• Journal of Computing Science and Engineering
• /
• v.5 no.3
• /
• pp.161-166
• /
• 2011

We present a fast algorithm for Korean text extraction and segmentation from subway signboards using smart phone sensors in order to minimize computational time and memory usage. The algorithm can be used as preprocessing steps for optical character recognition (OCR): binarization, text location, and segmentation. An image of a signboard captured by smart phone camera while holding smart phone by an arbitrary angle is rotated by the detected angle, as if the image was taken by holding a smart phone horizontally. Binarization is only performed once on the subset of connected components instead of the whole image area, resulting in a large reduction in computational time. Text location is guided by user's marker-line placed over the region of interest in binarized image via smart phone touch screen. Then, text segmentation utilizes the data of connected components received in the binarization step, and cuts the string into individual images for designated characters. The resulting data could be used as OCR input, hence solving the most difficult part of OCR on text area included in natural scene images. The experimental results showed that the binarization algorithm of our method is 3.5 and 3.7 times faster than Niblack and Sauvola adaptive-thresholding algorithms, respectively. In addition, our method achieved better quality than other methods.

• Journal of KIISE:Software and Applications
• /
• v.26 no.11
• /
• pp.1350-1358
• /
• 1999

이 논문에서는 유전밴드 영상신호에 포함되어 있는 지형적 특징을 이용하여 밝기의 변화가 일정하지 않은 유전밴드를 인식하는 방법을 연구하였다. 유전밴드는 동일인을 식별하는데 있어서 지문보다 높은 신뢰성을 가지고 있으므로, 유전밴드 영상에서 유전밴드의 유무와 위치를 자동적으로 검출하는 것은 매우 중요하다. 레인내의 밝기의 변화가 일정한 유전밴드는 미분연산자에 의해 검출할 수 있지만, 밝기의 변화가 일정하지 않은 레인내의 유전밴드는 일반적인 인식방법에 의해서는 검출하기 어렵다. 따라서 유전밴드 영상으로부터 지형적 특징을 추출하고, 이것으로부터 계산한 곡률(curvature)의 크기에 의해 유전밴드를 인식함으로써 레인의 밝기가 변화하는 경우에도 효과적으로 인식하였다.Abstract This paper presents recognition of DNA band using the topographical features of DNA band images. The DNA band provides a more reliable way of identification than fingerprints. Recognition based on differentiation operators can easily detect the DNA band if the brightness of lane in the image is almost uniform. When the brightness of the lane changes gradually, the DNA bands are hard to be recognized. Using the curvature magnitude of the lane computed from topographic features extracted from DNA images, the DNA bands are efficiently recognized in the lane whose brightness changes.

• Journal of KIISE:Computing Practices and Letters
• /
• v.8 no.1
• /
• pp.116-125
• /
• 2002

This paper presented a method of extracting shape information from a clipart image and then measured the similarity between clipart images using the extracted shape information. The results indicated that the outlines of the extracted clipart images were clearer that those of the original images. Previous methods of extracting shape information could be classified into outline-based methods and region-based methods. Included in the former category, the proposed method expressed the convex and concave aspects of an outline using the ratio of a rectangle. Accordingly, the proposed method was superior in expressing shape information than previous outline-based feature methods.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.1
• /
• pp.90-94
• /
• 2010

In this paper, we propose a vehicle tracking method that can be applied in the intelligent traffic information system. The proposed method mainly consists of two steps: overlap removal and background updating. In order to remove overlap, we detect the overlap based on the location of the vehicle from successive images. Background updating is to calculate a background using statistical analysis of successive images. We collected a set of test images from the traffic monitoring system and experimented. The experimental results show more than 96% of tracking accuracy.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.374-376
• /
• 1999

본 논문은 연속적인 영상에서 움직이는 물체의 광류를 예측하는데 있어서 웨이브릿과 에피폴라 평면(Epipolar-Plane Images, EPI)을 사용하여 물체의 움직임을 분석하는 기법을 제안한다. 하나의 영상에서 물체의 특징을 찾는데 2차 웨이브릿 변환이 사용되고 있으나 연적인 영상에 대한 분석에서 시간에 대한 또 하나의 변환을 해 줌으로서 움직이는 물체의 정보를 얻어낼 수 있다. 3차 웨이브릿 변환에서 유도된 데이터를 가지고 만들어지는 에피폴라 평면은 움직이는 물체의 광류를 예측하는데 있어서 기존의 방법보다 시간적으로 절약을 할 수 있다. 특히 서로 다른 방향에 대한 민감성을 보여 주는 웨이브릿 계수들은 움직이는 물체의 광류 예측에 많은 도움을 주고 있다. EPI 분석에서는 물체가 깊이 방향으로 움직이는 경우에도 물체의 각 에지들(edges)의 기울기를 분석함으로서 깊이 방향의 광류를 측정할 수 있다. 본 논문에서 제시한 3차 웨이브릿 변환과 EPI 기법의 조합으로 분석된 실험 결과와 그 전 연구들과의 비교가 마지막 부분에 서술되었다.

