Anders Hast

Rotation invariant feature matching-based on Gaussian filtered log polar transform and phase correlation

Rotation invariance is an important property for any feature matching method and it has been implemented in different ways for different methods. The Log Polar Transform has primarily been used for image registration where it is applied after phase correlation, which in its turn is applied on the whole images or in the case of template matching, applied on major parts of them followed by an exhaustive search. We investigate how this transform can be used on local neighborhoods of features and how phase correlation as well as normalized cross correlation can be applied on the result. Thus, the order is reversed and we argue why it is important to do so. We demonstrate a common problem with the log polar transform and that many implementations of it are not suitable for local feature detectors. We propose an implementation of it based on Gaussian filtering. We also show that phase correlation generally will perform better than normalized cross correlation. Both handles illumination differences well, but changes in scale is handled better by the phase correlation approach.

Faster shading by equal angle interpolation of vectors

We show how spherical linear interpolation can be used to produce shading with a quality at least similar to Phong shading at a computational effort in the inner loop that is close to that of the Gouraud method. We show how to use the Chebyshevs recurrence relation in order to compute the shading very efficiently. Furthermore, it can also be used to interpolate vectors in such a way that normalization is not necessary, which will make the interpolation very fast. The somewhat larger setup effort required by this approach can be handled through table look up techniques.

GeoMemories—A Platform for Visualizing Historical, Environmental and Geospatial Changes in the Italian Landscape

The GeoMemories project aims at publishing on the Web and digitally preserving historical aerial photographs that are currently stored in physical form within the archives of the Aerofototeca Nazionale in Rome. We describe a system, available at http://www.geomemories.org, that lets users visualize the evolution of the Italian landscape throughout the last century. The Web portal allows comparison of recent satellite imagery with several layers of historical maps, obtained from the aerial photos through a complex workflow that merges them together. We present several case studies carried out in collaboration with geologists, historians and archaeologists, that illustrate the great potential of our system in different research fields. Experiments and advances in image processing technologies are envisaged as a key factor in solving the inherent issue of vast amounts of manual work, from georeferencing to mosaicking to analysis.

Automated classification of glandular tissue by statistical proximity sampling

Due to the complexity of biological tissue and variations in staining procedures, features that are based on the explicit extraction of properties from subglandular structures in tissue images may have difficulty generalizing well over an unrestricted set of images and staining variations. We circumvent this problem by an implicit representation that is both robust and highly descriptive, especially when combined with a multiple instance learning approach to image classification. The new feature method is able to describe tissue architecture based on glandular structure. It is based on statistically representing the relative distribution of tissue components around lumen regions, while preserving spatial and quantitative information, as a basis for diagnosing and analyzing different areas within an image. We demonstrate the efficacy of the method in extracting discriminative features for obtaining high classification rates for tubular formation in both healthy and cancerous tissue, which is an important component in Gleason and tubule-based Elston grading. The proposed method may be used for glandular classification, also in other tissue types, in addition to general applicability as a region-based feature descriptor in image analysis where the image represents a bag with a certain label (or grade) and the region-based feature vectors represent instances.

Robust and Invariant Phase Based Local Feature Matching

Any feature matching algorithm needs to be robust, producing few false positives but also needs to be invariant to changes in rotation, illumination and scale. Several improvements are proposed to a previously published Phase Correlation based algorithm, which operates on local disc areas, using the Log Polar Transform to sample the disc neighborhood and the FFT to obtain the phase. It will be shown that the matching can be done in the frequency domain directly, using the Chi-squared distance, instead of computing the cross power spectrum. Moreover, it will be shown how combining these methods yields an algorithm that sorts out a majority of the false positives. The need for a peak to sub lobe ratio computation in order to cope with sub pixel accuracy will be discussed as well as how the FFT of the periodic component can enhance the matching. The result is a robust local feature matcher that is able to cope with rotational, illumination and scale differences to a certain degree.

Simple filter design for first and second order derivatives by a double filtering approach

Spline filters are usually implemented in two steps, where in the first step the basis coefficients are computed by deconvolving the sampled function with a factorized filter and the second step reconstructs the sampled function. It will be shown how separable spline filters using different splines can be constructed with fixed kernels, requiring no inverse filtering. Especially, it is discussed how first and second order derivatives can be computed correctly using cubic or trigonometric splines by a double filtering approach giving filters of length 7.

A Segmentation-Free Handwritten Word Spotting Approach by Relaxed Feature Matching

The automatic recognition of historical handwritten documents is still considered a challenging task. For this reason, word spotting emerges as a good alternative for making the information contained in these documents available to the user. Word spotting is defined as the task of retrieving all instances of the query word in a document collection, becoming a useful tool for information retrieval. In this paper we propose a segmentation-free word spotting approach able to deal with large document collections. Our method is inspired on feature matching algorithms that have been applied to image matching and retrieval. Since handwritten words have different shape, there is no exact transformation to be obtained. However, the sufficient degree of relaxation is achieved by using a Fourier based descriptor and an alternative approach to RANSAC called PUMA. The proposed approach is evaluated on historical marriage records, achieving promising results.

Retrospective illumination correction of greyscale historical aerial photos

Illumination correction is a method aiming at removing the influence of light from the environment and other distorting factors in the image capture process. A novel algorithm based on luminance mapping is proposed that both removes the low frequency variations in intensity as well as increases the contrast in low contrast areas. Moreover, it avoids the common problems with homomorphic filters. This algorithm is being applied on historical aerial photos with good results.

A chronological and mathematical overview of digital circle generation algorithms : Introducing efficient 4- and 8-connected circles

Circles are one of the basic drawing primitives for computers and while the naive way of setting up an equation for drawing circles is simple, implementing it in an efficient way using integer arithmetic has resulted in quite a few different algorithms. We present a short chronological overview of the most important publications of such digital circle generation algorithms. Bresenham is often assumed to have invented the first all integer circle algorithm. However, there were other algorithms published before his first official publication, which did not use floating point operations. Furthermore, we present both a 4- and an 8-connected all integer algorithm. Both of them proceed without any multiplication, using just one addition per iteration to compute the decision variable, which makes them more efficient than previously published algorithms.

Towards automatic stereo pair extraction for 3D visualisation of historical aerial photographs

An efficient and almost automatic method for stereo pair extraction of aerial photos is proposed. There are several challenging problems that needs to be taken into consideration when creating stereo pairs from historical aerial photos. These problems are discussed and solutions are proposed in order to obtain an almost automatic procedure with as little input as possible needed from the user. The result is a rectified and illumination corrected stereo pair. It will be discussed why viewing aerial photos in stereo is important since the depth cue gives more information than single photos do.