• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권4호
• /
• pp.1712-1731
• /
• 2016

In this paper, we propose a novel saliency detection framework via multiple random walks (MRW) which simulate multiple agents on a graph simultaneously. In the MRW system, two agents, which represent the seeds of background and foreground, traverse the graph according to a transition matrix, and interact with each other to achieve a state of equilibrium. The proposed algorithm is divided into three steps. First, an initial segmentation is performed to partition an input image into homogeneous regions (i.e., superpixels) for saliency computation. Based on the regions of image, we construct a graph that the nodes correspond to the superpixels in the image, and the edges between neighboring nodes represent the similarities of the corresponding superpixels. Second, to generate the seeds of background, we first filter out one of the four boundaries that most unlikely belong to the background. The superpixels on each of the three remaining sides of the image will be labeled as the seeds of background. To generate the seeds of foreground, we utilize the center prior that foreground objects tend to appear near the image center. In last step, the seeds of foreground and background are treated as two different agents in multiple random walkers to complete the process of salient object detection. Experimental results on three benchmark databases demonstrate the proposed method performs well when it against the state-of-the-art methods in terms of accuracy and robustness.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권10호
• /
• pp.4976-4994
• /
• 2018

The diffusion-based salient object detection methods have shown excellent detection results and more efficient computation in recent years. However, the current diffusion-based salient object detection methods still have disadvantage of detecting the object appearing at the image boundaries and different scales. To address the above mentioned issues, this paper proposes a multi-scale diffusion-based salient object detection algorithm with background and objectness seeds. In specific, the image is firstly over-segmented at several scales. Secondly, the background and objectness saliency of each superpixel is then calculated and fused in each scale. Thirdly, manifold ranking method is chosen to propagate the Bayessian fusion of background and objectness saliency to the whole image. Finally, the pixel-level saliency map is constructed by weighted summation of saliency values under different scales. We evaluate our salient object detection algorithm with other 24 state-of-the-art methods on four public benchmark datasets, i.e., ASD, SED1, SED2 and SOD. The results show that the proposed method performs favorably against 24 state-of-the-art salient object detection approaches in term of popular measures of PR curve and F-measure. And the visual comparison results also show that our method highlights the salient objects more effectively.

• Journal of Mechanical Science and Technology
• /
• 제16권4호
• /
• pp.427-435
• /
• 2002

This paper presents a development result for image processed tracking system of multiple moving objects based on Kalman filter and a simple window tracking method. The proposed algorithm of foreground detection and background adaptation (FDBA) is composed of three modules: a block checking module(BCM), an object movement prediction module(OMPM), and an adaptive background estimation module (ABEM). The BCM is processed for checking the existence of objects. To speed up the image processing time and to precisely track multiple objects under the object's mergence, a concept of a simple window tracking method is adopted in the OMPM. The ABEM separates the foreground from the background in the reset simple tracking window in the OMPM. It is shown through experimental results that the proposed FDBA algorithm is robustly adaptable to the background variation in a short processing time. Furthermore, it is shown that the proposed method can solve the problems of mergence, cross and split that are brought up in the case of tracking multiple moving objects.

• 한국통신학회논문지
• /
• 제40권9호
• /
• pp.1828-1836
• /
• 2015

객체 추적 알고리즘들은 객체 인식 결과를 이용한 관심영역 설정을 통해 영상 전체에 대한 연산이 수행되는 것을 방지하여 연산량을 줄일 수 있다. 따라서 객체 인식 알고리즘의 정확한 객체 검출은 객체 추적에서 매우 중요한 과정이다. 고정된 카메라를 기반으로 하여 이동하는 객체를 검출 하는 방법으로 배경 차 알고리즘이 널리 사용되어왔고 많은 연구에 의해 배경 모델링 방법이 개선되면서 배경 차 알고리즘의 성능이 개선되었으나 여전히 정확하지 못한 배경 모델링에 의한 객체 오검출의 문제를 가진다. 이에 본 논문에서는 제스쳐 인식에 주로 사용되는 모션 히스토리 이미지 알고리즘을 배경 차 알고리즘과 융합하여 기존의 배경 차 알고리즘이 가지는 문제점을 극복할 수 있는 다중 이동객체 검출 알고리즘을 제안한다. 제안하는 알고리즘은 융합 과정 추가로 수행시간이 다소 길어지나 실시간성을 만족하며 기존의 배경 차 알고리즘에 비해 높은 정확도를 가짐을 실험을 통해 확인하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1999년도 제14차 학술회의논문집
• /
• pp.262-265
• /
• 1999

