DOCSLIB.ORG

Features • Harris Corner Detector • SIFT Features •Extensions • Applications

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Features • Harris Corner Detector • SIFT Features •Extensions • Applications Outline •Features • Harris corner detector • SIFT Features •Extensions • Applications Digital Visual Effects Yung-Yu Chuang with slides by Trevor Darrell Cordelia Schmid, David Lowe, Darya Frolova, Denis Simakov, Robert Collins and Jiwon Kim Features • Also known as interesting points, salient points or keypoints. Points that you can easily point out their correspondences in multiple images using only local information. Features ? Desired properties for features Applications • Distinctive: a single feature can be correctly • Object or scene recognition matched with high probability. • Structure from motion • Invariant: invariant to scale, rotation, affine, •Stereo illumination and noise for robust matching • Motion tracking across a substantial range of affine distortion, viewpoint change and so on. That is, it is •… repeatable. Components • Feature detection locates where they are • Feature description describes what they are • Feature matching decides whether two are the same one Harris corner detector Moravec corner detector (1980) Moravec corner detector • We should easily recognize the point by looking through a small window • Shifting a window in any direction should give a large change in intensity flat Moravec corner detector Moravec corner detector flat flat edge Moravec corner detector Moravec corner detector Change of intensity for the shift [u,v]: E(u,v) w(x, y)I(x u, y v) I(x, y) 2 x, y window shifted intensity function intensity corner flat edge Four shifts: (u,v) = (1,0), (1,1), (0,1), (-1, 1) isolated point Look for local maxima in min{E} Problems of Moravec detector Harris corner detector • Noisy response due to a binary window function Noisy response due to a binary window function • Only a set of shifts at every 45 degree is Use a Gaussian function considered • Only minimum of E is taken into account Harris corner detector (1988) solves these problems. Harris corner detector Harris corner detector Only a set of shifts at every 45 degree is considered Only a set of shifts at every 45 degree is considered Consider all small shifts by Taylor’s expansion Consider all small shifts by Taylor’s expansion E(u,v) w(x, y)I(x u, y v) I(x, y) 2 x, y 2 2 2 w(x, y)I xu I yv O(u ,v ) x, y E(u,v) Au2 2Cuv Bv 2 2 A w(x, y)I x (x, y) x, y 2 B w(x, y)I y (x, y) x, y C w(x, y)I x (x, y)I y (x, y) x, y Harris corner detector Harris corner detector (matrix form) Equivalently, for small shifts [u,v] we have a bilinear 2 E(u) w(x0 ) | I(x0 u) I(x0 ) | approximation: x0W (p) 2 | I(x0 u) I(x0 ) | u 2 E(u,v) u v M I T I u I v 0 0 x 2 , where M is a 22 matrix computed from image derivatives: I T u 2 x I x I x I y M w(x, y) 2 T T I I x, y I x I y I y u u x x uT Mu Harris corner detector Harris corner detector Only minimum of E is taken into account High-level idea: what shape of the error function A new corner measurement by investigating the will we prefer for features? shape of the error function 100 100 100 80 80 80 T 60 60 60 u Mu represents a quadratic function; Thus, we 40 40 40 can analyze E’s shape by looking at the property 20 20 20 of M 0 0 0 10 10 10 12 12 12 10 10 10 8 5 8 8 6 5 6 5 6 4 4 4 2 2 2 0 0 0 0 0 0 flat edge corner Quadratic forms Symmetric matrices • Quadratic form (homogeneous polynomial of • Quadratic forms can be represented by a real degree two) of n variables xi symmetric matrix A where • Examples = Eigenvalues of symmetric matrices Eigenvectors of symmetric matrices Brad Osgood Eigenvectors of symmetric matrices Harris corner detector Intensity change in shifting window: eigenvalue analysis u , – eigenvalues of M E(u,v) u,v M 1 2 T v x Ax T T T x Q Λ Q x z z 1 Ellipse E(u,v) = const direction of the 2 q2 fastest change T 1 q1 direction of the QTx Λ QTx slowest change T -1/2 y Λy (max) T ( )-1/2 1 T 1 x x 1 min Λ 2 y Λ 2 y zTz Visualize quadratic functions Visualize quadratic functions T T 1 0 1 01 01 0 4 0 1 04 01 0 A A 0 1 0 10 10 1 0 1 0 10 10 1 Visualize quadratic functions Visualize quadratic functions T T 3.25 1.30 0.50 0.871 0 0.50 0.87 7.75 3.90 0.50 0.871 0 0.50 0.87 A A 1.30 1.75 0.87 0.500 40.87 0.50 3.90 3.25 0.87 0.500 100.87 0.50 Harris corner detector Harris corner detector 2 Only for reference, Classification of