A Rotation Invariance Image Matching Method Based on Harris Corner Detection

Competition between Points of Interest (POIs) refers to the situation in which two POIs directly or indirectly provide similar services to secure businesses. A large portion of prior studies on competition analysis focuses on mining textual data, e.g., news articles and social comments. However, the increasing availability of human mobility and mobile query data enables a new paradigm for analyzing the competitive relationships among POIs, which remains largely unexplored. To this end, in this paper, we attempt to mine large-scale online map search query data for better understanding POI competitive relationships. Based on a co-query POI graph built from the map search query data, we develop a novel neural graphlet-based prediction framework to predict the competitive relationships among POIs. A unique perspective of our model is to infer latent POI competitive relationships by integrating multiple distinct factors, e.g., graphlet structure, geographical distance, and regional features, reflected in map search query data and POI data. Finally, we conduct extensive experiments on real-world datasets to demonstrate the effectiveness of the proposed framework, and show that our framework outperforms all baselines with a significant margin in all evaluation metrics.

Interest points have traditionally been favoured over dense features for image retrieval tasks, where the goal is to retrieve images similar to a query image from an image corpus. While interest points are invariant to scale and rotation, their coverage of the image is not adequate for sub-image retrieval problems, where the query image occupies a small part of the corpus image. On the other hand, dense features provide excellent coverage but lack invariance, as they are computed at a fixed scale and orientation. Recently, we proposed a novel technique of combining dense features with interest points (Bhattacharya and Gavrilova, Vis Comput 29(6---8):491---499, 2013) to leverage the benefits of both worlds. This allows dense features to be scale invariant but not rotation invariant. In this paper, we build on this framework by incorporating rotation invariance for dense features and introducing several improvements in the voting and match score computation stages. Our method can produce high-quality recognition results that outperform bag of words even with geometric verification and several state-of-art methods that have considered spatial information. We achieve significant improvements in terms of both search speed and accuracy over (Bhattacharya and Gavrilova, Vis Comput 29(6---8):491---499, 2013). Experiments on Oxford Buildings, Holidays and UKbench datasets reveal that our method is not only robust to viewpoint and scale changes that occur in real-world photographs but also to geometric transformations.

Due to the availability of media editing software, the authenticity and reliability of digital images are important. Region manipulation is a simple and effective method for digital image forgeries. Hence, the potential to identify the image manipulation is current research issue these days and copy–move forgery detection (CMFD) is a main domain in image authentication. In copy–move forgery, one region is simply copied and pasted over other region in the same image for manipulating the image. In this paper, we have proposed a method based on Harris corner and adaptive non-maximal Suppression (ANMS). Initially, the input image is taken, and then Harris corner detection algorithm is used to detect the interest points, and ANMS is adopted to control the number of Harris points in an image. This gives an appropriate number of interest points for different size of images and gives the assurance for finding the manipulated region in manageable time. For each extracted interest point, SIFT is used for calculating the descriptors. Now obtained descriptors are matched using the outlier rejection with nearest neighbour. Here RANSAC is used to find the best set of matches to identify the manipulated regions. Experimental results show the robustness against different transformation and post-processing operations.

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.

Identifying feature correspondences between multimodal images is facing enormous challenges because of the significant differences both in radiation and geometry. To address these problems, we propose a novel feature matching method (named R <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> FD <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> ) that is robust to radiation and rotation differences, which consists of a repeatable feature detector and a rotation-invariant feature descriptor. In the first stage, a repeatable feature detector called the Multi-channel Auto-correlation of the Log-Gabor (MALG) is presented for feature detection, which combines the multi-channel auto-correlation strategy with the Log-Gabor wavelets to detect interest points (IPs) with high repeatability and uniform distribution. In the second stage, a rotation-invariant feature descriptor is constructed, named the Rotation-invariant Maximum index map of the Log-Gabor (RMLG), which includes fast assignment of dominant orientation and construction of feature representation. In the process of fast assignment of dominant orientation, a Rotation-invariant Maximum Index Map (RMIM) is built to address rotation deformations. Then, the proposed RMLG incorporates the rotation-invariant RMIM with the spatial configuration of DAISY to improve RMLG’s resistance to radiation and rotation variances. Finally, we conduct experiments to validate the matching performance of our R <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> FD <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> utilizing different types of multimodal image datasets. Experimental results show that the proposed R <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> FD <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> outperforms five state-of-the-art feature matching methods. Moreover, our R <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> FD <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> achieves the accuracy of matching within two pixels and has a great advantage in matching efficiency over contrastive methods.

In this paper, we consider whether statistical regularities in natural images might be exploited to provide an improved selection criterion for interest points. One approach that has been particularly influential in this domain, is the Harris corner detector. The impetus for the selection criterion for Harris corners, proposed in early work and which remains in use to this day, is based on an intuitive mathematical definition constrained by the need for computational parsimony. In this paper, we revisit this selection criterion free of the computational constraints that existed 20 years ago, and also importantly, taking advantage of the regularities observed in natural image statistics. Based on the motivating factors of stability and richness of structure, a selection threshold for Harris corners is proposed based on a definition of optimality with respect to the structure observed in natural images. As a whole, the paper affords considerable insight into why existing approaches for selecting interest points work, and also their shortcomings. We also demonstrate how a proposal that is inspired by the properties of natural image statistics might be applied to overcome these shortcomings.

