• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.9
• /
• pp.858-862
• /
• 2015

This paper presents a new forward-viewing mono-camera based obstacle detection algorithm for mobile robots. The proposed method extracts the coarse location of an obstacle in an image using inverse perspective mapping technique from sequential images. In the next step, graph-cut based image labeling is conducted for estimating the exact obstacle boundary. The graph-cut based labeling algorithm labels the image pixels as either obstacle or floor as the final outcome. Experiments are performed to verify the obstacle detection performance of the developed algorithm in several examples, including a book, box, towel, and flower pot. The low illumination condition, low color contrast between floor and obstacle, and floor pattern cases are also tested.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.10a
• /
• pp.236-238
• /
• 2003

Human face detection is often the first step in applications such as video surveillance, human computer interface, fare recognition, and image database management. We have constructed a simple and fast system to detect frontal human faces in complex environment and different illumination. This paper presents a fast segmentation method to combine neighboring pixels with similar hue. The algorithm constructs eye, mouth, and boundary maps for verifying each fare candidate. We test the system on images in complex environment and with confusing objects. The experiment shows a robust detection result with few false detected fates.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04b
• /
• pp.592-594
• /
• 2000

변형모델(deformable model)은 볼륨의료영상(volumetric medical image)으로부터 복잡한 인체기관의 3차원적 경계를 분할해내기 위해 효과적인 방법을 제공한다. 그러나, 기존 변형모델은 초기와 의존성, 오목한 경계(concavity) 분할의 비적합성, 그리고 모델내 요소간 자체교차(self-intersection)의 제한점을 가지고 있었다. 본 연구에서는 이러한 제한점을 극복하고, 오목한 구조를 포함하는 복잡한 인체기관의 경계를 분할하기에 적합한 새로운 변형모델을 제안하였다. 제안한 변형모델은 볼륨영상 피라미드(pyramid)를 기반으로 다해상도(multiresolution)의 모델 정제화(refinement)를 수행한다. 다해상도 모델 정제화는 전역적 시셈플링(global resampling) 및 지역적 리샘플링(local resampling)를 통하여 저해상도의 모델로부터 점차 고해상도의 모델로 이동하면서 객체의 경계를 계층적으로 분할해가는 방법이다. 다해상도 모델에 의한 계층적 경계 분할은 초기화 조건에의 의존성을 극복할 수 있게할 뿐 아니라, 빠른 속도로 원하는 객체의 경계에 수렴할 수 있게 한다. 또한 지역적 리샘플링은 모델 구성요소의 정규화를 수행함으로써 객체의 오목한 부분을 성공적으로 분할할 수 있게 한다. 그리고, 제안 모델은 기존 변형모델에서 포함하는 내부 힘(internal force)과 외부 힘(external force)외에 자체교차방지 힘(non-self-intersection force)을 추가함으로서 효과적으로 모델내의 자체교차를 방지할 수 있게 하였다.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.5 s.98
• /
• pp.48-57
• /
• 1999

Applications of thresholding technique are based on the assumption that object and background pixels in a digital image can be distinguished by their gray level values. For the segmentation of more complex images, it is necessary to resort to multiple threshold selection techniques. This paper describes a new method for multiple threshold selection of gray level images which are not clearly distinguishable from the background. The proposed method consists of three main stages. In the first stage, a probability distribution function for a gray level histogram of an image is derived. Cluster points are defined according to the probability distribution function. In the second stage, fuzzy partition matrix of the probability distribution function is generated through the fuzzy clustering process. Finally, elements of the fuzzy partition matrix are classified as clusters according to gray level values by using max-membership method. Boundary values of classified clusters are selected as multiple threshold. In order to verify the performance of the developed algorithm, automatic inspection process of ball grid array is presented.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.11A
• /
• pp.1098-1103
• /
• 2005

The edge and contour information are very much appreciated by the human visual systems and are responsible for our perceptions and recognitions. Therefore, if edge information is integrated during extracting video objects, we can generate boundaries of oects closer to human visual systems for multimedia applications such as interaction between video objects, object-based coding, and representation. Most of object extraction methods are difficult to implement real-time systems due to their iterative and complex arithmetic operations. In this paper, we propose a VLSI architecture integrating edge information to extract video objects for precisely located object boundaries. The proposed architecture can be easily implemented into hardware due to simple arithmetic operations. Also, it can be applied to real-time object extraction for object-oriented multimedia applications.

