Automatic multiple circle detection based on artificial immune systems

Hough transform (HT) has been the most common method for circle detection, exhibiting robustness but adversely demanding a considerable computational load and large storage. Alternative approaches for multiple circle detection include heuristic methods built over iterative optimization procedures which confine the search to only one circle per optimization cycle yielding longer execution times. On the other hand, artificial immune systems (AIS) mimic the behavior of the natural immune system for solving complex optimization problems. The clonal selection algorithm (CSA) is arguably the most widely employed AIS approach. It is an effective search method which optimizes its response according to the relationship between patterns to be identified, i.e. antigens (Ags) and their feasible solutions also known as antibodies (Abs). Although CSA converges to one global optimum, its incorporated CSA-Memory holds valuable information regarding other local minima which have emerged during the optimization process. Accordingly, the detection is considered as a multi-modal optimization problem which supports the detection of multiple circular shapes through only one optimization procedure. The algorithm uses a combination of three non-collinear edge points as parameters to determine circles candidates. A matching function determines if such circle candidates are actually present in the image. Guided by the values of such function, the set of encoded candidate circles are evolved through the CSA so the best candidate (global optimum) can fit into an actual circle within the edge map of the image. Once the optimization process has finished, the CSA-Memory is revisited in order to find other local optima representing potential circle candidates. The overall approach is a fast multiple-circle detector despite considering complicated conditions in the image.     

Information theoretic novelty detection

We present a novel approach to online change detection problems when the training sample size is small. The proposed approach is based on estimating the expected information content of a new data point and allows an accurate control of the false positive rate even for small data sets. In the case of the Gaussian distribution, our approach is analytically tractable and closely related to classical statistical tests. We then propose an approximation scheme to extend our approach to the case of the mixture of Gaussians. We evaluate extensively our approach on synthetic data and on three real benchmark data sets. The experimental validation shows that our method maintains a good overall accuracy, but significantly improves the control over the false positive rate.     

3D face detection using curvature analysis

Face detection is a crucial preliminary in many applications. Most of the approaches to face detection have focused on the use of two-dimensional images. We present an innovative method that combines a feature-based approach with a holistic one for three-dimensional (3D) face detection. Salient face features, such as the eyes and nose, are detected through an analysis of the curvature of the surface. Each triplet consisting of a candidate nose and two candidate eyes is processed by a PCA-based classifier trained to discriminate between faces and non-faces. The method has been tested, with good results, on some 150 3D faces acquired by a laser range scanner.     

Dark-spot detection from SAR intensity imagery with spatial density thresholding for oil-spill monitoring

Dark-spot detection is a critical and fundamental step in marine oil-spill detection and monitoring. In this paper, a novel approach for automated dark-spot detection using synthetic aperture radar (SAR) intensity imagery is presented. The key to the approach is making use of a spatial density feature to differentiate between dark spots and the background. A detection window is passed through the entire SAR image. First, intensity threshold segmentation is applied to each window. Pixels with intensities below the threshold are regarded as potential dark-spot pixels while the others are potential background pixels. Second, the density of potential background pixels is estimated using kernel density estimation within each window. Pixels with densities below a certain threshold are the real dark-spot pixels. Third, an area threshold and a contrast threshold are used to eliminate any remaining false targets. In the last step, the individual detection results are mosaicked to produce the final result. The proposed approach was tested on 60 RADARSAT-1 ScanSAR intensity images which contain verified oil-spill anomalies. The same parameters were used in all tests. For the overall dataset, the average of commission error, omission error, and average difference were 7.0%, 6.1%, and 0.4 pixels, respectively. The average number of false alarms was 0.5 per unit image and the average computational time for a detection window was 1.2 s using a PC-based MATLAB platform. Our experimental results demonstrate that the proposed approach is fast, robust and effective.     

基于离散曲率熵的徘徊行为检测

针对公共重点区域的智能监视问题,提出了一种新的徘徊行为异常检测方法。该方法利用视频目标跟踪算法得到可疑行人的运动轨迹,通过曲线拟合对运动目标的离散点轨迹进行平滑,计算离散点的离散曲率,计算感兴趣区域内运动目标轨迹点的离散曲率的熵及方差,通过离散熵阈值比较进行徘徊行为判断,该方法只需计算运动目标的轨迹,无需建立样本库,实验证明了该方法的有效性、实时性。     

