A Multi-scale Image Registration Algorithm Based on Wavelet Transform

Multispectral image fusion based on fractal features

Registration of images of different nature is an important technique used in image fusion, change detection, efficient information representation and other problems of computer vision. Solving this task using feature-based approaches is usually more complex than registration of several optical images because traditional feature descriptors (SIFT, SURF, etc.) perform poorly when images have different nature. In this paper we consider the problem of registration of SAR and optical images. We train neural network to build feature point descriptors and use RANSAC algorithm to align found matches. Experimental results are presented that confirm the method’s effectiveness.

위성 SAR 영상의 활용이 증가하면서 영상의 해석 및 융합을 위한 정밀 기하보정에 대한 필요성이 높아지고 있다. 특히 광역감시 목적으로 활용되기 위해 서로 다른 해상도를 갖는 SAR 영상간 정보융합도 활발해지고 있다. 일반적으로 SAR 영상의 기하보정은 위성의 궤도 및 자세정보를 활용하여 수행할 수 있지만 SAR 센서의 궤도 및 시스템 오차, 대상지형 특성에 의한 왜곡으로 인해 추가적인 보정이 필요하게 된다. SAR 영상을 통한 변화탐지나 타 영상과의 융합에 적용하기 위해서는 기하 오차 보정이 반드시 선행되어야 한다. 이를 위해 다수의 지상 기준점을 선정하고 이를 포함하는 기준 영상과 비교하여 원본 영상에서 대응점을 찾는 방식으로 정밀 기하보정을 수행할 수 있다. Speeded Up Robust Feature (SURF) 기법은 쉽고 빠르게 영상의 기준점을 찾을 수 있지만 상대적으로 해상도가 낮고 스펙클 잡음에 영향을 받는 SAR 영상에서는 활용하기가 어렵다고 알려져 있다. 본 논문에서는 SURF 기법을 위성 SAR 영상에 적용할 때 발생할 수 있는 오차를 추출하고 영상 특성에 따른 성능 변화를 분석하였다. SURF 알고리즘의 적용이 가능한 입력 변수의 적정 범위를 제시하고 그에 따른 영상 정합의 오차를 분석하여 중저해상도의 위성 SAR 영상에 대해서도 SURF 기법을 통한 기하 보정 및 영상 정합이 적용될 수 있음을 검증하였다. As applications of spaceborne SAR imagery are extended, there are increased demands for accurate registrations for better understanding and fusion of radar images. It becomes common to adopt multi-resolution SAR images to apply for wide area reconnaissance. Geometric correction of the SAR images can be performed by using satellite orbit and attitude information. However, the inherent errors of the SAR sensor's attitude and ground geographical data tend to cause geometric errors in the produced SAR image. These errors should be corrected when the SAR images are applied for multi-temporal analysis, change detection applications and image fusion with other sensor images. The undesirable ground registration errors can be corrected with respect to the true ground control points in order to produce complete SAR products. Speeded Up Robust Feature (SURF) technique is an efficient algorithm to extract ground control points from images but is considered to be inappropriate to apply to SAR images due to high speckle noises. In this paper, an attempt is made to apply SURF algorithm to SAR images for image registration and fusion. Matched points are extracted with respect to the varying parameters of Hessian and SURF matching thresholds, and the performance is analyzed by measuring the imaging matching accuracies. A number of performance measures concerning image registration are suggested to validate the use of SURF for spaceborne SAR images. Various simulations methodologies are suggested the validate the use of SURF for the geometric correction and image registrations and it is shown that a good choice of input parameters to the SURF algorithm should be made to apply for the spaceborne SAR images of moderate resolutions.

Image registration is an essential pre-processing step for several computer vision problems like image reconstruction and image fusion. In this paper, we present a review on image registration approaches using deep learning. The focus of the survey presented is on how conventional image registration methods such as area-based and feature-based methods are addressed using deep net architectures. Registration approach adopted depends on type of images and type of transformation used to describe the deformation between the images in an application. We then present a comparative performance analysis of convolutional neural networks that have shown good performance across feature extraction, matching and transformation estimation in featured-based registration. Experimentation is done on each of these approaches using a dataset of aerial images generated by inducing deformations such as scale.

Recently a number of researches have demonstrated performance improvement in the video fractal compression compared to the current video transmission standards (MPEG, H.263, H.264). This article describes a current problem of relatively low fractal encoding speed. Indeed, high computational complexity is a sore point of fractal compression approach. It seems almost every paper on this subject touches the problem of encoding speed. Productive ideas and algorithms can be borrowed from the pattern recognition problem. In the course of recent decades feature points approach in computer vision has been demonstrating good performance in SLAM and pattern recognition. Technology of feature detection, description and tracking is being developed successfully and has effective applications in augmented reality like Android ARCore and IOS ARKit frameworks that are real-time engines. Similarities among parts of video frames are analyzed and used for both image registration and visual scene tracking therefore it fits highly to block matching task. Statistic properties for domain/range blocks matching has been analyzed on the basis of previous investigation for fractal compression. As a result, a simple algorithm is proposed based on computer vision approach. The approach includes a visual feature points extraction, feature descriptors calculation and fast NN-search in descriptor space. The key idea of the proposed approach is as follows. Only a limited number of domain blocks around the most salient points are subject to selection. Other blocks are not essential for matching as transforms would have big Lipschitz constant and will have worse contractive properties. Salient points should be unique as well. Further the descriptors for feature point are calculated. The algorithm has O(N log N) complexity for pixel number in the frame image, however if the number of domain blocks is limited the complexity could be almost linear. Python program for the algorithm test has been developed and shows that reconstruction result is acceptable in terms of encoding speed (< 2 s on 2 GHz CPU) and quality (PSNR) ~25 dB. The result of the proposed approach could be interesting for further improvement both for image and video compression. Further steps for quality increasing are also described.

A projection kernel regression framework is set and applied for image registration and fusion in video-based criminal investigation. In image registration, a dominant point is defined to capture the local variation property of an image when the resolution is very low and thus most algorithms proposed till now for control point extraction fail. The order relationship between the sorted dominant point sequences, extracted respectively from the reference image and the target image, matches the two images, while the location relationship between the two sequences determines the input-output pairs in projection kernel regression, for approximation of the coordinate mapping function of the reference image and the target image. In image reconstruction, an analogue image is firstly estimated by the projection kernel regression using all of the registered images, and then re-sampled to obtain an enlarged image with arbitrary resolution. Experimental results on a section of surveillance video for criminal investigation show that the presented method is effective in solving the image registration and fusion problems in the aforementioned case.

Kinship verification from face images is a new and challenging problem in pattern recognition and computer vision, and it has many potential real-world applications including social media analysis and children adoptions. Most existing methods for kinship verification assume that each positive pair of face images (with kin relationship) has greater similarity score than those of negative pairs without kin relationships under a distance metric to be learned. In practice, however, this assumption is usually too strict for real-life kin samples. Instead, we propose in this paper learning a robust similarity model, under which the similarity score of each positive pair is greater than average similarity score of some negative ones. In addition, we develop an online similarity learning algorithm for more scalable application. We empirically evaluate the proposed methods on benchmark datasets, and experimental results show that our method outperforms some state-of-the-art kinship verification methods in terms of verification accuracy and computational efficiency.

Image segmentation is an important problem in pattern recognition, computer vision and other related area, which is still a research focus. In this paper, we consider the segmentation as pixel classification scheme and introduce a manifold way to address this problem. Some local features, such as Haar, LBP and SIFT, are used to represent each pixel in the image together with the basic property of the pixel. We put these pixel features on a manifold called pixel feature manifold (PFM) obtained via manifold learning methods and classify pixels with k-NN classifier in the pixel embedding space. Experimental results on MSRC image dataset show that our PFM method can effectively segment images.

Robust subspace clustering via penalized mixture of Gaussians

In order to determine the similarity between two planar shapes, which is an important problem in computer vision and pattern recognition, it is necessary to first match the two shapes as good as possible. As sets of allowed transformation to match shapes we consider translations, rigid motions, and similarities. We present a generic probabilistic algorithm based on random sampling for matching shapes which are modelled by sets of curves. The algorithm is applicable to the three considered classes of transformations. We analyze which similarity measure is optimized by the algorithm and give rigorous bounds on the number of samples necessary to get a prespecified approximation to the optimal match within a prespecified probability.

