A quick scale-invariant interest point detecting approach

In this paper, a novel face representation in terms of dense local image descriptors is proposed. Scale Invariant Feature Transform (SIFT) and Gabor, two of the most popular local image descriptors, at dense grid pixels of a face image are used to represent the face. The efficiency of the representation has been investigated in gender recognition. There are four problems when applying the SIFT to facial gender recognition. (1) There may be only a few keypoints that can be found in a face image due to the missing texture and ill-illumined faces; (2) The SIFT descriptors at the keypoints (we called it sparse SIFT) are distinctive whereas alternative descriptors at non-keypoints (e.g. grid) could cause negative impact on the accuracy; (3) Most of the existing methods employ SIFT descriptors matching in which relative larger image size is required in order that enough keypoints can be found to support the matching and (4) The matching is assumed that the faces are well registered. We provide solutions to the above difficulties in this paper and the problem of recognizing gender using the combination of SIFT descriptors and Gabor of face images is studied. The Gabor representations of the face images are fused with the dense SIFT at the feature-level to improve the accuracy. AdaBoost is adopted to select features and form a strong classifier. The experimental results on a large set of faces have shown that the proposed method can achieve high accuracies even for faces that are not aligned.

This paper proposes a novel image compression scheme based on the local feature descriptor - Scale Invariant Feature Transform (SIFT). The SIFT descriptor characterizes an image region invariantly to scale and rotation. It is used widely in image retrieval. By using SIFT descriptors, our compression scheme is able to make use of external image contents to reduce visual redundancy among images. The proposed encoder compresses an input image by SIFT descriptors rather than pixel values. It separates the SIFT descriptors of the image into two groups, a visual description which is a significantly sub sampled image with key SIFT descriptors embedded and a set of differential SIFT descriptors, to reduce the coding bits. The corresponding decoder generates the SIFT descriptors from the visual description and the differential set. The SIFT descriptors are used in our SIFT-based matching to retrieve the candidate predictive patches from a large image dataset. These candidate patches are then integrated into the visual description, presenting the final reconstructed images. Our preliminary but promising results demonstrate the effectiveness of our proposed image coding scheme towards perceptual quality. Our proposed image compression scheme provides a feasible approach to make use of the visual correlation among images.

With the advent of e-commerce, digital services and social media, scammers have changed their way to gain illegal benefits in various forms such as capturing the credit card information or exploiting personal cloud accounts which is termed as phishing. For this reason, against this cyber crime, last two decades have witnessed a variety of combatting methodologies like HTML content based similarity analysis, URL based classification and recently visual similarity based matching since phishing web pages visually mimic to their legitimate counterparts in order to create an illusion to deceive innocent users. To this end, in this study, we propose a computer vision and machine learning based approach in order to classify whether a suspicious web page is phishing and further recognize its original brand name. In this regard, we have utilized and investigated two different local image descriptors namely Scale Invariant Feature Transform (SIFT) and DAISY. Apart from their common properties such as scale invariance, the aforementioned descriptors have apparent differences such that in addition to rotational invariance, SIFT employs key-point based sampling whereas DAISY applies dense sampling by default. Therefore, we first aimed to investigate the feasibility of these two local image descriptors in addition to revealing the effects of sampling strategy and rotational invariance in problem domain. Furthermore, in order to create a discriminative representation of a web page, we followed the bag of visual words (BOVW) approach having different vocabulary sizes such as 50, 100, 200 and 400. In order to evaluate the proposed approach, we have utilized a publicly available phishing dataset including snapshots of webpages sampled from both 14 different highly phished brands and ordinary legitimate web pages yielding a challenging open-set problem. The aforementioned dataset involves 1313 training and 1539 testing image samples in total. The visual features extracted via SIFT and DAISY were first transformed to a BOVW histogram and fed to three different machine learning methods such as SVM, Random Forest and XGBoost. According to the conducted experiments, based on a 400-D visual vocabulary, SIFT descriptor along with XGBoost has been found as the best descriptor-learner configuration having reached up to 89.34% validation accuracy with 0.76% false positive rate. Moreover, SIFT has outperformed DAISY descriptor in all settings. As a result, it has been shown that SIFT descriptors equipped with BOVW representation can be effectively used for brand identification of phishing web pages.

This paper provides a new feature extraction method for object recognition using PCA-KNN algorithm with SIFT descriptor. The proposed method is divided into three steps. The first step is based on feature extraction from the input images using SIFT (Scale Invariant Feature Transform) descriptor. Each of the features is represented using one or more feature descriptors. In medical systems images used as patterns are also represented by feature vectors. In the second step eigen values and eigen vectors are extracted from each image. We apply PCA algorithm after we reduce the number of features by SIFT algorithm. The goal is to extract the important information as a set of new orthogonal variables called principal components. In the final step a nearest neighbor classifier is designed for classifying the images based on the extracted features. The algorithm is experimented in MATLAB and tested with the Caltech 101 database and the experimental results are shown.

