肝CT图像中阴影部分的精确检测

肝部阴影是肝癌的重要疑似对象,因此检测肝癌可以先将肝部阴影检测出来.但肝部阴影与正常肝组织密度接近,很难分割.为此,提出一种CV分割方法的初始距离函数的设置方法,该方法使初始曲线一开始就接近图像的分割边缘,极大地减少了CV方法的迭代次数,加快了CV方法目标提取的速度.最后将该方法应用于肝部阴影的精确检测,成功地分割了图像中的肝部组织与其中的阴影部分.     

指纹图像的一种奇异性检测算法

分析了现有的指纹图像奇异性检测方法中存在的问题,提出了新方法。将指纹的方向图转换为类似灰度纹理,用所提出的改进的新纹理特征检测奇异性。实验表明新方法检测奇异性的正确率为90．2％。     

Detection and characterization of junctions in a 2D image

A new junction characterization and validation method is proposed. Junction branches of volumetric objects are extracted at interest points in a 2D image, using a topologically constrained grouping process. This is followed by structural validation and position refinement of extracted junctions. An interesting feature of the proposed method is that all types of junctions are described uniformly and extracted using the same generic process. For instance, the size of the interest regions is kept constant despite local variations in contour density and curvature. Validation rate of real junctions is high and most false hypotheses are properly rejected. An experimental evaluation illustrates the capabilities of the proposed method in demanding situations.     

A discrete geometry approach for dominant point detection

We propose two fast methods for dominant point detection and polygonal representation of noisy and possibly disconnected curves based on a study of the decomposition of the curve into the sequence of maximal blurred segments [2]. Starting from results of discrete geometry [3] and [4], the notion of maximal blurred segment of width ν[2] has been proposed, well adapted to possibly noisy curves. The first method uses a fixed parameter that is the width of considered maximal blurred segments. The second method is deduced from the first one based on a multi-width approach to obtain a non-parametric method that uses no threshold for working with noisy curves. Comparisons with other methods in the literature prove the efficiency of our approach. Thanks to a recent result [5] concerning the construction of the sequence of maximal blurred segments, the complexity of the proposed methods is O(n log n). An application of vectorization is also given in this paper.     

Accurate video text detection through classification of low and high contrast images

Detection of both scene text and graphic text in video images is gaining popularity in the area of information retrieval for efficient indexing and understanding the video. In this paper, we explore a new idea of classifying low contrast and high contrast video images in order to detect accurate boundary of the text lines in video images. In this work, high contrast refers to sharpness while low contrast refers to dim intensity values in the video images. The method introduces heuristic rules based on combination of filters and edge analysis for the classification purpose. The heuristic rules are derived based on the fact that the number of Sobel edge components is more than the number of Canny edge components in the case of high contrast video images, and vice versa for low contrast video images. In order to demonstrate the use of this classification on video text detection, we implement a method based on Sobel edges and texture features for detecting text in video images. Experiments are conducted using video images containing both graphic text and scene text with different fonts, sizes, languages, backgrounds. The results show that the proposed method outperforms existing methods in terms of detection rate, false alarm rate, misdetection rate and inaccurate boundary rate.     

Episode detection in videos captured using a head-mounted camera

With the advent of wearable computing, personal imaging, photojournalism and personal video diaries, the need for automated archiving of the videos captured by them has become quite pressing. The principal device used to capture the human-environment interaction with these devices is a wearable camera (usually a head-mounted camera). The videos obtained from such a camera are raw and unedited versions of the visual interaction of the wearer (the user of the camera) with the surroundings. The focus of our research is to develop post-processing techniques that can automatically abstract videos based on episode detection. An episode is defined as a part of the video that was captured when the user was interested in an external event and paid attention to record it. Our research is based on the assumption that head movements have distinguishable patterns during an episode occurrence and these patterns can be exploited to differentiate between an episode and a non-episode. Here we present a novel algorithm exploiting the head and body behaviour for detecting the episodes. The algorithms performance is measured by comparing the ground truth (user-declared episodes) with the detected episodes. The experiments show the high degree of success we achieved with our proposed method on several hours of head-mounted video captured in varying locations.     

基于匹配点相似度引导采样的图像多平面检测

针对实际广泛存在的具有深度变化的多平面场景,提出一种基于匹配点引导采样的多平面检测算法.根据平面结构中匹配点的相似度改进匹配点的采样规则,通过对匹配点的残差信息进行排序和加权分析,获取场景中各个平面结构对应的单应矩阵,从而实现了场景中多平面区域的准确检测.实验结果表明,与现有典型的算法相比,提出的算法可获得较高的平面检测准确率.     