This paper describes a new method for object extraction necessary for image tracking systems. The extraction method which this paper proposes here is that an M-array is set between a camera and the object and the obtained image including the object and M-array is pro-cessed for extracting the object. The image processing utilizes a characteristic of M-array which is robust to noise. When an M-array is overlapped on the object in background image, the object woud have a part of M-array, which is detected by use of partial correlation between the mosaic image of M-array and the standard M-array. Thus the shape and position of the object are extracted by extracting a common domain of width of high correlation value. Experiments are carried out by using an actual photo of Kumamoto city taken from an airplane as background, and by use of a rectangular and circular object. The results of experiment show a wide application of this method for practical image tracking systems.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2008년도 International Symposium on Remote Sensing
• /
• pp.126-129
• /
• 2008

In this paper, we proposed a method extracting an object from background of the satellite image. The image segmentation techniques have been widely studied for the technology to segment image and to synthesis segment object with other images. Proposed algorithm is to perform the edge detection of a selected object using genetic algorithm. We segment region of object based on detection edge using watershed algorithm. We separated background and object in indefinite region using gradual region merge from segment object. And, we make GUI for the application of the proposed algorithm to various tests. To demonstrate the effectiveness of the proposed method, several analysis on the satellite images are performed.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.1887-1890
• /
• 2003

This paper presents a three-dimensional (3D) head pose estimation algorithm using the stereo image. Given a pair of stereo image, we automatically extract several important facial feature points using the disparity map, the gabor filter and the canny edge detector. To detect the facial feature region , we propose a region dividing method using the disparity map. On the indoor head & shoulder stereo image, a face region has a larger disparity than a background. So we separate a face region from a background by a divergence of disparity. To estimate 3D head pose, we propose a 2D-3D Error Compensated-SVD (EC-SVD) algorithm. We estimate the 3D coordinates of the facial features using the correspondence of a stereo image. We can estimate the head pose of an input image using Error Compensated-SVD (EC-SVD) method. Experimental results show that the proposed method is capable of estimating pose accurately.

• 한국의류산업학회지
• /
• 제8권6호
• /
• pp.672-678
• /
• 2006

This study examines the implications of fashion in self-expression or image management among college students in Korea. Socio-demographic factors are considered in addressing following research questions: why Korean college students seek luxury goods; how they recognize the effects of using luxury goods on their image management; whether or not they have purchased counterfeit luxury goods; and why they buy counterfeit goods. In order to explain the relationship between fashion and social class, the study examines various sociological theories including Erving Goffman's dramaturgical approach. The data were drawn from 1419 students from 10 universities nationwide in 2005. Chi-square analyses yields outcomes as follows: Using luxury goods works as a class symbol that gives the users the image of higher socio-economic background; use of counterfeit luxury goods and its symbolic effects in image management do not have significant relationship with socio-economic background.

• Journal of Information Processing Systems
• /
• 제13권1호
• /
• pp.114-127
• /
• 2017

This paper proposes a color image coding algorithm based on shape-adaptive all phase biorthogonal transform (SA-APBT). This algorithm is implemented through four procedures: color space conversion, image segmentation, shape coding, and texture coding. Region-of-interest (ROI) and background area are obtained by image segmentation. Shape coding uses chain code. The texture coding of the ROI is prior to the background area. SA-APBT and uniform quantization are adopted in texture coding. Compared with the color image coding algorithm based on shape-adaptive discrete cosine transform (SA-DCT) at the same bit rates, experimental results on test color images reveal that the objective quality and subjective effects of the reconstructed images using the proposed algorithm are better, especially at low bit rates. Moreover, the complexity of the proposed algorithm is reduced because of uniform quantization.

• 한국멀티미디어학회논문지
• /
• 제19권8호
• /
• pp.1288-1296
• /
• 2016

The reliable detection of the limited defect in TFT-LCD images is difficult due to the small intensity difference with the background. However, the proposed detection method reliably detects the limited defect by enhancing the TFT-LCD image based on the cumulative histogram and then detecting the defect through the mean and standard deviation of the enhanced image. Notably, an image enhancement using a cumulative histogram increases the intensity contrast between the background and the limited defect, which then allows defects to be detected by using the mean and standard deviation of the enhanced image. Furthermore, through the comparison with the histogram equalization, we confirm that the proposed algorithm suppresses the emphasis of the noise. Experimental comparative results using real TFT-LCD images and pseudo images show that the proposed method detects the limited defect more reliably than conventional methods.