The performance of matching and object recognition methods based on interest points depends on both the properties of the underlying interest points and the choice of associated image descriptors. This paper demonstrates advantages of using generalized scale-space interest point detectors in this context for selecting a sparse set of points for computing image descriptors for image-based matching. For detecting interest points at any given scale, we make use of the Laplacian $$\nabla ^2_{norm} L$$?norm2L, the determinant of the Hessian $$\det {\mathcal {H}}_{norm} L$$detHnormL and four new unsigned or signed Hessian feature strength measures $${\mathcal {D}}_{1,norm} L$$D1,normL, $$\tilde{\mathcal {D}}_{1,norm} L$$D~1,normL, $${\mathcal {D}}_{2,norm} L$$D2,normL and $$\tilde{\mathcal {D}}_{2,norm} L$$D~2,normL, which are defined by generalizing the definitions of the Harris and Shi-and-Tomasi operators from the second moment matrix to the Hessian matrix. Then, feature selection over different scales is performed either by scale selection from local extrema over scale of scale-normalized derivates or by linking features over scale into feature trajectories and computing a significance measure from an integrated measure of normalized feature strength over scale. A theoretical analysis is presented of the robustness of the differential entities underlying these interest points under image deformations, in terms of invariance properties under affine image deformations or approximations thereof. Disregarding the effect of the rotationally symmetric scale-space smoothing operation, the determinant of the Hessian $$\det {\mathcal {H}}_{norm} L$$detHnormL is a truly affine covariant differential entity and the Hessian feature strength measures $${\mathcal {D}}_{1,norm} L$$D1,normL and $$\tilde{\mathcal {D}}_{1,norm} L$$D~1,normL have a major contribution from the affine covariant determinant of the Hessian, implying that local extrema of these differential entities will be more robust under affine image deformations than local extrema of the Laplacian operator or the Hessian feature strength measures $${\mathcal {D}}_{2,norm} L$$D2,normL, $$\tilde{\mathcal {D}}_{2,norm} L$$D~2,normL. It is shown how these generalized scale-space interest points allow for a higher ratio of correct matches and a lower ratio of false matches compared to previously known interest point detectors within the same class. The best results are obtained using interest points computed with scale linking and with the new Hessian feature strength measures $${\mathcal {D}}_{1,norm} L$$D1,normL, $$\tilde{\mathcal {D}}_{1,norm} L$$D~1,normL and the determinant of the Hessian $$\det {\mathcal {H}}_{norm} L$$detHnormL being the differential entities that lead to the best matching performance under perspective image transformations with significant foreshortening, and better than the more commonly used Laplacian operator, its difference-of-Gaussians approximation or the Harris---Laplace operator. We propose that these generalized scale-space interest points, when accompanied by associated local scale-invariant image descriptors, should allow for better performance of interest point based methods for image-based matching, object recognition and related visual tasks.

Histogram Intersection Kernel Support Vector Machines (SVM) was used for the image classification problem. Specifically, each image was split into blocks, and each block was represented by the Scale Invariant Feature Transform (SIFT) descriptors; secondly, k-means cluster method was applied to separate the SIFT descriptors into groups, each group represented a visual keywords; thirdly, count the number of the SIFT descriptors in each image, and histogram of each image should be constructed; finally, Histogram Intersection Kernel should be built based on these histograms. In our experimental study, we use Corel-low images to test our method. Compared with typical RBF kernel SVM, the Histogram Intersection kernel SVM performs better than RBF kernel SVM.

Image registration is an essential step in many remote-sensing (RS) applications. This article presents a study of a multisource image automatic registration system (MIARS) based on the scale-invariant feature transform (SIFT), which has been demonstrated to be the most robust local invariant feature descriptor for automatically registering various RS images. The SIFT descriptor has two shortcomings: it is unsuitable for extremely large images and has an irregular distribution of feature points. Therefore, three steps are proposed for the MIARS: image division, histogram equalization and the elimination of false point matches by a subregion least squares iteration. Image division makes it possible to use the SIFT descriptor to extract control points from an extremely large RS image. Histogram equalization in prematching improves the contrast sensitivity of RS images. The subregion least squares iteration refines the registration accuracy. Images from multisensor systems, including Quickbird, IRS-P6, Landsat/TM, HJ-CCD, HJ-IRS, light detection and ranging (LiDAR) intensity images and aerial data, were selected to test the reliability of the MIARS. The results indicated that better registration accuracy was achieved, which will be very helpful in the future development of a registration model.

For feature point detection with variable scale, rotation, variable illumination and variable 3D view port, a feature point detection and tracking method combining scale invariant feature transform (SIFT) and KLT (Kanade-Lucas-Tomasi) is proposed in this paper. SIFT feature point detection method is improved and it is used to detect feature points of image, and then KLT method is used to track the feature points continuously. In order to verify the feasibility of the proposed method, simulation experiments are carried out in real scene image sequences with different complexity using this method, better results of detection and tracking are obtained and the obtained feature point is more stable than conventional method.