a00 a11 (a00 a11) 4a10a01 2 edge you do not need image points 2 them to compute R using eigenvalues 2 >> 1 Corner Measure of corner response: of M: 1 and 2 are large, 1 ~ 2; E increases in all 2 directions R detM ktraceM det M 12 and are small; 1 2 edge E is almost constant flat trace M 1 2 in all directions 1 >> 2 1 (k – empirical constant, k = 0.04-0.06) Harris corner detector Another view Another view Another view Summary of Harris detector Summary of Harris detector 1. Compute x and y derivatives of image 4. Define the matrix at each pixel x y S 2 (x, y) S (x, y) I G I I G I x xy x y M (x, y) S (x, y) S 2 (x, y) xy y 2. Compute products of derivatives at every pixel 5. Compute the response of the detector at each I 2 I I I 2 I I I I I x x x y y y xy x y pixel R det M ktraceM 2 3. Compute the sums of the products of derivatives at each pixel 6. Threshold on value of R; compute nonmax suppression. S 2 G I 2 Sx2 G ' I x2 y ' y Sxy G ' I xy Harris corner detector (input) Corner response R Threshold on R Local maximum of R Harris corner detector Harris detector: summary • Average intensity change in direction [u,v] can be expressed as a bilinear form: u E(u,v) u,v M v • Describe a point in terms of eigenvalues of M: measure of corner response 2 R 12 k1 2 • A good (corner) point should have a large intensity change in all directions, i.e. R should be large positive Now we know where features are Harris detector: some properties • But, how to match them? • Partial invariance to affine intensity change • What is the descriptor for a feature? The Only derivatives are used => simplest solution is the intensities of its spatial invariance to intensity shift I I + b neighbors. This might not be robust to brightness change or small shift/rotation. Intensity scale: I a I 12 3 45 6 R R threshold 78 9 x (image coordinate) x (image coordinate) ( 1 2 3 4 5 6 7 8 9 ) Harris Detector: Some Properties Harris Detector is rotation invariant • Rotation invariance Repeatability rate: # correspondences # possible correspondences Ellipse rotates but its shape (i.e. eigenvalues) remains the same Corner response R is invariant to image rotation Harris Detector: Some Properties Harris detector: some properties • Quality of Harris detector for different scale • But: not invariant to image scale! changes Repeatability rate: # correspondences # possible correspondences All points will be Corner ! classified as edges Scale invariant detection Scale invariant detection • Consider regions (e.g. circles) of different sizes • The problem: how do we choose corresponding around a point circles independently in each image? • Regions of corresponding sizes will look the • Aperture problem same in both images SIFT • SIFT is an carefully designed procedure with empirically determined parameters for the invariant and distinctive features. SIFT (Scale Invariant Feature Transform) SIFT stages: 1. Detection of scale-space extrema • Scale-space extrema detection • For scale invariance, search for stable features detector • Keypoint localization across all possible scales using a continuous • Orientation assignment function of scale, scale space. descriptor • Keypoint descriptor • SIFT uses DoG filter for scale space because it is efficient and as stable as scale-normalized Laplacian of Gaussian. ( ) local descriptor A 500x500 image gives about 2000 features DoG filtering Scale space Convolution with a variable-scale Gaussian doubles for the next octave Difference-of-Gaussian (DoG) filter K=2(1/s) Convolution with the DoG filter Dividing into octave is for efficiency only. Detection of scale-space extrema Keypoint localization X is selected if it is larger or smaller than all 26 neighbors Decide scale sampling frequency Decide scale sampling frequency • It is impossible to sample the whole space, tradeoff efficiency with completeness. • Decide the best sampling frequency by experimenting on 32 real image subject to synthetic transformations. (rotation, scaling, affine stretch, brightness and contrast change, adding noise…) Decide scale sampling frequency Pre-smoothing for detector, repeatability for descriptor, distinctiveness s=3 is the best, for larger s, too many unstable features =1.6, plus a double expansion Scale invariance 2. Accurate keypoint localization • Reject points with low contrast (flat) and poorly localized along an edge (edge) • Fit a 3D quadratic function for sub-pixel maxima 6 5 1 -10 +1 2.
