Papers by Keyword: Image Segmentation

Paper TitlePage

Authors: Feng Gao, Gang Li, Hiroshi Okada
Abstract: Coronary artery disease is a narrowing of lumen in the coronary artery usually resulting in permanent heart muscle damage or heart attack. Intravascular stents are tubular structures placed into stenotic artery to expand the inside passage and improve blood flow. The mechanical factors affect the restenosis after stenting and image-based simulation has become a popular tool for acquiring information. The study aims to provide physicians with a feasible method for 3D entity reconstruction of coronary stented artery. The coronary artery images derived from patient before and after stenting were processed by Mimics for image segmentation and 3D reconstruction. The coronary blood and wall were constructed, as well as the stented artery model. The model can be used for hemodynamic and fluid structure interaction simulation.
504
Authors: Hong Ke Wang, Xiao Feng Wang
Abstract: 3D reconstruction is used in applications such as virtual reality, digital cinematography and urban planning .The 3D registration is the important part of 3D reconstruction, which is one of outstanding and very basic problems in computer vision. In the paper, considering that there often exist a great number of planes in scenes, we show a planar-feature-based registration method. The planar features from the range image are extracted. Then, we can compute the transformation by SVD between the two coordinate systems and achieve the registration of these two range images.
274
Authors: Xiao Hong Wang, Bin Liu, Zhi Qiang Song
Abstract: Segmentation of brain MRI in an image sequence is one of the most challenging problems in image processing, while at the same time one that finds numerous applications. In this paper, we propose a robust multi-layer background subtraction technique and seed region growing approach which takes advantages of local texture features represented by local binary patterns (LBP) and photometric invariant color measurements in RGB color space. Due to the use of hybridization of layer-based strategy and seed region growing approach, the approach can model moving background pixels with quasiperiodic flickering as well as background scenes which may vary over time due to the addition and removal of long-time stationary objects. The experiment results prove that in the view of the brain MRI segmentation, this algorithm provides fast segmentation with high perceptual segmentation quality.
218
Authors: Li Jun Tian, Da Hui Li
Abstract: The paper shows a segmentation method of Synthetic Aperture Radar (SAR) image. In the method, firstly estimate the different parameters with normal distribution from histogram. Then make different judgment on each pixel. Finally make experiments in many images and the image segmentation results show that the method can reduce noise; it is a feasible method for SAR image segmentation.
509
Authors: Ning Li, Jing Wen Xu, Jun Fang Zhao, Yu Dan Zhao, Peng Hou
Abstract: Image segmentation is the technique and the process to separate the image into regions which have different characteristics and extract the interested objects from the image. Meanwhile, image segmentation is a vital important issue in many fields such as image processing, pattern recognition and artificial intelligence and it has wide application in various fields. This paper performs a great deal of contrastive analysis experiments on a series of images by using improved meanshift software and Edison software. The results show that improved meanshift software is easier to segment clearly than Edison in terms of similar color; the improved meanshift software segmentation is smoother than Edison in image shadow, the segmentation results hold favorable consistency in terms of human perception; the improved meanshift software segmentation is clearer than Edison in texture segmentation such as vegetation. The improved meanshift software has a better effect on the segmentation of boundary, road, etc. Both of them can remove the noise points effectively, but improved meanshift software is more sensitive to brightness; while the Edison software has a faster speed compared to the improved meanshift software.
253
Authors: Song Yang, Long Tan Shao, Xiao Xia Guo, Xiao Liu, Bo Ya Zhao
Abstract: A segmentation method of combining gray-level threshold and fractal feature for crack images is proposed, and the fractal law for the perimeter and area of the target is introduced as the constraint condition for the image segmentation of crack. At first, Otsu algorithm is used for the initial segmentation of the crack image, and then the edge of crack is optimized in accordance with fractal law. At last, boundary of crack is determined, and the final result of the image segmentation is obtained. This method makes full use of the fractal geometry law and image information, to effectively solve the problems such as crack contour detection, regional connection and cross crack identification. Several typical examples are analyzed, and the results show that this method has a good segmentation effect on crack images, and it can also be used to identify the other images which have fractal feature.
622
Authors: Hong Wei Han, Lin Tian, Jia Qing Miao
Abstract: Fuzzy c-means (FCM) algorithm is an unsupervised clustering algorithm for image segmentation, and has been widely applied because the segmentation results are consistent with human visual characteristics. Enhanced fuzzy c-means clustering (EnFCM) algorithm is the improved FCM algorithm, which reduces the computational complexity. But, both FCM algorithm and EnFCM algorithm, clustering number still need to be manually determined. This paper, in order to realize the automation degree of algorithm, presents an improved algorithm. It first analyzes the histogram, then automatically determines the clustering number and peak value of each class through use of the peak point detection technology, finally segments image by using EnFCM algorithm. Experiments show that this method is a kind of faster fuzzy clustering algorithm with automatic classification ability for image segmentation.
1489
Authors: He Qun Qiang, Chun Hua Qian, Sheng Rong Gong
Abstract: According to the problem that classical graph-based image segmentation algorithms are not robust to segmentation of texture image. We propose a novel segmentation algorithm that GBCTRS, which overcame the shortcoming of existed graph-based segmentation algorithms N-cut and EGBIS. It extract feature vector of blocks using color-texture feature, calculate weight between each block using the neighborhood relationship, use minimum spanning tree method to clustering segmentation. The experimental show that the new algorithm is more efficient and robust to segment texture image and strong edges image.
401
Authors: Zhi Bin Zhang, Cai Xia Liu, Xiao Dong Xu
Abstract: Green vegetation segmentation in color images is a fundamental issue for automated remote sensing and machine vision applications, plant ecological assessments, precision crop management, and weed control. A simple green vegetation feature extraction method (GVFE) is proposed in this paper to segment the green vegetation from their non-green backgrounds due to the fact that the green component content is always greater than that of the red and blue in RGB color space. The conventional based-auto-threshold method, ExG (Excess Green) was compared with GVFE, in which a green index ratio was defined to evaluate the performance of them. A digital color image set of single Canna flower taken in natural lighting were used to test them. Experimental results have showed that GVFE has superior performance over ExG+auto-threshold in term of stability, and is insensible to illuminant variations.
660
Authors: Yuan Bin Hou, Yang Meng, Jin Bo Mao
Abstract: According to the requirements of efficient image segmentation for the manipulator self-recognition target, a method of image segmentation based on improved ant colony algorithm is proposed in the paper. In order to avoid segmentation errors by local optimal solution and the stagnation of convergence, ant colony algorithm combined with immune algorithm are taken to traversing the whole image, which uses pheromone as standard. Further, immunization selection through vaccination optimizes the heuristic information, then it improves the efficiency of ergodic process, and shortens the time of segmentation effectively. Simulation and experimental of image segmentation result shows that this algorithm can get better effect than generic ant colony algorithm, at the same condition, segmentation time is shortened by 6.8%.
50
Showing 1 to 10 of 314 Paper Titles