• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.968-970
• /
• 1995

The Information Diffusion Neural Networks is proposed to regenerate the 3-dimensional terrain elevation data from contour lines. Contours in paper map are an expression of terrain elevation in highly compressed form. A real time regeneration of terrain data for each grid points from the the contour information is required for various applications. In the proposed neural networks, the elevation information on contours is diffused to neighbor units through updating its output toward that of neighbor units. An interpolation of terrain information is achieved from such computation mechanithm. Terrain data regeneration simulation has been done with sampled terrain data on contour lines.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.2 no.2
• /
• pp.1-8
• /
• 1999

Information representing the thickness of the original lines from the thinning results can be used efficiently in order to implement the automated vectorizing system. This paper proposes a preprocessing scheme of thinning which can show the information of the original lines' thickness from the thinning result. In the proposed scheme, the depth of each pixel constructing the lines was calculated, which was represented by the number of layers composed of neighboring pixels surrounding the original pixel. And then the original lines' thickness could be recognized through the depth information of the skeleton from the thinning results. We implemented the proposed scheme and experimented on a contour map. Using the depth information of the skeleton, we could easily distinguish each line of the contour either an intermediate or an index contour.

• Journal of Advanced Navigation Technology
• /
• v.5 no.2
• /
• pp.123-133
• /
• 2001

The existing visualization methods using the satellite images or map images require complicated preprocessing stages and a large amount of visual data to represent the 3-D terrain. This paper presents a 3-D visualization method for geographical information, which enables automatic generation of 3-D terrain. It is generated based, on contour information obtained from a numerical map. This paper also introduces a method that resolves the three main problems needed to visualize 3-D terrain from contour lines such as correspondence, tiling, and branching. The virtual contour line is defined to extend a distorted contour line to have a similar shape to the corresponding contour line that is used, to generate 3-D surfaces. It helps that 3-D terrain is represented exactly and in detail.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.934-936
• /
• 1995

To get a good result of the feature-based stereo matching, contour of buildings must be extracted exactly. In this paper, an algorithm that extracts contour of flat top buildings exactly is proposed. The Algorithm is composed of three steps. One is to find corner points of 4 types in whole image and another is to extract exact lines between coners by edge following technique, the third is to extract exact contour of buildings using binding structures. We have a good result in extracting contour of buildings.

• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.4
• /
• pp.7-16
• /
• 2002

En this paper, we propose the algorithm that has analyzed the map Information automatically to extract the contour lines and numbers, symbols from the map image. After converting the input image to binary one, thinned image is obtained by thinning algorithm. The contour elements in the thinned image are classified and the classified elements are analyzed to automatically classify the numbers from symbols. Finally, the broken parts are restored by reconstruction algorithm. The performance of proposed algorithm is verified through the simulation. The proposed one has good performance.

• Journal of Korea Multimedia Society
• /
• v.6 no.2
• /
• pp.230-239
• /
• 2003

This paper presents face recognition algorithm using projection vector reflecting local feature for the area in contour lines. The outline shape of a face has many difficulties to distinguish people because human has similar face shape. For 3 dimensional(3D) face images include depth information, we can extract different face shapes from the nose tip using some depth values for a face image. In this thesis deals with 3D face image, because the extraction of contour lines from 2 dimensional face images is hard work. After finding nose tip, we extract two areas in the contour lilies from some depth values from 3D face image which is obtained by 3D laser scanner. And we propose a method of projection vector to localize the characteristics of image and reduce the number of index data in database. Euclidean distance is used to compare of similarity between two images. Proposed algorithm can be made recognition rate of 94.3% for face shapes using depth information.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.6 no.2
• /
• pp.243-248
• /
• 2011

In this paper, we propose a new method to extract palm lines and read it with simple techniques from one photo. We use morphological information and 8-directional contour tracking algorithm. From the digitalized image, we transform original RGB information to YCbCr color model which is less sensitive to the brightness information. The palm region is extracted by simple threshold as Y:65~255, Cb:25~255, Cr:130~255 of skin color. Noise removal process is then followed with morphological information of the palm such that the palm area has more than quarter of the pixels and the rate of width vs height is more than 2:1 and 8-directional contour tracking algorithm. Then, the stretching algorithm and Sobel mask are applied to extract edges. Another morphological information that the meaningful edges(palm lines) have between 10 and 20 pixels is used to exclude noise edges and boundary lines of the hand from block binarized image. Main palm lines are extracted then by labeling method. This algorithm is quite effective even reading the palm from a photographed by a mobile phone, which suggests that this method could be used in various applications.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.4
• /
• pp.101-109
• /
• 2014

It is an essential element for the establishment of image processing related systems to find the exact contour from the image of an arbitrary object. In particular, if a vision system is established to inspect the products in the automated production process, it is very important to detect the contours for standardized shapes such lines and curves. In this paper, we propose a prototype adaptive dynamic contour model, p-Snake with improved contour extraction algorithms by adding the prototype energy. The proposed method is to find the initial contour by applying the existing Snake algorithm after Sobel operation is performed for prototype analysis. Next, the final contour of the object is detected by analyzing prototypes such as lines and circles, defining prototype energy and using it as an additional energy item in the existing Snake function on the basis of information on initial contour. We performed experiments on 340 images obtained by using an environment that duplicated the background of an industrial site. It was found that even if objects are not clearly distinguished from the background due to noise and lighting or the edges being insufficiently visible in the images, the contour can be extracted. In addition, in the case of similarity which is the measure representing how much it matches the prototype, the prototype similarity of contour extracted from the proposed p-ACM is superior to that of ACM by 9.85%.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.6
• /
• pp.160-166
• /
• 2004

In this study, a new algorithm, named as Contour Offset Algorithm(COA) is developed to fabricate precise features or patterns in the range of several micrometers by nano replication printing(nRP) process. In the nRP process, a femto-second laser is scanned on a photosensitive monomer resin in order to induce polymerization of the liquid monomer according to a voxel matrix which is transformed from the bitmap format file. After polymerization, a droplet of ethanol is dropped to remove the unnecessary remaining liquid resin and then only the polymerized figures with nano-scaled precision are remaining on the glass plate. To obtain more precise replicated features, the contour lines in voxel matrix should be modified considering a voxel size. In this study, the efficiency of the proposed method is shown through two examples in view of accuracy.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.27 no.3
• /
• pp.347-356
• /
• 2003

The characteristics of near wakes of circular cylinders with serrated fins are investigated experimentally using a hot-wire anemometer for various freestream velocities. Near wake structures of the fin tubes are observed using a phase average technique. With increasing fin height and decreasing fin pitch. oscillation of streamwise velocity increases. It file oscillation of lateral velocity decreases. The time averaged V-component velocity distribution of the finned tube is contrary to that of the circular cylinder due to the different strength of entrainment flow. This strength is affected by the distance of (equation omitted) = 1.0 contour lines. (equation omitted) = 1.0 contour line approaches to the wake center line when the fin density is increased. When the distance between (equation omitted) = 1.0 contour lines comes close the shear force should be increased and the flow toward the wake center line can be more strengthened because of the shear force. Factors related to the velocity recovery in the near wake of the finned tube are attributed to tile turbulent intensity, the boundary layer thickness. the position and strength of entrainment process.