• Journal of Biomedical Engineering Research
• /
• v.27 no.3
• /
• pp.110-116
• /
• 2006

Finite element method (FEM) provides several advantages over other numerical methods such as boundary element method, since it allows truly volumetric analysis and incorporation of realistic electrical conductivity values. Finite element mesh generation is the first requirement in such in FEM to represent the volumetric domain of interest with numerous finite elements accurately. However, conventional mesh generators and approaches offered by commercial packages do not generate meshes that are content-adaptive to the contents of given images. In this paper, we present software that has been implemented to generate content-adaptive finite element meshes (cMESHes) based on the contents of MR images. The software offers various computational tools for cMESH generation from multi-slice MR images. The software named as the Content-adaptive FE Mesh Generation Toolbox runs under the commercially available technical computation software called Matlab. The major routines in the toolbox include anisotropic filtering of MR images, feature map generation, content-adaptive node generation, Delaunay tessellation, and MRI segmentation for the head conductivity modeling. The presented tools should be useful to researchers who wish to generate efficient mesh models from a set of MR images. The toolbox is available upon request made to the Functional and Metabolic Imaging Center or Bio-imaging Laboratory at Kyung Hee University in Korea.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.6
• /
• pp.1156-1161
• /
• 2007

Edge representing the boundary between two regions with the large briskness difference in mage includes diverse information about object. Therefore, this information has been utilized in fields such as image segmentation and object recognition. There are many kinds of edge according to duration time and the amplitude of brightness variation and edge is generally detected through the differential. Recently, in fields of image processing and computer vision, edge detection methods have been proposed to use in specific applications. Hence, in this paper the wavelet function for improved edge detection properties was proposed and detected line-edge components of images and its performance was proven through simulations.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.6
• /
• pp.1833-1848
• /
• 2022

Named entity recognition (NER) is an important basic task in the field of Natural Language Processing (NLP). Recently deep learning approaches by extracting word segmentation or character features have been proved to be effective for Chinese Named Entity Recognition (CNER). However, since this method of extracting features only focuses on extracting some of the features, it lacks textual information mining from multiple perspectives and dimensions, resulting in the model not being able to fully capture semantic features. To tackle this problem, we propose a novel Multi-view Semantic Feature Fusion Model (MSFM). The proposed model mainly consists of two core components, that is, Multi-view Semantic Feature Fusion Embedding Module (MFEM) and Multi-head Self-Attention Mechanism Module (MSAM). Specifically, the MFEM extracts character features, word boundary features, radical features, and pinyin features of Chinese characters. The acquired font shape, font sound, and font meaning features are fused to enhance the semantic information of Chinese characters with different granularities. Moreover, the MSAM is used to capture the dependencies between characters in a multi-dimensional subspace to better understand the semantic features of the context. Extensive experimental results on four benchmark datasets show that our method improves the overall performance of the CNER model.

• Journal of Biomedical Engineering Research
• /
• v.25 no.3
• /
• pp.189-194
• /
• 2004

Pixel values of contrast enhanced computed tomography (CE-CT) images are randomly changed. Also, the middle liver part has a problem to segregate the liver structure because of similar gray-level values of a pancreas in the abdomen. In this paper, an automatic liver segmentation method using a partial histogram threshold (PHT) algorithm is proposed for overcoming randomness of CE-CT images and removing the pancreas. After histogram transformation, adaptive multi-modal threshold is used to find the range of gray-level values of the liver structure. Also, the PHT algorithm is performed for removing the pancreas. Then, morphological filtering is processed for removing of unnecessary objects and smoothing of the boundary. Four CE-CT slices of eight patients were selected to evaluate the proposed method. As the average of normalized average area of the automatic segmented method II (ASM II) using the PHT and manual segmented method (MSM) are 0.1671 and 0.1711, these two method shows very small differences. Also, the average area error rate between the ASM II and MSM is 6.8339 ％. From the results of experiments, the proposed method has similar performance as the MSM by medical Doctor.

• The Journal of Engineering Geology
• /
• v.19 no.1
• /
• pp.51-61
• /
• 2009

Fractures and segmentation in association with the activities of the Yangsan fault are studied around Mt. Namsan, Gyengju city in the southeastern part of Korea. It is believed that the higher values of joint density and fractal dimension with the approach of the center of the Yangsan fault mean intense fracturing due to the fault activity. The boundary between fault damage zone and host rock is inferred to be placed at about 2.7 km from the center of the Yangsan fault where the values of joint density and fractal dimension abruptly decrease and the orientations of joint are also much dispersed. The small faults within the damage zone of the Yangsan fault are definitely divided into right-lateral and left-lateral strike-slip faults. The former is considered to be formed during the right-lateral movement of the Yangsan fault and the latter during the left-lateral movement. The Yangsan fault is segmented in the study area with obvious evidences as follows: (1) the difference of fault strike between northern and southern segments, (2) The geometry of contractional imbricate fans and syncline plunging $9^{\circ}$, $S85^{\circ}E$ at the end of northern segment, and (3) anticline plunging $28^{\circ}$, $N4^{\circ}W$ at the end of southern segment.