vlfeat 图像处理库

/** @file sift.c ** @brief SIFT - Definition ** @author Andrea Vedaldi **/ /* Copyright (C) 2007-12 Andrea Vedaldi and Brian Fulkerson. All rights reserved. This file is part of the VLFeat library and is made available under the terms of the BSD license (see the COPYING file). */ /** <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ --> @page sift Scale Invariant Feature Transform (SIFT) @author Andrea Vedaldi @par "Credits:" May people have contributed with suggestions and bug reports. Although the following list is certainly incomplete, we would like to thank: Wei Dong, Loic, Giuseppe, Liu, Erwin, P. Ivanov, and Q. S. Luo. <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ --> @ref sift.h implements a @ref sift-usage "SIFT filter object", a reusable object to extract SIFT features @cite{lowe99object} from one or multiple images. - @ref sift-intro - @ref sift-intro-detector - @ref sift-intro-descriptor - @ref sift-intro-extensions - @ref sift-usage - @ref sift-tech - @ref sift-tech-ss - @ref sift-tech-detector - @ref sift-tech-detector-peak - @ref sift-tech-detector-edge - @ref sift-tech-detector-orientation - @ref sift-tech-descriptor - @ref sift-tech-descriptor-can - @ref sift-tech-descriptor-image - @ref sift-tech-descriptor-std <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ --> @section sift-intro Overview <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ --> A SIFT feature is a selected image region (also called keypoint) with an associated descriptor. Keypoints are extracted by the <b>@ref sift-intro-detector "SIFT detector"</b> and their descriptors are computed by the <b>@ref sift-intro-descriptor "SIFT descriptor"</b>. It is also common to use independently the SIFT detector (i.e. computing the keypoints without descriptors) or the SIFT descriptor (i.e. computing descriptors of custom keypoints). <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ --> @subsection sift-intro-detector SIFT detector <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ --> @sa @ref sift-tech-ss "Scale space technical details", @ref sift-tech-detector "Detector technical details" A SIFT <em>keypoint</em> is a circular image region with an orientation. It is described by a geometric <em>frame</em> of four parameters: the keypoint center coordinates @e x and @e y, its @e scale (the radius of the region), and its @e orientation (an angle expressed in radians). The SIFT detector uses as keypoints image structures which resemble &ldquo;blobs&rdquo;. By searching for blobs at multiple scales and positions, the SIFT detector is invariant (or, more accurately, covariant) to translation, rotations, and rescaling of the image. The keypoint orientation is also determined from the local image appearance and is covariant to image rotations. Depending on the symmetry of the keypoint appearance, determining the orientation can be ambiguous. In this case, the SIFT detectors returns a list of up to four possible orientations, constructing up to four frames (differing only by their orientation) for each detected image blob. @image html sift-frame.png "SIFT keypoints are circular image regions with an orientation." There are several parameters that influence the detection of SIFT keypoints. First, searching keypoints at multiple scales is obtained by constructing a so-called &ldquo;Gaussian scale space&rdquo;. The scale space is just a collection of images obtained by progressively smoothing the input image, which is analogous to gradually reducing the image resolution. Conventionally, the smoothing level is called <em>scale</em> of the image. The construction of the scale space is influenced by the following parameters, set when creating the SIFT filter object by ::vl_sift_new(): - <b>Number of octaves</b>. Increasing the scale by an octave means doubling the size of the smoothing kernel, whose effect is roughly equivalent to halving the image resolution. By default, the scale space spans as many octaves as possible (i.e. roughly <code> log2(min(width,height)</code>), which has the effect of searching keypoints of all possible sizes. - <b>First octave index</b>. By convention, the octave of index 0 starts with the image full resolution. Specifying an index greater than 0 starts the scale space at a lower resolution (e.g. 1 halves the resolution). Similarly, specifying a negative index starts the scale space at an higher resolution image, and can be useful to extract very small features (since this is obtained by interpolating the input image, it does not make much sense to go past -1). - <b>Number of levels per octave</b>. Each octave is sampled at this given number of intermediate scales (by default 3). Increasing this number might in principle return more refined keypoints, but in practice can make their selection unstable due to noise (see [1]). Keypoints are further refined by eliminating those that are likely to be unstable, either because they are selected nearby an image edge, rather than an image blob, or are found on image structures with low contrast. Filtering is controlled by the follow: - <b>Peak threshold.</b> This is the minimum amount of contrast to accept a keypoint. It is set by configuring the SIFT filter object by ::vl_sift_set_peak_thresh(). - <b>Edge threshold.</b> This is the edge rejection threshold. It is set by configuring the SIFT filter object by ::vl_sift_set_edge_thresh(). <table> <caption>Summary of the parameters influencing the SIFT detector.</caption> <tr style="font-weight:bold;"> <td>Parameter</td> <td>See also</td> <td>Controlled by</td> <td>Comment</td> </tr> <tr> <td>number of octaves</td> <td> @ref sift-intro-detector </td> <td>::vl_sift_new</td> <td></td> </tr> <tr> <td>first octave index</td> <td> @ref sift-intro-detector </td> <td>::vl_sift_new</td> <td>set to -1 to extract very small features</td> </tr> <tr> <td>number of scale levels per octave</td> <td> @ref sift-intro-detector </td> <td>::vl_sift_new</td> <td>can affect the number of extracted keypoints</td> </tr> <tr> <td>edge threshold</td> <td> @ref sift-intro-detector </td> <td>::vl_sift_set_edge_thresh</td> <td>decrease to eliminate more keypoints</td> </tr> <tr> <td>peak threshold</td> <td> @ref sift-intro-detector </td> <td>::vl_sift_set_peak_thresh</td> <td>increase to eliminate more keypoints</td> </tr> </table> <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ --> @subsection sift-intro-descriptor SIFT Descriptor <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ --> @sa @ref sift-tech-descriptor "Descriptor technical details" A SIFT descriptor is a 3-D spatial histogram of the image gradients in characterizing the appearance of a keypoint. The gradient at each pixel is regarded as a sample of a three-dimensional elementary feature vector, formed by the pixel location and the gradient orientation. Samples are weighed by the gradient norm and accumulated in a 3-D histogram @em h, which (up to normalization and clamping) forms the SIFT descriptor of the region. An additional Gaussian weighting function is applied to give less importance to gradients farther away from the keypoint center. Orientations are quantized into eight bins and the spatial coordinates into four each, as follows: @image html sift-descr-easy.png "The SIFT descriptor is a spatial histogram of the image gradient." SIFT descriptors are computed by either calling ::vl_sift_calc_keypoint_descriptor or ::vl_sift_calc_raw_descriptor. They accept as input a keypoint frame, which specifies the descriptor center, its size, and its orientation on the image plane. The following parameters influence the descriptor calculation: - <b>magnification factor</b>. The descriptor size is determined by multiplying the keypoint scale by this factor. It is set