Age estimation based on the human face remains a significant problem in computer vision and pattern recognition. In order to estimate an accurate age or age group of a facial image, most of the existing algorithms require a huge face data set attached with age labels. This imposes a constraint on the utilization of the immensely unlabeled or weakly labeled training data, e.g., the huge amount of human photos in the social networks. These images may provide no age label, but it is easy to derive the age difference for an image pair of the same person. To improve the age estimation accuracy, we propose a novel learning scheme to take advantage of these weakly labeled data through the deep convolutional neural networks. For each image pair, Kullback-Leibler divergence is employed to embed the age difference information. The entropy loss and the cross entropy loss are adaptively applied on each image to make the distribution exhibit a single peak value. The combination of these losses is designed to drive the neural network to understand the age gradually from only the age difference information. We also contribute a data set, including more than 100 000 face images attached with their taken dates. Each image is both labeled with the timestamp and people identity. Experimental results on two aging face databases show the advantages of the proposed age difference learning system, and the state-of-the-art performance is gained.

We propose a novel computationally efficient correspondence algorithm to identify the correspondence of similar features of the Reference frame to Search frame in the dynamic image sequence analysis for face tracking. The correspondence of the features between the set of images is the central problem in Computer Vision(CV), Image Analysis(IA) and Pattern Recognition(PR). In these areas Correspondence of features is the combinatorial explosion problem or NP-hard, because of their exhaustive searching for features in the sequence of image frames. This correspondence has three major steps such as segmentation, feature extraction and matching. In this paper we propose block-based segmentation in which the frame which contains the face to be track can be segmented as window of size 20*20 which covers the face. Here we consider the window trace mean is the feature since this is rotation invariant and it covers all the rows and columns of the window and it reduces the dimensionality and finally for matching we used the minimum absolute difference method which does not involves more computations since no multiplication operation is involved. We restrict the searching space to [-3,+3] pixels horizontally and vertically in the search image. Experimental results show that this novel algorithm could achieve much higher computational reduction as compared with full search (FS), Diamond search (DS)[6], Cross Diamond Search (CDS)[7,8] and Area Based Correspondence[14] algorithm for face tracking image sequence while similar prediction accuracy is maintained and it is especially suitable for video conferencing and slow moving dynamic image sequence.

Matching two geometric objects in two-dimensional (2D) and three-dimensional (3D) spaces is a central problem in computer vision, pattern recognition, and protein structure prediction. In particular, the problem of aligning two polygonal chains under translation and rotation to minimize their distance has been studied using various distance measures. It is well known that the Hausdorff distance is useful for matching two point sets, and that the Fréchet distance is a superior measure for matching two polygonal chains. The discrete Fréchet distance closely approximates the (continuous) Fréchet distance, and is a natural measure for the geometric similarity of the folded 3D structures of biomolecules such as proteins. In this paper, we present new algorithms for matching two polygonal chains in two dimensions to minimize their discrete Fréchet distance under translation and rotation, and an effective heuristic for matching two polygonal chains in three dimensions. We also describe our empirical results on the application of the discrete Fréchet distance to protein structure-structure alignment.

No object is mysterious. The mystery is your eye. – Elizabeth Bowen Introduction There are two fundamentally different philosophies concerning understanding the brain. (1) Understand the brain first. If we can understand how the brain works, we can build smart machines. (2) Using any technique we can think of, make a smart machine. If we can accomplish that, it will give us some hints about how the brain works. This book is all about the second approach, although it draws from current understanding of biological computing. In this chapter, however, we define a few terms, introduce the greater localglobal problem, and then give a very brief introduction to the function of the mammalian brain. • (Section 1.2) From signal and systems perspective, we describe the differences between Computer Vision and some other closely related fields of studies, including, e.g., image processing and pattern recognition. • (Section 1.3) Since almost all problems in Computer Vision involve the issue of localness versus globalness, we briefly explain the “local-global” problem and the “consistency” principle used to solve this problem. • (Section 1.4) Computer Vision is deep-rooted in biological vision. Therefore, in this section, we discuss the biological motivation of Computer Vision and some amazing discoveries from the study of the human visual system. Some Definitions Computer Vision is the process whereby a machine, usually a digital computer, automatically processes an image and reports “what is in the image.” That is, it recognizes the content of the image. For example, the content may be a machined part, and the objective may be not only to locate the part but to inspect it as well. Students tend to get confused by other terms that often appear in the literature, such as Image Processing , Machine Vision , Image Understanding , and Pattern Recognition . We can divide the entire process of Image Processing into Low-Level Image Processing and High-Level Image Processing . If we interpret these processes from signal and systems perspective, it is more clear to describe their difference and similarity from the format of input/output of the system. When a Low-Level Image Processing system processes an input image, the output is still an image, but a somewhat different image. For example, it may be an image with noise removed, an image that does not take as much storage space as the input image, an image that is sharper than the input image, etc.

Computer detection intelligent mining algorithm for software defined networks