With the development of the manufacturing technique of the microchip, the integral performance of the Field-Programmable Gate Array (FPGA) is becoming more and more adaptive for real-time embedded systems. Interest point detection is a prime step in many advanced computer vision applications such as 3-D reconstruction, 3-D object tracking and so on. Many image processing algorithms need to extract interest point in advance. We can easily implement these algorithms in software, but it can't meet with the request of a real-time embedded systems because of its low speed. In this paper, we achieved a hardware implementation of the Harris corner feature detector based on Zedboard platform which is a heterogeneous SoC composed of two ARM9 chips and a Xilinx xc7z020-clg484-1 chip. The hardware architecture is implemented with Verilog HDL and consists of 6 modules: CMOS register initialization, CMOS data fetcher, CMOS data graying, block RAM frame buffer, Harris Corner Detector(HCD), HDMI displayer. The implementation can process RGB565 video in 640×480 resolution. According to the simulation results, the hardware implementation can extract Harris corner at the speed of 154 frames per second. It can meet most requirements for real-time computer vision applications.

To facilitate processing of 3D objects is common to use high-level representations. The interest points are one of them. An interest point should possess a distinctive feature regarding its locality and should be stable in different instances of the object. This article proposes a descriptor based on symmetry (GISIFs) and heat diffusion (HKS). From this features, we select a set of representative points. The GISIFs referenced in this article has not been used to extract local features. We compare our results with the results of other techniques, which make up the state of the art in interest point detection. We use a benchmark that evaluates the accuracy of the selected points with respect to an ideal set of interest points.

Objectives: With the rise of locative media fostered by the growing ubiquity of mobile devises, many researches to detect users’ preferred location information have been actively studied. Methods/Statistical Analysis: This paper proposes a method for hot place detection based on social media contents. Especially, we focus on POIs (Point-Of-Interests) disambiguation using linguistic clues based on social media content analysis. We try to combine implicit clues using linguistic analysis and geometric metadata which are embedded in tweet mentions. This feature can help to overcome the limitation of using explicit information only. Findings: By experiment results based on real tweet data, we show the effects and usage of our proposed method. Improvements/Applications: The POI method can also be enhanced by considering other efficiency metrics.

On an algorithm for human action recognition

Many of the near-duplicate (ND) image detection methods involve a greater number of interest points (IPs) and large dimensions of the feature descriptors requiring huge computations and are unsuitable for large image databases. They may fail to detect NDs if the query and images in the database contain sparse IPs due to low entropy. Besides, the k-means algorithm used for the quantization of visual words may land at a sub-optimal minimum for descriptors because of their distance distribution in feature space. This article presents a new ND image detection method, which uniformly distributes the IPs over low and high entropy regions, reduces the dimension of feature descriptors using discrete wavelet transform (DWT) and employs Seagull Optimization algorithm (SOA) for optimally forming the visual words. It examines proposed method performs on image databases of various sizes and shows that the developed method is more reliable and computationally efficient than the alternatives.

In this paper, a simple and fast algorithm was proposed to detect face. Firstly, some interest points marking skin regions were searched by only using simple chrominance Cr information instead of simultaneously using chrominance Cr and Cb. And then, a conventional and popular AdaBoost algorithm was employed to make a decision whether around the detected interest points was there face and then located the face if there was. 400 face patches were translated into YCbCr space, and it was found from the 400 face patches that skin Cr histogram overlapped a little with non-skin Cr histogram and its cut-off was about 137. From LFW database, another 215 facial images of 108 subjects were random selected to test the proposed method. Compared with other interest detection methods, the detection based simple Cr method can not only find out all face regions, but also the number of its detected interest points was the least and the whole detection time was the least too. Therefore, the proposed method was an effective face detection method.

A feature-based matching scheme: MPCD and robust matching strategy

Image based target used in augmented reality application is not the same as traditional fiducial markers, data markers code and QR-codes in detection and tracking. The available features from the image detected and tracked are naturally found in the image itself. Image target commonly used in recognizing and augmented hard copy media and product for marketing campaigns, gaming, and visualizing products in the environment where the product was targeted to be used. HOwever, for mobile-based augmented reality application, image features detection and tracking still expose many challenges. This paper aims to review previous and current keypoint detection and tracking techniques for image target and address several issues face in mobile based augmented reality application. Most traditional interest-point detection and description methods are handcrafted. These methods focus on interest points in a generic setting and lack provision to adapt toward a specific dataset. Learning-based approaches can be a new solution to real-time application such mobile-based application. This project continuity work from our previous work done for mobile-based augmented reality coloring application [1].

At present, there are many methods to realize the matching of specified images with features, and the basic components include image feature point detection, feature description, and image matching. Based on this background, this article has done different research and exploration around these three aspects. The image feature point detection method is firstly studied, which commonly include image edge information-based feature detection method, corner information-based detection method, and various interest operators. However, all of the traditional detection methods are involved in problems of large computation burden and time consumption. In order to solve this problem, a feature detection method based on image grayscale information-FAST operator is used in this paper, which is combined with decision tree theory to effectively improve the speed of extracting image feature points. Then, the feature point description method BRIEF operator is studied, which is a local expression of detected image feature points based on descriptors. Since the descriptor does not have rotation invariance, the detection operator is endowed by a direction that is proposed in this paper, and then the local feature description is conducted on the feature descriptor to generate a binary string array containing direction information. Finally, the feature matching machine learning method is analyzed, and the nearest search method is used to find the nearest feature point pair in Euclidean distance, of which the calculation burden is small. The simulation results show that the proposed nearest neighbor search and matching machine learning algorithm has higher matching accuracy and faster calculation speed compared with the classical feature matching algorithm, which has great advantages in processing a large number of array images captured by the light field camera.