• Journal of KIISE:Software and Applications
• /
• v.36 no.11
• /
• pp.947-954
• /
• 2009

This paper proposes a novel method that reconstructs a surfel-based object by using visual hull from multiple images. The surfel is a point primitive that effectively approximates point-set surface. We create the surfel representation of an object from images by combining the LDC(Layered Depth Cube) surfel sampling with the concept of visual hull that represents the approximated shape from input images. Because the surfel representation requires relatively smaller memory resources than the polygonal one and its LDC resolution is freely changed, we can control the reconstruction quality of the target object and acquire the maximal quality on the given memory resource.

• Journal of KIISE:Databases
• /
• v.30 no.2
• /
• pp.134-144
• /
• 2003

Spatial relationships among objects are one of the important ingredients for expressing constraints of an image in image or multimedia retrieval systems. In this paper, we propose a unified image retrieval scheme using spatial relationships among objects and their features. The proposed scheme is especially effective in computing similarity between query image and images in the database. Also, objects and their spatial relationships are captured and annotated in XML. It could give better precision and flexibility in retrieving images from database. Finally, we have implemented a prototype system for retrieving images based on proposed technique and showed some of the experiment results.

• Journal of KIISE:Software and Applications
• /
• v.31 no.3
• /
• pp.276-292
• /
• 2004

In this paper. we present methods that extract lung regions from chest EBT(electron beam tomography) images then segment the extracted lung region into lung lobes. We use histogram based thresholding and mathematical morphology for extracting lung regions. For detecting pulmonary fissures, we use edge detector and knowledge-based search method. We suggest this edge detector, which uses adaptive filter scale, to work very well for real edge and insensitive for edge by noise. Our experiments showed about 95% accuracy or higher in extracting lung regions and about 5 pixel distance error in detecting pulmonary fissures.

• Journal of the Korean earth science society
• /
• v.35 no.5
• /
• pp.375-384
• /
• 2014

The number of students choosing science, technology, engineering, and mathematics (STEM) related careers are declining. Thus it became a worldwide challenge in the $21^{st}$ century. As public images of the engineers are unfavorable and inaccurate, misconceptions and stereotypes about engineers are prevailing. The purpose of this study was to investigate elementary school students' perceived mental and pictorial images of engineers and the nature of engineering work. This study involved 512 fifth and sixth grade students (Boys: 287 and Girls: 225) from four elementary schools at one of metropolitans in South Korea. The Draw An Engineer-Korean version (DAE-K) was developed based on Draw an Engineer (DAE) and Draw a Scientist (DAS), and Song and Kim (1999)'s instruments. A pilot-tested was conducted with 33 elementary students prior to the main study. The students were asked to answer how they think the engineers would be, to draw an engineer at work, and to write the engineer's personal information and the job description. Engineers were perceived as a person fixing, building, manufacturing, working outdoors in labors' clothes such as a robe. Engineers were shown with building tools, robots, airplanes, machines, conveyor belt, etc. Moreover, compared to the scientists, engineers were perceived as less intelligent, less imaginative, and less accurate. The results of this study revealed that elementary school students had a lack of accurate images of engineers. Students' current perceived images of engineers could help educators find the baselines for the future engineering education in elementary schools. In addition, the findings of this study could also contribute to the development of engineering education in terms of gender issues, STEM career choice, and even cultural diversity.

• Journal of KIISE:Databases
• /
• v.29 no.2
• /
• pp.110-118
• /
• 2002

This paper presents a 3-D graphic database system based on XML that supports content-based retrievals of 3-D images, Most of graphics application systems are currently centered around the processing of 2-D images and research works on 3-D graphics are mainly concerned about the visualization aspects of 3-D image. They do not support the semantic modeling of 3-D objects and their spatial relations. In our data model, 3-D images are represented as compositions of 3-D graphic objects with associated spatial relations. Complex 3-D objects are mode]ed using a set of primitive 3-D objects rather than the lines and polygons that are found in traditional graphic systems. This model supports content-based retrievals of scenes containing a particular object or those satisfying certain spatial relations among the objects contained in them. 3-D images are stored in the database as XML documents using 3DGML DTD that are developed for modeling 3-D graphic data. Finally, this paper describes some examples of query executed in our Web-based prototype database system.