A complete processor for SIFT feature matching in video sequences

The Scale Invariant Feature Transform (SIFT) feature can be used for an image distance measure. SIFT keypoints are mainly located on high-contrast regions of an image, such as object edges and textures, which are often visually important. Therefore, it can be said that if a resized image keeps SIFT features which the corresponding original image has, the resized image is visually acceptable. To the best of our knowledge, there is no resizing method for explicit preservation of SIFT features. In this paper, we propose a resizing method based on mesh warping for explicit preservation of SIFT features. The effectiveness of our resizing method is demonstrated by experiments.

Aiming at the problems of large calculating scale and high complexity in Scale Invariant Feature Transform (SIFT) feature matching algorithm, this paper presents an improved SIFT feature matching algorithm based on quasi Euclidean distance.The traditional Euclidean distance can only calculate out the variance of the two images to the corresponding pixel, so when a slight shift or distortion occurs in the image, it may produce a large deviation.The quasi Euclidean distance instead of Euclidean distance is as the similarity measure of feature descriptors to improve the SIFT feature matching.It reduces the dimensions of SIFT feature vector to improve the efficiency of feature matching.Experimental results show that under the condition of keeping the image matching rate and algorithm robust, the method can not only improve the matching accuracy but also shorten the matching time.The new algorithm has better performance than traditional algorithm, it is possible and valid, which are useful for the fields of image recognition, image reconstruction, etc.

Image stitching is one of the branches of computer vision. It combines two or more images for a scene to acquire a high-resolution panoramic image. An invariant local function often uses to stitch two images together. Since the flat plate of a digital radiography (DR) system does not cover all parts of the body, the whole bone structure image cannot seize in a single scan. To solved this problem, image stitching is broadly utilized by medical systems to stitch DR images, which can be helpful for scoliosis or lower extremity deformities in the diagnosis, and pre-operative planning are of great importance. In this paper, the stitching and retrieval of medical images planned. To conquer the background noise in medical images, and improve the recovery of quality and stitching rapidity of medical images, a random sample consensus (RANSAC) algorithm is useful to stitching the images of Chest digital radiography by scale-invariant feature transform (SIFT) and speeded-up robust features (SURF) feature extraction. Down-sampling utilizes to lessen the size of the images and reduction the measure of calculation. In the interim, the phase correlation is engaged to discover the overlapping region. After feature matching and perspective transformation, the stitched image is gotten dependent on the homography. At last, experimentation has finished showing the presentation.

Copy-move forgery is a general widespread type of digital image forgery, where a segment of an image is attached into a new portion of the similar image to hide or replicate the parts which are called forgered image. The forgered image appears original, as the objective region in spite of being forged, has attained the fundamental qualities of the similar image itself. The capability of the copy-move forgery detection (CMFD) technique is lacked due to some post-processing functions, like JPEG compression scaling, or rotation, etc. Therefore, this paper intends to develop a CMFD using Scale-invariant feature transform (SIFT), best-fin-first algorithm (BBF) and RANdom SAmple Consensus (RANSAC) directed by grey wolf optimization (GWO) algorithm. Initially, the keypoints are selected using SIFT principle, and BBF algorithm identifies the matched keypoints using keypoint threshold. Further, SIFT feature descriptor is determined, and the final extracted paired keypoints are given to RANSAC algorithm to remove all the mismatched keypoints. In this CMFD model, the parameters such as parameters keypoint threshold, maximum distance of inliers in RANSAC and distance threshold in SIFT features are optimized using GWO. The foremost purpose of this research work is maximizing the number of paired keypoints. Hence the proposed model is termed as GWO-based parameter optimization for CMFD (GWPO-CMD). The proposed model is compared over several other meta-heuristic-based keypoint threshold selections and proves its efficiency through diverse analysis.

In computer vision, Local Binary Pattern (LBP) and Scale Invariant Feature Transform (SIFT) are two widely used local descriptors. In this paper, we propose to combine them effectively for scene categorization. First, LBP and SIFT features are regularly extracted from training images for constructing a LBP feature codebook and a SIFT feature codebook. Then, a two-dimensional table is created by combining the obtained codebooks. For creating a representation for an image, LBP and SIFT features extracted from the same positions of the image are encoded together based on sparse coding by using the two-dimensional table. After processing all features in the input image, we adopt spatial max pooling to determine its representation. