Removal of specular reflections from image sequences using feature correspondences

The presence of specular highlights can hide underlying features of a scene within an image and can be problematic in many application scenarios. In particular, this poses a significant challenge for applications where image stitching is used to create a single static image of a scene from inspection footage of pipes, gas tubes, train tracks and concrete structures. Furthermore, they can hide small defects in the images causing them to be missed during inspection. We present a method which exploits additional information in neighbouring frames from video footage to reduce specularity from each frame. The technique first automatically determines frames which contain overlapping regions before the relationship that exists between them is exploited in order to suppress the effects of specular reflections. This results in an image that is free from specular highlights provided there is at least one frame present in the sequence where a given pixel is present in a diffuse form. The method is shown to work well on greyscale as well as colour images and effectively reduces specularity and significantly improves the quality of the stitched image, even in the presence of noise. While applied to the challenge of reducing specularity in inspection videos, the method improves upon the state-of-the-art in specularity removal, and its applications are wide-ranging as a general purpose pre-processing tool.     

基于局部仿射不变特征的宽基线影像匹配

提出了一种基于局部仿射不变量特征的宽基线影像匹配算法。该算法以影像特征点为定位点,使用分层变尺度窗口内的几何和亮度仿射不变量特征实现立体匹配。由于使用局部特征,在较大窗口范围内构造尺度、旋转不变特征,以及将大窗口划分为较小的子区域,因此,该算法具有较高的匹配可靠性、较高的效率和匹配精度。     

Pose and motion recovery from feature correspondences and a digital terrain map

A novel algorithm for pose and motion estimation using corresponding features and a digital terrain map is proposed. Using a digital terrain (or digital elevation) map (DTM/DEM) as a global reference enables the elimination of the ambiguity present in vision-based algorithms for motion recovery. As a consequence, the absolute position and orientation of a camera can be recovered with respect to the external reference frame. In order to do this, the DTM is used to formulate a constraint between corresponding features in two consecutive frames. Explicit reconstruction of the 3D world is not required. When considering a number of feature points, the resulting constraints can be solved using nonlinear optimization in terms of position, orientation, and motion. Such a procedure requires an initial guess of these parameters, which can be obtained from dead-reckoning or any other source. The feasibility of the algorithm is established through extensive experimentation. Performance is compared with a state-of-the-art alternative algorithm, which intermediately reconstructs the 3D structure and then registers it to the DTM. A clear advantage for the novel algorithm is demonstrated in variety of scenarios.     

3D fingerprint reconstruction system using feature correspondences and prior estimated finger model

The paper studies a 3D fingerprint reconstruction technique based on multi-view touchless fingerprint images. This technique offers a solution for 3D fingerprint image generation and application when only multi-view 2D images are available. However, the difficulties and stresses of 3D fingerprint reconstruction are the establishment of feature correspondences based on 2D touchless fingerprint images and the estimation of the finger shape model. In this paper, several popular used features, such as scale invariant feature transformation (SIFT) feature, ridge feature and minutiae, are employed for correspondences establishment. To extract these fingerprint features accurately, an improved fingerprint enhancement method has been proposed by polishing orientation and ridge frequency maps according to the characteristics of 2D touchless fingerprint images. Therefore, correspondences can be established by adopting hierarchical fingerprint matching approaches. Through an analysis of 440 3D point cloud finger data (220 fingers, 2 pictures each) collected by a 3D scanning technique, i.e., the structured light illumination (SLI) method, the finger shape model is estimated. It is found that the binary quadratic function is more suitable for the finger shape model than the other mixed model tested in this paper. In our experiments, the reconstruction accuracy is illustrated by constructing a cylinder. Furthermore, results obtained from different fingerprint feature correspondences are analyzed and compared to show which features are more suitable for 3D fingerprint images generation.     

Local feature extraction network with high correspondences for 3d point cloud registration

Applied Intelligence - 3D point cloud registration is an important task in computer vision. Due to the irregularity of point clouds, it is still a challenging problem to realize the accurate...     