Load more

Recommended publications
  • Hough Transform, Descriptors Tammy Riklin Raviv Electrical and Computer Engineering Ben-Gurion University of the Negev Hough Transform
    DIGITAL IMAGE PROCESSING Lecture 7 Hough transform, descriptors Tammy Riklin Raviv Electrical and Computer Engineering Ben-Gurion University of the Negev Hough transform y m x b y m 3 5 3 3 2 2 3 7 11 10 4 3 2 3 1 4 5 2 2 1 0 1 3 3 x b Slide from S. Savarese Hough transform Issues: • Parameter space [m,b] is unbounded. • Vertical lines have infinite gradient. Use a polar representation for the parameter space Hough space r y r q x q x cosq + ysinq = r Slide from S. Savarese Hough Transform Each point votes for a complete family of potential lines: Each pencil of lines sweeps out a sinusoid in Their intersection provides the desired line equation. Hough transform - experiments r q Image features ρ,ϴ model parameter histogram Slide from S. Savarese Hough transform - experiments Noisy data Image features ρ,ϴ model parameter histogram Need to adjust grid size or smooth Slide from S. Savarese Hough transform - experiments Image features ρ,ϴ model parameter histogram Issue: spurious peaks due to uniform noise Slide from S. Savarese Hough Transform Algorithm 1. Image à Canny 2. Canny à Hough votes 3. Hough votes à Edges Find peaks and post-process Hough transform example http://ostatic.com/files/images/ss_hough.jpg Incorporating image gradients • Recall: when we detect an edge point, we also know its gradient direction • But this means that the line is uniquely determined! • Modified Hough transform: for each edge point (x,y) θ = gradient orientation at (x,y) ρ = x cos θ + y sin θ H(θ, ρ) = H(θ, ρ) + 1 end Finding lines using Hough transform
    [Show full text]
  • A PERFORMANCE EVALUATION of LOCAL DESCRIPTORS 1 a Performance Evaluation of Local Descriptors
    MIKOLAJCZYK AND SCHMID: A PERFORMANCE EVALUATION OF LOCAL DESCRIPTORS 1 A performance evaluation of local descriptors Krystian Mikolajczyk and Cordelia Schmid Dept. of Engineering Science INRIA Rhone-Alpesˆ University of Oxford 655, av. de l'Europe Oxford, OX1 3PJ 38330 Montbonnot United Kingdom France [email protected] [email protected] Abstract In this paper we compare the performance of descriptors computed for local interest regions, as for example extracted by the Harris-Affine detector [32]. Many different descriptors have been proposed in the literature. However, it is unclear which descriptors are more appropriate and how their performance depends on the interest region detector. The descriptors should be distinctive and at the same time robust to changes in viewing conditions as well as to errors of the detector. Our evaluation uses as criterion recall with respect to precision and is carried out for different image transformations. We compare shape context [3], steerable filters [12], PCA-SIFT [19], differential invariants [20], spin images [21], SIFT [26], complex filters [37], moment invariants [43], and cross-correlation for different types of interest regions. We also propose an extension of the SIFT descriptor, and show that it outperforms the original method. Furthermore, we observe that the ranking of the descriptors is mostly independent of the interest region detector and that the SIFT based descriptors perform best. Moments and steerable filters show the best performance among the low dimensional descriptors. Index Terms Local descriptors, interest points, interest regions, invariance, matching, recognition. I. INTRODUCTION Local photometric descriptors computed for interest regions have proved to be very successful in applications such as wide baseline matching [37, 42], object recognition [10, 25], texture Corresponding author is K.