使用多弦长曲率多项式的角点检测算法

在弦到点的距离累加(CPDA)技术和曲率积的基础上,提出了多弦长曲率多项式的角点检测算法。首先利用Canny边缘检测器抽取边缘,然后对于不同弦长下边缘轮廓曲率局部极大值点,计算曲率的和;对于非极值点,计算曲率的积。该方法不仅可以显著增强曲率极值点的峰值,而且避免了曲率积对一些角点平滑。最后,为了降低人为设定门限带来的错检或漏检,利用局部自适应阈值去判别角点。实验结果表明,与其他的角点检测算法相比,该方法具有很强的鲁棒性,它的平均检测准确率提高了14.5%,而且在角点数重复率准则上平均性能提高了12.6%。     

融合前景判别和圆形搜索的目标跟踪算法

针对运动目标在发生遮挡、形变、旋转和光照等变化时会导致跟踪误差大甚至丢失目标以及传统跟踪算法实时性差的问题,提出了一种融合前景判别和圆形搜索（CS）的目标跟踪算法。该算法采用了图像感知哈希技术来描述与匹配跟踪目标,跟踪过程使用了两种跟踪策略相结合的方法,能够有效地解决上述问题。首先,根据目标运动方向的不确定性和帧间目标运动的缓慢性,通过CS算法搜索当前帧局部（目标周围）最佳匹配位置;然后,采用前景判别PBAS算法搜索当前帧全局最优目标前景;最终,选取两者与目标模板相似度更高者为跟踪结果,并根据匹配阈值判断是否更新目标模板。实验结果表明,所提算法在精度、准确率和实时性上都比MeanShift算法更好,在目标非快速运动时有较好的跟踪优势。     

用两步Hough变换检测圆

Hough变换在图像处理中占有重要地位,是一种检测曲线的有效方法。但使用传统的Hough变换来检测圆,具有存储空间大计算时间长的缺点。为此提出了采用两步Hough变换的圆检测方法,利用圆的斜率特性,降低了Hough参数空间的维度,提高了运算效率,并推广到椭圆的检测之中。     

A new algorithm for ball recognition using circle Hough transform and neural classifier

A large number of methods for circle detection have been studied in the last years for several image processing applications. The context application considered in this work is the soccer game. In the sequences of soccer images it is very important to identify the ball in order to verify the goal event. This domain is a challenging one as a great number of problems have to be faced, such as occlusions, shadows, objects similar to the ball, real-time processing and so on. In this work a visual framework trying to solve the above-stated problems, mainly considering real-time computational aspects, has been developed. The ball detection algorithm has to be very simple in terms of time processing and also has to be efficient in terms of false positive rate. Our framework consists of two sequential steps for solving the ball recognition problem: the first step uses a modified version of the directional circle Hough transform to detect the region of the image that is the best candidate to contain the ball; in the second step a neural classifier is applied on the selected region to confirm if the ball has been properly detected or a false positive has been found. Some tricks like background subtraction and ball tracking have been applied in order to maintain the search of the ball only in limited areas of the image. Different light conditions have been considered as they introduce strong modifications on the appearance of the ball in the image: when the image sequences are taken with natural light, as the light source is strictly directional, the ball, due to self-shades, appears as a spherical cap; this case has been taken in account and the search of the ball has been modified in order to manage this situation. A large number of experiments have been carried out showing that the proposed method obtains a high detection score.     

改进的曲率尺度空间角点检测

在曲率尺度空间（CSS）角点检测中,通常采用高斯滤波对图像进行去噪处理。但该方法很大程度上降低了角点检测的准确性和精确性,因此,提出了利用双边滤波来改进的CSS角点检测算法,可以在很好去噪的同时又保证角点检测的高精度。实验结果也充分验证了该算法较其他算法具有的高效性和准确性。     

A new approximation algorithm for labeling points with circle pairs

We study the NP-hard problem of labeling points with maximum-radius circle pairs: given n point sites in the plane, find a placement for 2n interior-disjoint uniform circles, such that each site touches two circles and the circle radius is maximized. We present a new approximation algorithm for this problem that runs in time and O(n) space and achieves an approximation factor of (≈1.486+ε), which improves the previous best bound of 1.491+ε.     

虹膜识别的过零检测循环编码方法

研究了虹膜特征提取和编码识别算法。首先对虹膜图像进行预处理获得归一化的虹膜图像,然后对归一化后的虹膜图像进行高斯平滑滤波和小波过零检测,对得到的特征矩阵通过二次循环编码以得到虹膜的特征值序列,最后通过改进的欧氏距离对虹膜进行判别。实验结果表明,识别率可以达到96.3%。该算法运算简单,能够解决虹膜识别中的旋转不变性问题,得到了较好的识别效果。     

新型亚像素圆检测算法

提出了一种在计算机视觉检测中用于亚像素圆检测的快速新算法,该算法把计算机图形学中的对圆形的生成算法理论引入到视觉检测中,避免了由于亚像素检圆检测带来的计算量大,速度慢的问题。实验表明,该检测方法不仅速度快,精度高,而且抗噪能力强。     