融合特征描述符约束的3维等距模型对应关系计算

目的 为了更准确地构建3维等距模型之间的对应关系,本文提出了一种基于热核签名与波核签名的融合特征描述符计算3维等距模型对应关系的方法。方法 首先计算3维模型Laplace算子获得模型的特征向量和特征值;然后将所得到特征值和特征向量作为基参数分别计算源模型与目标模型的热核签名和波核签名,并将热核签名与波核签名融合为一个新的特征描述符。融合特征描述符作为模型上随机均匀采样点的约束,通过最小值匹配算法得到源模型和目标模型之间的对应关系。结果 实验结果表明,利用融合特征描述符约束进行计算得到的对应关系正确匹配率比热核签名约束计算得到的对应关系匹配率平均提高19.429%,比波核签名约束计算得到的对应关系匹配率平均提高4.857%。结论 本文提出的融合特征描述符适用于计算3维等距模型或近似等距的3维模型之间的对应关系,与单一使用热核签名或波核签名特征描述符相比,可以得到更加准确的对应关系。     

基于力场收敛特征的多姿态人耳识别*

提出了一种通过提取力场收敛特征进行多姿态人耳识别的新方法。首先把人耳图像转换为力场图像,通过计算力场的散度得到人耳收敛特征,然后使用零空间线性判别分析算法进一步提取特征并分类识别。实验结果表明,力场收敛特征比最初基于力场变换的势能阱特征更为稳定,而零空间线性判别分析方法也优于传统的主元分析降维方法,更好地解决了小样本问题,识别率得到进一步提高。该方法能够有效识别多姿态人耳图像。     

一种基于运动特征的快速镜头边界检测方法

提出了一种基于MPEG视频流运动特征的镜头边界检测模糊推理方法。首先提取MPEG视频流中每帧的宏块信息,然后分析这些信息分别得到相似度、相似度差、运动活动性强度差、运动集中度差等,并将它们作为隶属度函数的输入量,按照一定的推理规则得到突变、渐变、无镜头变换三种情况的隶属度值,值最大者决定该帧是何种类型。实验结果表明该方法具有较高的检测精度,而且由于该方法不用对MPEG视频流进行解压缩,因此处理速度快,适合于实时应用场合。     

Rapid speaker ID using discrete MMI feature quantisation

This paper presents a method of rapidly determining speaker identity from a small sample of speech, using a tree-based vector quantiser trained to maximise mutual information (MMI). The method is text-independent and new speakers may be rapidly enrolled. Unlike most conventional hidden Markov model approaches, this method is computationally inexpensive enough to work on a modest integer microprocessor, yet is robust even with only a small amount of test data. Thus speaker identification is rapid in terms of both computational cost and the small amount of test speech necessary to identify the speaker. This paper presents theoretical and experimental results, showing that perfect ID accuracy may be achieved on a 15-speaker corpus using little more than 1 s of text-independent test speech. Also presented is a demonstration of how this method may be used to segment audio data by speaker.     

Force field convergence map and Log-Gabor filter based multi-view ear feature extraction

Based on force field convergence map and Log-Gabor filter, a novel multi-view ear feature extraction approach is proposed. This work first introduces the basic concepts and principles of force field transformation. Then a discussion on why force field convergence map rather than force field transformation is more suitable for multi-view ear feature extraction is given. After getting multi-view ear force field convergence map, Log-Gabor filter is applied to extract multiple scale and multiple orientation features. Finally, to verify the effectiveness of the proposed feature extraction method, different classifiers and different multi-view ear dataset are well utilized, to perform multi-view ear classification task. Experimental results and comparisons show the efficiency and the superiority of the proposed convergence map with the Log-Gabor filter method.     

一种基于脑血管图像特征的快速边界跟踪算法*

在处理复杂的脑血管图像时,经典的边界跟踪算法暴露出边界精度不高、边界不够平滑,且速度不尽人意等缺点。提出了一种新的快速边界跟踪算法,该算法在分析脑血管边缘垂直细节远多于水平细节的特征基础上,结合方向记忆选择搜索方向,并在不同的搜索方向上赋予不同的权值,最终得到下一个边界点。实验表明：该算法提取的脑血管边界平滑、速度快,适合脑血管图像的边界提取,为下一步的脑血管形状特征提取及表示提供了精确的数据准备。     

Robot Self—Location by Line Correspondences

This paper thoroughly investigates the problem of robot self-location by line correspondences.The original cotributions are three-fold:(1) Obtain the necessary and sufficient condition to determine linearly the robot‘s pose by two line correspondences.(2) Show that if the space lines are vertical ones,it is impossible to determine linearly the robot‘s pose no matter how many line correspondences we have,and the minimum number of line correspondences is 3 to determine uniquely (but non-linearly)the robot‘s pose.(3) Show that if the space lines are horizontal ones,the minimum number of line correspondences is 3 for linear determination and 2 for non-linear determination of the robot‘s pose.     

On an assumption guaranteeing boundary layer convergence of singularly perturbed systems

In a recent paper by B. A. Francis, an assumption was made that guaranteed convergence in the boundary layer for singularly perturbed linear systems, but the assumption was not discussed. This note examines this assumption in some detail. Verifiable sufficient and necessary conditions are given. Illustrative examples are presented.     