Vanishing point detection using cascaded 1D Hough Transform from single images

Vanishing point detection algorithms based on 2D histogramming techniques have been employed in a variety of computer vision systems. Previous algorithms achieved some good results but still failed to maintain a balanced performance in both accuracy and time. Recent research (Li et al., 2010) shows that, vanishing point detection could be converted to a 1D histogram search problem, which largely accelerates the procedure. In this paper, we further improve this idea and propose a complete scheme for vanishing point detection from images of the so called “Manhattan world”. We test our algorithm and some commonly used vanishing point detection methods on public database YorkUrbanDB and our own implemented database PKUCampusDB. Our algorithm shows significant performance improvements.     

Pothole detection in asphalt pavement images

Pavement condition assessment is essential when developing road network maintenance programs. In practice, the data collection process is to a large extent automated. However, pavement distress detection (cracks, potholes, etc.) is mostly performed manually, which is labor-intensive and time-consuming. Existing methods either rely on complete 3D surface reconstruction, which comes along with high equipment and computation costs, or make use of acceleration data, which can only provide preliminary and rough condition surveys. In this paper we present a method for automated pothole detection in asphalt pavement images. In the proposed method an image is first segmented into defect and non-defect regions using histogram shape-based thresholding. Based on the geometric properties of a defect region the potential pothole shape is approximated utilizing morphological thinning and elliptic regression. Subsequently, the texture inside a potential defect shape is extracted and compared with the texture of the surrounding non-defect pavement in order to determine if the region of interest represents an actual pothole. This methodology has been implemented in a MATLAB prototype, trained and tested on 120 pavement images. The results show that this method can detect potholes in asphalt pavement images with reasonable accuracy.     

Accurate and efficient curve detection in images: the importance sampling Hough transform

The Hough transform is a well known technique for detecting parametric curves in images. We place a particular group of Hough transforms, the probabilistic Hough transforms, in the framework of importance sampling. This framework suggests a way in which probabilistic Hough transforms can be improved: by specifying a target distribution and weighting the sampled parameters accordingly to make identification of curves easier. We investigate the use of clustering techniques to simultaneously identify multiple curves in the image. We also use probabilistic arguments to develop stopping conditions for the algorithm. Results from applying our method and two popular versions of the Hough transform to both simulated and real data are shown.     

Early fire detection method in video for vessels

New generation vessels are equipped with fire detecting sensors; however, fire may not immediately be detected if it is far away from the sensors. The fire process therefore cannot be recorded. A video-based fire alarm system is developed to overcome the drawbacks of traditional fire detection equipment. This paper presents a video-based flame and smoke detection method for vessels. For flame detection, the dominant flame color lookup table (DFCLT) is created by using the fuzzy c-means clustering algorithm. The changed video frames are automatically selected and the changed regions deduced from these frames. An elementary, medium, or emergency flame alarm is then triggered by comparing the pixels of changed regions with the DFCLT. The changed video frames are automatically selected for smoke detection. The changed regions are deduced from these frames. If the shape of the changed region conforms to the characteristic which the top area is wider than the bottom area, a dangerous smoke alarm is sounded. The experimental results show that the proposed fire detection approach can detect dangerous flames and smoke, effectively and efficiently.     

Accurate ball detection in soccer images using probabilistic analysis of salient regions

Automatic sport video analysis has became one of the most attractive research fields in the areas of computer vision and multimedia technologies. In particular, there has been a boom in soccer video analysis research. This paper presents a new multi-step algorithm to automatically detect the soccer ball in image sequences acquired from static cameras. In each image, candidate ball regions are selected by analyzing edge circularity and then ball patterns are extracted representing locally affine invariant regions around distinctive points which have been highlighted automatically. The effectiveness of the proposed methodologies is demonstrated through a huge number of experiments using real balls under challenging conditions, as well as a favorable comparison with some of the leading approaches from the literature.     

A new method for linear feature and junction enhancement in 2D images based on morphological operation,oriented anisotropic Gaussian function and Hessian information

Feature enhancement is an important preprocessing step in many image processing tasks. It is the process of adjusting image intensities so that the enhanced results are more suitable for analysis. Good enhancement results for linear structures such as vessels or neurites can be used as inputs for segmentation and other operations. In this paper, a novel linear feature enhancement filter – an adaptive multi-scale morpho-Gaussian filter – which can enhance and smooth linear features is proposed based on morphological operation, anisotropic Gaussian function and Hessian information. This filter can enhance and smooth along the local orientation of the linear structures and the Hessian measurement is used to further enhance the linear features. We utilize the Hessian matrix to calculate the orientation information for our directional morphological operation and the oriented anisotropic Gaussian smoothing. We also propose a novel method for junction enhancement, which can solve the problem of junction suppression. We decompose the junctions and enhance along each linear structure within a junction region. We present the test results of our algorithm on images of different types and compare our method with three existing methods. The experimental results show that the proposed approach can achieve better results.     

