We propose an approach that can reduce the feature extraction time of the Scale Invariant Feature Transform (SIFT). The main idea is to search for the keypoints around a set of randomly generated particles rather than to perform exhaustive search in the whole difference of Gaussian pyramid. The proposed approach makes it possible to define the required number of keypoints in advance. A relation...

Human detection in camera attract wide interest because of its extensive applications in anomalous incident recognition, counting human being in a crowded area, person classification, and recognition of falling activity for aged people, etc. The paper discuss abnormalities in the human activity and provide efficient solution to detect abnormality. The first step in the proposed work is to captu...

We propose the n-dimensional scale invariant feature transform (n-SIFT) method for extracting and matching salient features from scalar images of arbitrary dimensionality, and compare this method's performance to other related features. The proposed features extend the concepts used for 2-D scalar images in the computer vision SIFT technique for extracting and matching distinctive scale invaria...

In this paper we introduce a general purpose graphical processing unit (GPGPU) based method for performing a sweep across a set of the scale invariant feature transform (SIFT) parameters for pairs of images. The focus of the paper is the analysis of the data generated using information visualisation techniques including a cross brushing technique between parallel coordinates, scatter plots and ...

The SIFT (Scale Invariant Feature Transform) is a computer vision algorithm that is used to detect and describe the local image features. The SIFT features are robust to changes in illumination, noise, and minor changes in viewpoint. The SIFT features have been used object recognition, image retrieval and matching, and so on.. The research of SIFT descriptors and improved SIFT descriptors is im...

Scale-invariant feature transform (SIFT) was an algorithm in computer vision to detect and describe local features in images. Due to its excellent performance, SIFT was widely used in many applications, but the implementation of SIFT was complicated and time-consuming. To solve this problem, this paper presented a novel acceleration algorithm for SIFT implementation based on Compute Unified Dev...

The SIFT algorithm[1] takes an image and transforms it into a collection of local feature vectors. Each of these feature vectors is supposed to be distinctive and invariant to any scaling, rotation or translation of the image. In the original implementation, these features can be used to find distinctive objects in differerent images and the transform can be extended to match faces in images. T...

–A detailed study on feature extractors in spatial and transformed domain is carried out in this work. The survey in Spatial domain include most of the traditional detectors until recently the SIFT and its variants. In the transformed domain, the detectors developed using the Fourier transforms to wavelet transforms have been explored. The advantages and the limitations of each one of them is e...

A novel digital image stabilization approach using Harris and Scale Invariant Feature Transform (SIFT) was presented in this article. Using SIFT in digital image stabilization, too many feature points and matches were extracted, but some of them were not so stable. Using these feature points and matches can not only increase the computational effort, but also enhance the wrong matching probabil...

TSR (Traffic sign recognition) has been studied for realizing drivers assisting system and automated navigation and is an important studied field in ITS (Intelligent traffic system). In this paper, a recognition method of traffic signs separated from real image was studied. Images were divided into several categories according to the actual weather, distance and angle of view etc. SIFT was firs...