we confirm that the results judged by the method of image segmentation using deep learning have deviations from the real object. In this paper, we study how to perform accuracy improvement through simple image processing just before outputting the output of deep learning image segmentation to increase the precision of image segmentation.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.10
• /
• pp.147-153
• /
• 2014

In this paper, we present a non-dyadic lens distortion correction model and image restoration method based on local self-similarity to remove jagging and blurring artifacts in the peripheral region of the geometrically corrected image. The proposed method can be applied in various application areas including vehicle real-view cameras, visual surveillance systems, and medical imaging systems.

• Archives of design research
• /
• v.15 no.4
• /
• pp.169-176
• /
• 2002

All kinds of artwork, including multimedia and digital image that has been subliminated into an af mediating two numbers 0 and 1 in recent age, are self-sufficient and autonomous in themselves. Nevertheless, each of those artworks can be realized as a real entity only if its appreciator is capable enough to explore some potential meaning out of it through his or her own perceptual work. According to Mikel Dufrenne, an artwork is composed of three existential tiers: "le sensible" or the sensible material; "fe representation" or the subject(le sujet), and "1′expression." Dufrenne contends that our esthetic perception can be realized by way of three steps that are comparable to those three tiers: perception of the presence of the body("le sensible"), contemplative perception by way of imagination("le representation"), and reflective perception ("1′expression") as a result of dialectics of sense and sensibility. This paper argues on the aesthetic perception with regard to digital image expressed by two numbers 0 and 1, putting focus on the epistemological role of sensibility(감) that explores "1′expression" a la Dufrenne.

• 제어로봇시스템학회:학술대회논문집
• /
• 1994.10a
• /
• pp.601-604
• /
• 1994

This paper describes an effective method to estimate a position of an automous vehicle equipped with a single CCD-camera along indoor passageways. Using the sequential image data from the self-movement of the vehicle, the position is estimated by integrating the approximated motion parameters. The detection of the yaw angle that is one of the motion parameter is difficult in general, e.g. slip or error for noise, therefore the different detection is presented, which is, without shaft encoders, based on a projection function for 2D-image data and a cross-correlation function so as to be robust for noise. The approximated geometric function to estimate the position is used to reduce the computational effort. To verify the effectiveness of the method, the analysis and the computational results are shown through the simulations. Furthermore, the experimental results by using the test vehicle for the real indoor passageway are shown.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.49.6-49
• /
• 2001

This paper describes a self-localization method for the mobile robot using panoramic view images. A panoramic view image has the information of location of the objects from the viewer robot and direction between the objects at a position. Among the sequence of panoramic view images, the target objects in the image like traffic signs, facade of a building, road signs, etc. locate in the real world so that robot´s position and direction deliver to localize from his view. With the previously captured panoramic images, the method calculates the distance and direction of the region of interest, corresponds the regions between the sequences, and identifies the location in the world. To obtain the region, vertical edge line segments

• Proceedings of the KIEE Conference
• /
• 1997.11a
• /
• pp.397-401
• /
• 1997

In this paper, we propose a neural-network that detects moving objects in an image using a diffusion neural network. The proposed neural network is improved by adding a self loop to diffusion layer to remove the noise in an image and to reduce the detection of phantom edge. Computer simulation with real images show that the proposed neural network can extract edges of moving object efficiently.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.2033-2036
• /
• 2004

A novel approach to estimate the real time moving trajectory of an object is proposed in this paper. The object position is obtained from the image data of a CCD camera, while a state estimator predicts the linear and angular velocities of the moving object. To overcome the uncertainties and noises residing in the input data, a Kalman filter and neural networks are utilized. Since the Kalman filter needs to approximate a non-linear system into a linear model to estimate the states, there always exist errors as well as uncertainties again. To resolve this problem, the neural networks are adopted in this approach, which have high adaptability with the memory of the input-output relationship. Kohonen Network(Self-Organized Map) is selected to learn the motion trajectory since it is spatially oriented. The superiority of the proposed algorithm is demonstrated through the real experiments.

• Cross-Cultural Studies
• /
• v.33
• /
• pp.33-52
• /
• 2013

Haizi, who ended his life with suicide on the railroad at the age of 25, is a poet who implemented his unique poetic world alone without belonging to any of the existing Chinese poetry schools in the 1980s. The process that Haizi reveals self-inside through a poetic work is rather to hide self-inside paradoxically, too. Accordingly, even a work of figuring out the real intention, which is hidden in poetic dictions that he selected, will be meaningful. In this sense, this study tried to inquire into the poetic imagination and self-image that were revealed in poetry focusing on "Spring, Haizi of 10 People", which is a work of having his name as topic, with having been written at the time of suicide, among Haizi's many poetic works. In addition, it figured out Haizi's private conscious world through analyzing the poem titled "Facing the sea with spring blossoms", which was created ahead of death same as "Spring, Haizi of 10 People". Thus, the aim was to look back on significance of his death and to broaden the width of understanding about Haizi's poetry. As for Haizi, the death can be regarded as the completion of 'performance,' which is a kind of Haizi's own final art form. Hence, Haizi's suicide needs to be seen from the perspective dubbed the continuity of creation through this performance, not the discontinuance of creation caused by 'intended death' that the poet himself selected. In the wake of pursuing the poetic world of a gifted poet Haizi, who died early, that this study examined, there will be any poet of Korea who is recalled naturally. One poet will be first recalled Yi Sang, who is a poet and a novelist of having been broadly known. Another poet is overlapped Gi Hyeong-do, who had been active as a poet and a journalist of having been dead after living in the similar period to Haizi. A comparative analysis among works by these Korean and Chinese poets has similarity beyond the temporal space. A research on this is thought to have value of being considered a little more deeply and generally hereafter. Still, this study mentioned only possibility of a comparative research on this.

• East Asian mathematical journal
• /
• v.39 no.2
• /
• pp.119-139
• /
• 2023

Most of calculus and real analysis are concerned with the study on continuous functions. Because of self-sustaining concept caused by everyday language, continuity has difficulties. This kind of viewpoint is strengthened with that teacher explains continuity by graph drawn ceaselessly and so finally confused with mathematics concept which is continuity and connection. Thus such a concept image of continuity becomes to include components which create conflicts. Therefore, we try to analyze understanding of continuity on university students by using the concept image as an analytic tool. We survey centering on problems which create conflicts with concept definition and image. And we investigate that difference of definition in continuous function which handles in calculus and analysis exists and so try to present various results on university students' understanding of continuity concept.