    [Show full text]
  • Robust Corner and Tangent Point Detection for Strokes with Deep
    Robust corner and tangent point detection for strokes with deep learning approach Long Zeng*, Zhi-kai Dong, Yi-fan Xu Graduate school at Shenzhen, Tsinghua University Abstract: A robust corner and tangent point detection (CTPD) tool is critical for sketch-based engineering modeling. This paper proposes a robust CTPD approach for hand-drawn strokes with deep learning approach, denoted as CTPD-DL. Its robustness for users, stroke shapes and biased datasets is improved due to multi-scaled point contexts and a vote scheme. Firstly, all stroke points are classified into segments by two deep learning networks, based on scaled point contexts which mimic human’s perception. Then, a vote scheme is adopted to analyze the merge conditions and operations for adjacent segments. If most points agree with a stroke’s type, this type is accepted. Finally, new corners and tangent points are inserted at transition points. The algorithm’s performance is experimented with 1500 strokes of 20 shapes. Results show that our algorithm can achieve 95.3% for all-or-nothing accuracy and 88.6% accuracy for biased datasets, compared to 84.6% and 71% of the state-of-the-art CTPD technique, which is heuristic and empirical-based. Keywords: corner detection, tangent point detection, stroke segmentation, deep learning, ResNet. 1. Introduction This work originates from our sketch-based engineering modeling (SBEM) system [1], to convert a conceptual sketch into a detailed part directly. A user friendly SBEM should impose as fewer constraints to the sketching process as possible [2]. Such system usually first starts from hand- drawn strokes, which may contain more than one primitives (e.g.
    [Show full text]
  • 1 Introduction
    1: Introduction Ahmad Humayun 1 Introduction z A pixel is not a square (or rectangular). It is simply a point sample. There are cases where the contributions to a pixel can be modeled, in a low order way, by a little square, but not ever the pixel itself. The sampling theorem tells us that we can reconstruct a continuous entity from such a discrete entity using an appropriate reconstruction filter - for example a truncated Gaussian. z Cameras approximated by pinhole cameras. When pinhole too big - many directions averaged to blur the image. When pinhole too small - diffraction effects blur the image. z A lens system is there in a camera to correct for the many optical aberrations - they are basically aberrations when light from one point of an object does not converge into a single point after passing through the lens system. Optical aberrations fall into 2 categories: monochromatic (caused by the geometry of the lens and occur both when light is reflected and when it is refracted - like pincushion etc.); and chromatic (Chromatic aberrations are caused by dispersion, the variation of a lens's refractive index with wavelength). Lenses are essentially help remove the shortfalls of a pinhole camera i.e. how to admit more light and increase the resolution of the imaging system at the same time. With a simple lens, much more light can be bought into sharp focus. Different problems with lens systems: 1. Spherical aberration - A perfect lens focuses all incoming rays to a point on the optic axis. A real lens with spherical surfaces suffers from spherical aberration: it focuses rays more tightly if they enter it far from the optic axis than if they enter closer to the axis.
