Matching precision of scale-invariant feature transform (SIFT) is evaluated and improved in this paper. The aim of the paper is not to invent a new feature detector more invariant than the others. Instead, we focus on SIFT method and evaluate and improve the matching precision, defined as the root mean square error (RMSE) under ground truth geometric transform. Matching precision reflects to so...

This report deals with parallel algorithms for computing discrete Fourier transforms of real sequences of length N not equal to a power of two. The method described is an extension of existing power of two transforms to sequences with N a product of small primes. In particular, this implementation requires N = 2 p 3 q 5 r. The communication required is the same as for a transform of length N = ...

The necessary and sufficient conditions for a class of functions f : Z 2 → Zq, where q ≥ 2 is an even positive integer, have been recently identified for q = 4 and q = 8. In this article we give an alternative characterization of the generalized Walsh-Hadamard transform in terms of the Walsh spectra of the component Boolean functions of f , which then allows us to derive sufficient conditions t...

Matching results depend on a chosen threshold for the Lowe criterion [3], i.e., a maximum value for the ratio of the descriptor distance of the best match to the descriptor distance of the second best match. In our test, we use for ASIFT a maximum Lowe score of 0.73, which is the default value of the provided implementation. For SIFT [3], to put us in the worst situation (many ambiguities, henc...

Object identification using Scale-Invariant Feature Transform (SIFT) keypoints requires stable keypoint signatures that can be reliably reproduced across variations in lighting, viewing angle, as well as camera imaging characteristics. While reproducibility has been demonstrated under various lighting and viewing angles elsewhere, this work performs an empirical evaluation of the reproducibilit...

We present a method for vision-based recovery of threedimensional structures through simultaneous model reconstruction and camera position tracking from monocular images. Our approach does not rely on robust feature detecting schemes (such as SIFT, KLT etc.), but works directly on intensity values in the captured images. Thus, it is well-suited for reconstruction of surfaces that exhibit only m...

In this work, we study efficiency of SIFT descriptor in discrimination of binary shapes. We also analyze how the use of 2 − tuples of SIFT keypoints can affect discrimination of shapes. The study is divided into two parts, the first part serves as a primary analysis where we propose to compute overlap of classes using SIFT and a majority vote of keypoints. In the second part, we analyze both cl...

Many presentations consisting of video, audio and slides are being recorded for wider dissemination purposes. Video slide alignment is necessary for efficient review and hence has attracted much attention. However, the recorded video style varies greatly because of different capturing systems, and most existing alignment approaches deal with one of the video styles. In this paper, a more genera...

This paper presents an integrated approach for robustly locating facial landmark for drivers. In the first step a cascade of probability learners is used to detect the face edge primitives from fine to coarse, so that faces with variant head poses can be located. The edge density descriptors and skin-tone color features are combined together as the basic features to examine the probability of a...