基于改进傅里叶描绘子的CBIR系统

在现有的基于傅里叶描绘子的CBIR系统中,为了提高检索速度,一般需要舍去物体轮廓经傅里叶变换后的大部分高频分量.当物体轮廓在细节部分具有较高能量时,此方法不具备有效性.为尽可能保证检索准确率并兼顾检索速度,在原有傅里叶描绘子上进行扩展,避免直接舍去高频分量,引入Fisher判别分析法将描绘子映射到子空间进行降维,并保证...     

SIFT在行星表面探测器视觉导航系统中的应用

介绍了行星探测器自主导航系统的相关背景,讨论了行星探测器自主视觉导航系统算法的主要目的和传感器信息融合的必要性,并就此引入了尺度不变特征变换(SIFT)的相关理论分析.对SIFT方法提出了改进,从而改善了算法的效果.最后给出了三维重建和目标追踪的实验结果.     

A numerical modelling for the extraction of decay regions from color images of monuments

An innovative application focused on the segmentation of decay zones from images of stone materials is presented. The adopted numerical approach to extract decay regions from the color images of monuments provides a tool that helps experts analyze degraded regions by contouring them. In this way even if the results of the proposed procedure depend on the evaluation of experts, the approach can be a contribution to improving the efficiency of the boundary detection process. The segmentation is a process that allows an image to be divided into disjoint zones so that partitioned zones contain homogeneous characteristics. The numerical method, used to segment color images, is based on the theory of interface evolution, which is described by the eikonal equation. We adopted the fast marching technique to solve the upwind finite difference approximation of the eikonal equation. The fast marching starts from a seed point in the region of interest and generates a front which evolves according to a specific speed function until the boundary of the region is identified. We describe the segmentation results obtained with two speed functions, attained by the image gradient computation and color information about the object of interest. Moreover, we present the extension of the working modality of the method by introducing the possibility to extract the regions not only in a local way but also in a global way on the entire image. In this case, in order to improve the segmentation efficiency the application of the fast marching technique starts with more seed points defined as seed regions. The study case concerns the impressive remains of the Roman Theatre in the city of Aosta (Italy). In the image segmentation process the color space L^∗a^∗b^∗$L^{\ast }{a}^{\ast }{b}^{\ast }$ is utilized.     

Multi-sensor calibration through iterative registration and fusion

In this paper, a new multi-sensor calibration approach, called iterative registration and fusion (IRF), is presented. The key idea of this approach is to use surfaces reconstructed from multiple point clouds to enhance the registration accuracy and robustness. It calibrates the relative position and orientation of the spatial coordinate systems among multiple sensors by iteratively registering the discrete 3D sensor data against an evolving reconstructed B-spline surface, which results from the Kalman filter-based multi-sensor data fusion. Upon each registration, the sensor data gets closer to the surface. Upon fusing the newly registered sensor data with the surface, the updated surface represents the sensor data more accurately. We prove that such an iterative registration and fusion process is guaranteed to converge. We further demonstrate in experiments that the IRF can result in more accurate and more stable calibration than many classical point cloud registration methods.     

A genetic algorithm with gene rearrangement for K-means clustering

In this paper, a new clustering algorithm based on genetic algorithm (GA) with gene rearrangement (GAGR) is proposed, which in application may effectively remove the degeneracy for the purpose of a more efficient search. A new crossover operator that exploits a measure of similarity between chromosomes in a population is also presented. Adaptive probabilities of crossover and mutation are employed to prevent the convergence of the GAGR to a local optimum. Using the real-world data sets, we compare the performance of our GAGR clustering algorithm with K-means algorithm and other GA methods. An application of the GAGR clustering algorithm in unsupervised classification of multispectral remote sensing images is also provided. Experiment results demonstrate that the GAGR clustering algorithm has high performance, effectiveness and flexibility.     

Learning a color distance metric for region-based image segmentation

In this paper we describe an experiment where we studied empirically the application of a learned distance metric to be used as discrimination function for an established color image segmentation algorithm. For this purpose we chose the Mumford–Shah energy functional and the Mahalanobis distance metric. The objective was to test our approach in an objective and quantifiable way on this specific algorithm employing this particular distance model, without making generalization claims. The empirical validation of the results was performed in two experiments: one applying the resulting segmentation method on a subset of the Berkeley Image Database, an exemplar image set possessing ground-truths and validating the results against the ground-truths using two well-known inter-cluster validation methods, namely, the Rand and BGM indexes, and another experiment using images of the same context divided into training and testing set, where the distance metric is learned from the training set and then applied to segment all the images. The obtained results suggest that the use of the specified learned distance metric provides better and more robust segmentations, even if no other modification of the segmentation algorithm is performed.     

Self-consistent gradient flow for shape optimization

We present a model for image segmentation and describe a gradient-descent method for level-set based shape optimization. It is commonly known that gradient-descent methods converge slowly due to zig–zag movement. This can also be observed for our problem, especially when sharp edges are present in the image. We interpret this in our specific context to gain a better understanding of the involved difficulties. One way to overcome slow convergence is the use of second-order methods. For our situation, they require derivatives of the potentially noisy image data and are thus undesirable. Hence, we propose a new method that can be interpreted as a self-consistent gradient flow and does not need any derivatives of the image data. It works very well in practice and leads to a far more efficient optimization algorithm. A related idea can also be used to describe the mean-curvature flow of a mean-convex surface. For this, we formulate a mean-curvature Eikonal equation, which allows a numerical propagation of the mean-curvature flow of a surface without explicit time stepping.     

A New Medical Image Enhancement Based on Human Visual Characteristics

Study of image enhancement shows that the quality of image heavily relies on human visual system. In this paper, we apply this fact effectively to design a new image enhancement method for medical images that improves the detail regions. First, the eye region of interest （ROI） is segmented; then the Un-sharp Masking （USM） is used to enhance the detail regions. Experiments show that the proposed method can effectively improve the accuracy of medical image enhancement and has a significant effect.