Crease detection from fingerprint images and its applications in elderly people

Conventional algorithms for fingerprint recognition are mainly based on minutiae information. But it is difficult to extract minutiae accurately and robustly for elderly people, and one of the main reasons is that there are many creases on the fingertips of elderly people. In this paper, we study on the detection of creases from fingerprint images, in which we treat the creases as a special kind of texture and design an optimal filter to extract them. We also study the applications of crease detection results to improve the performance of fingerprint recognition in elderly people, which include two aspects. First, it is used to remove the falsely detected minutiae. Second, the creases can be treated as a novel feature for elderly people's fingerprints, which is combined with minutiae feature to improve the performance. Experimental results illustrate the effectiveness of proposed methods.     

基于直线检测算法的卫星图片中建筑物轮廓提取

提出一种方法,可以从卫星图像中自动检测建筑物.介绍了直线提取和直线合并的算法,分别讨论算法的实现结果和对结果的评价.建筑物检测的结果为矢量的二维候选数据,缩短了原始图像数据和最后对图像理解之间的差距.     

Accurate discovery of co-derivative documents via duplicate text detection

Documents are co-derivative if they share content: for two documents to be co-derived, some portion of one must be derived from the other, or some portion of both must be derived from a third document. An existing technique for concurrently detecting all co-derivatives in a collection is document fingerprinting, which matches documents based on the hash values of selected document subsequences, or chunks. Fingerprinting is hampered by an inability to accurately isolate information that is useful in identifying co-derivatives. In this paper we present spex, a novel hash-based algorithm for extracting duplicated chunks from a document collection. We discuss how information about shared chunks can be used for efficiently and reliably identifying co-derivative clusters, and describe deco, a prototype package that combines the spex algorithm with other optimisations and compressed indexing to produce a flexible and scalable co-derivative discovery system. Our experiments with multi-gigabyte document collections demonstrate the effectiveness of the approach.     

基于光学图像的舰船航迹检测

舰船航迹检测在海上交通管制和军事领域中有着广泛的应用前景．现有的航迹检测方法大都基于SAR图像，信息不直观而且算法复杂．提出了一种新颖的基于光学图像的航迹检测方法．首先利用纹理分析方法判断待检测区域中是否含有航迹，然后在通过判断的区域中使用条纹增强算法，凸现航迹特征，最后使用Radon变换检测航迹，并对结果进行了优化．与现有的检测方法相比，该方法针对性强，复杂度低．使用该方法对实际航拍图片进行了检测实验，取得了很好的效果．     

Real-time detection of steam in video images

In this paper, we present a real-time image processing technique for the detection of steam in video images. The assumption made is that the presence of steam acts as a blurring process, which changes the local texture pattern of an image while reducing the amount of details. The problem of detecting steam is treated as a supervised pattern recognition problem. A statistical hidden Markov tree (HMT) model derived from the coefficients of the dual-tree complex wavelet transform (DT-CWT) in small 48×48 local regions of the image frames is used to characterize the steam texture pattern. The parameters of the HMT model are used as an input feature vector to a support vector machine (SVM) technique, specially tailored for this purpose. By detecting and determining the total area covered by steam in a video frame, a computerized image processing system can automatically decide if the frame can be used for further analysis. The proposed method was quantitatively evaluated by using a labelled image data set with video frames sampled from a real oil sand video stream. The classification results were 90% correct when compared to human labelled image frames. The technique is useful as a pre-processing step in automated image processing systems.     

一种新的全局指纹图像参考点检测算法

提出了一种全局指纹图像参考点检测算法,首先计算指纹的下曲率值,然后建立一个参考点检测模型,利用下曲率最大的优化方法确定参考点。还提出了一种估计参考点的算法,当参考点在图像的外面时,算法可以估计出参考点的位置。实验结果显示,算法不仅精度比传统的PI算法高,而且也比PI稳健,可以检测出拱形指纹的参考点,而PI算法则不能。     

Hough transform for feature detection in panoramic images

Omni-directional sensors are useful in obtaining a 360° field-of-view. With a radially symmetric mirror and conventional lens system this can be achieved with a single camera. There are several proposed profiles for the mirror, but most violate the single viewpoint (SVP) criteria necessary to allow functional equivalence to the standard perspective projection, posing challenges that have not yet been addressed in the literature. Such a imaging system with a non-SVP optical system do not benefit from the affine quality of straight line features being represented as collinear points in the image plane. To utilize these non-SVP mirrors, a new method to recognize such features is required. This work describes an approach to detecting features in panoramic non-SVP images using a modified Hough transform. A mathematical model for this feature extraction process is given. Experimental results are presented to validate this model and show robust performance in identifying line features with only estimated calibration.