The SIFT (scale invariant feature transform) has demonstrated its superior performance in identifying transformed images over many other approaches. However, both of its detection and matching stages are expensive, because a large number of keypoints are detected in the scale-space and each keypoint is described using a 128-dimensional vector. We present two possible solutions for feature-point reduction. First is to down scale the image before the SIFT keypoint detection and second is to use corners (instead of SIFT keypoints) which are visually significant, more robust, and much smaller in number than the SIFT keypoints. Either the curvature descriptor or the highly distinctive SIFT descriptors at corner locations can be used to represent corners.We then describe a new feature-point matching technique, which can be used for matching both the down-scaled SIFT keypoints and corners. Experimental results show that two feature-point reduction solutions combined with the SIFT descriptors and the proposed feature-point matching technique not only improve the computational efficiency and decrease the storage requirement, but also improve the transformed image identification accuracy (robustness).

Human action recognition has been a challenging task in computer vision because of intra-class variability. State-of-the-art methods have shown good performance for constrained videos but have failed to achieve good results for complex scenes. Reasons for their failing include treating spatial and temporal dimensions without distinction as well as not capturing temporal information in video representation. To address these problems we propose principled changes to an action recognition framework that is based on video interest points (IP) detection with capturing differential motion as the central theme. First, we propose to detect points with high curl of optical flow, which captures relative motion boundaries in a frame. We track these points to form dense trajectories. Second, we discard points on the trajectories that do not represent change in motion of the same object, yielding temporally localized IPs. Third, we propose a video representation based on spatio-temporal arrangement of IPs with respect to their neighboring IPs. The proposed approach yields a compact and information-dense representation without using any local descriptor around the detected IPs. It significantly outperforms state-of-the-art methods on UCF youtube dataset, which has complex action classes, as well as on KTH dataset, which has simple action classes.

In this paper, a color image representation approach is proposed for color image retrieval. First, an input color image is represented by a number representative images (called color degree images) consisting of chromatic (including red, green, blue, cyan, magenta, and yellow) and achromatic (including black and white) degree images. For each pixel, the degree to which its color value is similar to each representative color will be computed. For the local window centered at each detected key point, a vector representing the degree values, called local color degree (LCD) descriptor, will be computed to describe the local color property. Meanwhile, the scale-invariant feature transform (SIFT) descriptor is extracted to describe the local texture characteristics. Both LCD descriptor and SIFT descriptor are combined together to form the local descriptor. Vector of locally aggregated descriptors (VLAD) is then employed to aggregate all local descriptors to get a single VLAD vector for each input image. Experimental results on INRIA Holidays and Leeds Butterfly datasets have shown that the proposed descriptor yield higher retrieval accuracy.

Recently, the popularity of user generated videos has highlighted efficient video indexing and browsing as an urgent problem. Points of interest (POI) detection is a technique to address this issue by establishing the implicit relationship among different media resources. The majority of existing studies detect POI by visual similarity, leveraging computer vision techniques. However, these methods suffer from high computational complexity when processing large-scale video sets and are challenging due to the sparse visual correlation among different consumer videos. The advent of geo-referenced videos provides an opportunity to detect POIs in an efficient manner. In this work, we first propose a probability model to formulate the capture intention distribution for video frames. Second, we detect the POIs by considering the contributions from multiple videos. Evaluations demonstrate that our algorithm successfully detects POIs with a reduced error distance from several dozens to a few meters.

In this paper, we compare the results of five 3D interest point detection techniques to the interest points marked by human subjects. This comparison is used to quantitatively evaluate the interest point detection algorithms. We asked human subjects to look at a number of 3D models, and mark interest points on the models via a web-based interface. We propose a voting-based method to construct ground truth out of humans' selections of interest points. Evaluation measures, namely False Positive and False Negative Errors, are then defined based on the geodesic distance between the interest points detected by a particular algorithm and the human-generated ground truth.

In this study, a novel interest point detection algorithm which combines image intensity variation and edge contour information is proposed. Firstly, the Canny edge contour detector is used to extract the edge map. Secondly, the imaginary parts of multi‐scale Gabor filters are applied to smooth input image and then the normalised information entropies at various scales can be acquired. Finally, multiplication of different normalised information entropies will be served as a new measure for interest point that can also be used for interest point detection. This method has two advantages: on the one hand, detection accuracy is greatly improved because combination information is adopted to extract interest points including contour shape information, grey variation of edge pixels and their neighbours; on the other hand, non‐interest points can be well inhabited due to multi‐scale product in detector is served as an interest point measure. Also, desirable noise robustness and time efficiency are validated through experiments. Compared with four other state‐of‐art methods, the proposed method shows excellent performance in terms of geometric transformations and localisation accuracy of repeated interest points.

Local feature-based multi-object recognition scheme for surveillance