    [Show full text]
  • A Combined Approach of Harris-SIFT Feature Detection for Image Mosaicing
    International Journal of Engineering Research & Technology (IJERT) ISSN: 2278-0181 Vol. 3 Issue 5, May - 2014 A Combined Approach of Harris-SIFT Feature Detection for Image Mosaicing Monika B. Varma, Prof. Kinjal Mistree C.E Department, Chotubhai Gopalbhai Patel Institute of Technology Uka Tarsadia University Gujarat, India. Abstract—This Image Mosaicing is a process of assembling appropriate transformations via a warping operation and multiple overlapping images of the same scene into a large image. merging the overlapping regions of warped Images, it is The output of the image Mosaicing operation is the union of the possible to construct a single image indistinguishable from a two or more overlapping input images. This technology is widely single large image of the same object, covering the entire used in photography, digital video, motion analysis, medical visible area of the scene. The basis of the Image Mosaicing image processing, remote sensing image processing, document technique is to find the common part in the overlap input image processing and other fields. images and then smoothly blend them to produce final Panorama. This paper describes a combined approach of Harris-SIFT feature detection for Image Mosaicing. Firstly, feature points are The procedure of the Image Mosaicing Consists of two basic detected by using Harris corner detector, then after SIFT Concept: 1) Image Registration and 2) Image Blending and descriptor is computed to store feature vector for each detected Warping[6], as shown in the Fig 1. keypoints and then feature matching is applied. The RANSAC Homography algorithm is used to detect wrong matches for improving the stability of the algorithm and for estimating the transformation model.
    [Show full text]
  • Accurate Corner Detection Methods Using Two Step Approach by Nitin Bhatia , Megha Chhabra Thapar University
    Global Journal of Computer Science & Technology Volume 11 Issue 6 Version 1.0 April 2011 Type: Double Blind Peer Reviewed International Research Journal Publisher: Global Journals Inc. (USA) Online ISSN: 0975 - 4172 & Print ISSN: 0975-4350 Accurate Corner Detection Methods using Two Step Approach By Nitin Bhatia , Megha Chhabra Thapar University Abstract- : Many image features are proved to be good candidates for recognition. Among them are edges, lines, corners, junctions or interest points in general. Importance of corner detection in digital images is increasing with increasing work in computer vision in imagery. One of the most promising techniques is the one based on Harris corner detection method. This work describes different approaches to detect corner in efficient way. Based on the works carried out by Harris method, the authors have worked upon increasing efficiency using edge detection methods on image, along with applying the Harris on this pre-processed image. Most of the time, such a step is performed as one of the first steps upon which more complicated algorithm rely. Hence, good outcome of such an operation influences the whole vision channel. This paper contains a quantitative comparison of three such modified techniques using Sobel–Harris, Canny-Harris and Laplace-Harris with Harris operator on the basis of distances computed by these methods from user detected corners. Keywords: Corner Detection, Harris, Laplace, Canny, Sobel. Classification: GJCST Classification: I.4.6 Accurate Corner Detection Methods using Two Step Approach Strictly as per the compliance and regulations of: © 2011 Nitin Bhatia , Megha Chhabra. This is a research/review paper, distributed under the terms of the Creative Commons Attribution-Noncommercial 3.0 Unported License http://creativecommons.org/licenses/by-nc/3.0/), permitting all non-commercial use, distribution, and reproduction inany medium, provided the original work is properly cited.
    [Show full text]
  • Detection and Evaluation Methods for Local Image and Video Features Julian Stottinger¨
    Technical Report CVL-TR-4 Detection and Evaluation Methods for Local Image and Video Features Julian Stottinger¨ Computer Vision Lab Institute of Computer Aided Automation Vienna University of Technology 2. Marz¨ 2011 Abstract In computer vision, local image descriptors computed in areas around salient interest points are the state-of-the-art in visual matching. This technical report aims at finding more stable and more informative interest points in the domain of images and videos. The research interest is the development of relevant evaluation methods for visual mat- ching approaches. The contribution of this work lies on one hand in the introduction of new features to the computer vision community. On the other hand, there is a strong demand for valid evaluation methods and approaches gaining new insights for general recognition tasks. This work presents research in the detection of local features both in the spatial (“2D” or image) domain as well for spatio-temporal (“3D” or video) features. For state-of-the-art classification the extraction of discriminative interest points has an impact on the final classification performance. It is crucial to find which interest points are of use in a specific task. One question is for example whether it is possible to reduce the number of interest points extracted while still obtaining state-of-the-art image retrieval or object recognition results. This would gain a significant reduction in processing time and would possibly allow for new applications e.g. in the domain of mobile computing. Therefore, the work investigates different corner detection approaches and evaluates their repeatability under varying alterations.