Randomised hough transform with error propagation for line and circle detection

In this paper, we introduce a new Randomised Hough Transform aimed at improving curve detection accuracy and robustness, as well as computational efficiency. Robustness and accuracy improvement is achieved by analytically propagating the errors with image pixels to the estimated curve parameters. The errors with the curve parameters are then used to determine the contribution of pixels to the accumulator array. The computational efficiency is achieved by mapping a set of points near certain selected seed points to the parameter space at a time. Statistically determined, the seed points are points that are most likely located on the curves and that produce the most accurate curve estimation. Further computational advantage is achieved by performing progressive detection. Examples of detection of lines using the proposed technique are given in the paper. The concept can be extended to non-linear curves such as circles and ellipses. ID="A1"Correspondance and offprint requests to: Q. Ji, Department of Electrical, Computer and Systems Engineering, Rensselaer Polytechnic Institute, Troy, NY 12180, USA. E-mail: qji@ecse.rpi.edu     

基于局部曲率函数的角点检测

角点检测是计算机图像处理领域的基本问题之一,在全局曲率函数角点检测的基础上,提出一种基于局部曲率函数的快速角点检测算法.通过Canny算子提取图像的边缘,在边缘的基础上计算轮廓的局部曲率函数,由于Canny算子首先用高斯滤波器对图像平滑处理,尽可能的去除了噪声而不损失角点,计算局部曲率函数的最大峰值,通过设定阈值检测出角点.对算法进行仿真,试验结果表明该算法可以稳定的检测角点,并对旋转、尺度和噪声具有较强的鲁棒性.     

基于最大内切圆的椭圆孔组检测

针对当前一些椭圆孔组工件检测成本高、时效低等问题,提出了一种基于最大内切圆的椭圆孔组检测方法。首先对椭圆孔组图像进行去噪、二值化和边缘检测等预处理;再根据椭圆的几何性质,结合椭圆中心估计方法和最值距离选取方法,求出椭圆最大内切圆,从而确定椭圆的中心坐标、长短轴长和倾斜角。实验数据表明,该方法能对椭圆孔组进行快速精确检测,在估计出椭圆中心的基础上能快速截取有效椭圆弧,大幅减少无效采样;与基于中心估计Hough椭圆检测算法和基于最小二乘改进椭圆检测算法相比,具有耗时短、精度高等优点,可有效应用于椭圆孔组工件的自动化检测。     

基于局部搜索快速随机检测多个圆

以随机采样一个图像点P1的5×5邻域图像点作拟合直线l1,与l1距离为d(d＞0)的平行线l3与l2(l2是通过P1点并垂直于l1的直线)的交叉点为Q,然后以Q为起点,在直线l3上按给定规则搜索两图像点P2和P3,用P1、P2和P3来确定候选圆.当采样和搜索图像点P2、P3时,通过剔除孤立、半连续噪声和非共圆点显著地减少了无效采样和无效计算.数值实验结果表明,该算法能快速检测多个圆.在检测多个圆时,其检测速度比随机圆检测算法快一个数量级;在孤立和半连续噪声不低于所有噪声的80%时,其检测速度比多个圆的快速随机检测算法大约快20%.     

基于Hough变换的汽车零件中圆形检测的改进算法

针对汽车零件中的圆检测实际需求,在分析了基本Hough变换和随机Hough变换进行圆检测的技术特征基础上,对基本Hough变换进行算法改进。采用Sobel算子提取图像边缘,利用圆参数范围已知的先验知识确定感兴趣区域和圆半径的检索范围,使得计算量大大减少,从而实现圆心坐标和半径的快速检测,满足工业生产实时性的要求。     

Stability analysis of the simplest Takagi-Sugeno fuzzy control system using circle criterion

In this paper, we present two sufficient conditions in the frequency domain for the global stability analysis of the simplest Takagi-Sugeno (T-S) fuzzy control system, based on the circle criterion and its graphical interpretation. These conditions are significant in graphically designing the simplest T-S fuzzy controller in the frequency domain. Four numerical examples are provided to demonstrate the efficiency of our two frequency domain-based conditions. Furthermore, this T-S fuzzy controller and the linear proportional controllers are also compared. It is concluded that the simplest T-S fuzzy controller can outperform the linear proportional controllers in a noisy environment with external disturbances.     

A hybrid sequential-parallel approach to accurate circle centre location

This paper studies practical means of accurately locating the centres of circular objects. The Hough transform approach is in many ways ideal but is rather computation intensive if full account is taken of radial and transverse errors. Overcoming this problem seems impossible if a fully parallel solution is required: however, a partly sequential scheme is derived which retains the advantages of the parallel approach, being fast, robust and highly accurate.