Integrating feature maps and competitive layer architectures for motion segmentation

We present a generic approach to integrate feature maps with a competitive layer architecture to enable segmentation by a competitive neural dynamics specified in terms of the latent space mappings constructed by the feature maps. We demonstrate the underlying ideas for the case of motion segmentation, using a system that employs Unsupervised Kernel Regression (UKR) for the creation of the feature maps, and the Competitive Layer Model (CLM) for the competitive layer architecture. The UKR feature maps hold learned representations of a set of candidate motions and the CLM dynamics, working on features defined in the UKR domain, implements the segmentation of observed trajectory data according to the competing candidates. We also demonstrate how the introduction of an additional layer can provide the system with a parametrizable rejection mechanism for previously unknown observations. The evaluation on trajectories describing four different letters yields improved classification results compared to our previous, pure manifold approach.     

Flue gas layer feature segmentation based on multi-channel pixel adaptive

Multimedia Tools and Applications - It is very difficult to accurately separate the smoke contour in fire video. Because the scene of a fire is complex and changeable, and there are often many...     

基于BP网络的权值更新快速收敛算法

针对标准BP网络学习算法收敛慢的问题,提出了两种权值更新的快速收敛算法,即基于梯度变化率的快速传递算法和基于梯度方向的弹性传递算法,并在煤矿事故救援游戏式训练系统中进行仿真和比较,让游戏角色根据井下空气成分学习判断危险程度,以便受训人员或仿生机器人采取相应的措施。仿真结果表明,所提算法的收敛时间比标准算法有一定改善。     

Feature correspondences using Morse Smale complex

Establishing corresponding features on two non-rigidly deformed 3D surfaces is a challenging and well-studied problem in computer graphics. Unlike previous approaches that constrain the matching between feature pairs using isometry-invariant distance metrics, we constrain the matching using a discrete connectivity graph derived from the Morse–Smale complex of the Auto Diffusion Function. We observed that the graph remains stable even for surfaces differing by topology or by significant deformation. This algorithm is simple to implement and efficient to run. When tested on a range of examples, our algorithm produces comparable results with state-of-art methods on surfaces with strong isometry but with greatly improved efficiency, and often gets better correspondences on surfaces with larger shape variances.     

基于头皮层特征点的三维头发重用方法

针对在三维头发模型重用过程中,三维头发贴合到不同的人头模型时可能会出现的错位或大小不匹配的问题,提出一种基于头皮层特征点的三维头发重用方法。首先,根据模型文件的数据存储结构,分离出头发模型的头皮层,并提取特征点;其次,结合二维平面图像人脸检测方法,对目标三维人头模型的发根范围进行了特征点提取;然后,根据两个模型的特征点计算出的平移量与缩放系数,对头发模型整体进行了平移与缩放操作;最后,单独对头皮层和人头模型的贴合进行处理。最终能够使三维头发适应目标人头模型,保证头发造型信息无丢失,而且头皮层与人头模型达到了紧密贴合的效果。实验结果表明,该方法能够有效地提高三维头发模型的重用性,并且不受头发模型个性部分和分布区域等限制。     

Structure from motion using line correspondences

A theory is presented for the computation of three-dimensional motion and structure from dynamic imagery, using only line correspondences. The traditional approach of corresponding microfeatures (interesting points-highlights, corners, high-curvature points, etc.) is reviewed and its shortcomings are discussed. Then, a theory is presented that describes a closed form solution to the motion and structure determination problem from line correspondences in three views. The theory is compared with previous ones that are based on nonlinear equations and iterative methods.     

Fingerprint warping using ridge curve correspondences

The performance of a fingerprint matching system is affected by the nonlinear deformation introduced in the fingerprint impression during image acquisition. This nonlinear deformation causes fingerprint features such as minutiae points and ridge curves to be distorted in a complex manner. A technique is presented to estimate the nonlinear distortion in fingerprint pairs based on ridge curve correspondences. The nonlinear distortion, represented using the thin-plate spline (TPS) function, aids in the estimation of an "average" deformation model for a specific finger when several impressions of that finger are available. The estimated average deformation is then utilized to distort the template fingerprint prior to matching it with an input fingerprint. The proposed deformation model based on ridge curves leads to a better alignment of two fingerprint images compared to a deformation model based on minutiae patterns. An index of deformation is proposed for selecting the "optimal" deformation model arising from multiple impressions associated with a finger. Results based on experimental data consisting of 1,600 fingerprints corresponding to 50 different fingers collected over a period of two weeks show that incorporating the proposed deformation model results in an improvement in the matching performance.