    [Show full text]
  • A Survey of Feature Extraction Techniques in Content-Based Illicit Image Detection
    Journal of Theoretical and Applied Information Technology 10 th May 2016. Vol.87. No.1 © 2005 - 2016 JATIT & LLS. All rights reserved . ISSN: 1992-8645 www.jatit.org E-ISSN: 1817-3195 A SURVEY OF FEATURE EXTRACTION TECHNIQUES IN CONTENT-BASED ILLICIT IMAGE DETECTION 1,2 S.HADI YAGHOUBYAN, 1MOHD AIZAINI MAAROF, 1ANAZIDA ZAINAL, 1MAHDI MAKTABDAR OGHAZ 1Faculty of Computing, Universiti Teknologi Malaysia (UTM), Malaysia 2 Department of Computer Engineering, Islamic Azad University, Yasooj Branch, Yasooj, Iran E-mail: 1,2 [email protected], [email protected], [email protected] ABSTRACT For many of today’s youngsters and children, the Internet, mobile phones and generally digital devices are integral part of their life and they can barely imagine their life without a social networking systems. Despite many advantages of the Internet, it is hard to neglect the Internet side effects in people life. Exposure to illicit images is very common among adolescent and children, with a variety of significant and often upsetting effects on their growth and thoughts. Thus, detecting and filtering illicit images is a hot and fast evolving topic in computer vision. In this research we tried to summarize the existing visual feature extraction techniques used for illicit image detection. Feature extraction can be separate into two sub- techniques feature detection and description. This research presents the-state-of-the-art techniques in each group. The evaluation measurements and metrics used in other researches are summarized at the end of the paper. We hope that this research help the readers to better find the proper feature extraction technique or develop a robust and accurate visual feature extraction technique for illicit image detection and filtering purpose.
    [Show full text]
  • Edge Detection and Corner Detection
    Edge Detection and Corner Detection Introduction to Computer Vision CSE 152 Lecture 7 CSE 152, Spring 2018 Introduction to Computer Vision Announcements • Homework 2 is due Apr 25, 11:59 PM • Reading: – Chapter 5: Local Image Features CSE 152, Spring 2018 Introduction to Computer Vision Edges CSE 152, Spring 2018 Introduction to Computer Vision Corners CSE 152, Spring 2018 Introduction to Computer Vision Edges What is an edge? A discontinuity in image intensity. Physical causes of edges 1. Object boundaries 2. Surface normal discontinuities 3. Reflectance (albedo) discontinuities 4. Lighting discontinuities (shadow boundaries) CSE 152, Spring 2018 Introduction to Computer Vision Object Boundaries CSE 152, Spring 2018 Introduction to Computer Vision Surface normal discontinuities CSE 152, Spring 2018 Introduction to Computer Vision Boundaries of materials properties CSE 152, Spring 2018 Introduction to Computer Vision Boundaries of lighting CSE 152, Spring 2018 Introduction to Computer Vision Profiles of image intensity edges CSE 152, Spring 2018 Introduction to Computer Vision Noisy Step Edge • Derivative is high everywhere. • Must smooth before taking gradient. CSE 152, Spring 2018 Introduction to Computer Vision Edge is Where Change Occurs: 1-D • Change is measured by derivative in 1D Ideal Edge Smoothed Edge First Derivative Second Derivative • Biggest change, derivative has maximum magnitude • Or 2nd derivative is zero. CSE 152, Spring 2018 Introduction to Computer Vision Numerical Derivatives f(x) x X0-h X0 X0+h Take Taylor series
    [Show full text]
  • An Analysis and Implementation of the Harris Corner Detector
    Published in Image Processing On Line on 2018–10–03. Submitted on 2018–06–04, accepted on 2018–09–18. ISSN 2105–1232 c 2018 IPOL & the authors CC–BY–NC–SA This article is available online with supplementary materials, software, datasets and online demo at https://doi.org/10.5201/ipol.2018.229 2015/06/16 v0.5.1 IPOL article class An Analysis and Implementation of the Harris Corner Detector Javier S´anchez1, Nelson Monz´on2, Agust´ın Salgado1 1 CTIM, Department of Computer Science, University of Las Palmas de Gran Canaria, Spain ({jsanchez, agustin.salgado}@ulpgc.es) 2 CMLA, Ecole´ Normale Sup´erieure , Universit´eParis-Saclay, France ([email protected]) Abstract In this work, we present an implementation and thorough study of the Harris corner detector. This feature detector relies on the analysis of the eigenvalues of the autocorrelation matrix. The algorithm comprises seven steps, including several measures for the classification of corners, a generic non-maximum suppression method for selecting interest points, and the possibility to obtain the corners position with subpixel accuracy. We study each step in detail and pro- pose several alternatives for improving the precision and speed. The experiments analyze the repeatability rate of the detector using different types of transformations. Source Code The reviewed source code and documentation for this algorithm are available from the web page of this article1. Compilation and usage instruction are included in the README.txt file of the archive. Keywords: Harris corner; feature detector; interest point; autocorrelation matrix; non-maximum suppression 1 Introduction The Harris corner detector [9] is a standard technique for locating interest points on an image.
    [Show full text]
  • Local Descriptors
    Local descriptors SIFT (Scale Invariant Feature Transform) descriptor • SIFT keypoints at locaon xy and scale σ have been obtained according to a procedure that guarantees illuminaon and scale invance. By assigning a consistent orientaon, the SIFT keypoint descriptor can be also orientaon invariant. • SIFT descriptor is therefore obtained from the following steps: – Determine locaon and scale by maximizing DoG in scale and in space (i.e. find the blurred image of closest scale) – Sample the points around the keypoint and use the keypoint local orientaon as the dominant gradient direc;on. Use this scale and orientaon to make all further computaons invariant to scale and rotaon (i.e. rotate the gradients and coordinates by the dominant orientaon) – Separate the region around the keypoint into subregions and compute a 8-bin gradient orientaon histogram of each subregion weigthing samples with a σ = 1.5 Gaussian SIFT aggregaon window • In order to derive a descriptor for the keypoint region we could sample intensi;es around the keypoint, but they are sensi;ve to ligh;ng changes and to slight errors in x, y, θ. In order to make keypoint es;mate more reliable, it is usually preferable to use a larger aggregaon window (i.e. the Gaussian kernel size) than the detec;on window. The SIFT descriptor is hence obtained from thresholded image gradients sampled over a 16x16 array of locaons in the neighbourhood of the detected keypoint, using the level of the Gaussian pyramid at which the keypoint was detected. For each 4x4 region samples they are accumulated into a gradient orientaon histogram with 8 sampled orientaons.
    [Show full text]
  • Local Feature Detectors and Descriptors Overview
    CS 6350 – COMPUTER VISION Local Feature Detectors and Descriptors Overview • Local invariant features • Keypoint localization - Hessian detector - Harris corner detector • Scale Invariant region detection - Laplacian of Gaussian (LOG) detector - Difference of Gaussian (DOG) detector • Local feature descriptor - Scale Invariant Feature Transform (SIFT) - Gradient Localization Oriented Histogram (GLOH) • Examples of other local feature descriptors Motivation • Global feature from the whole image is often not desirable • Instead match local regions which are prominent to the object or scene in the image. • Application Area - Object detection - Image matching - Image stitching Requirements of a local feature • Repetitive : Detect the same points independently in each image. • Invariant to translation, rotation, scale. • Invariant to affine transformation. • Invariant to presence of noise, blur etc. • Locality :Robust to occlusion, clutter and illumination change. • Distinctiveness : The region should contain “interesting” structure. • Quantity : There should be enough points to represent the image. • Time efficient. Others preferable (but not a must): o Disturbances, attacks, o Noise o Image blur o Discretization errors o Compression artifacts o Deviations from the mathematical model (non-linearities, non-planarities, etc.) o Intra-class variations General approach + + + 1. Find the interest points. + + 2. Consider the region + ( ) around each keypoint. local descriptor 3. Compute a local descriptor from the region and normalize the feature.
    [Show full text]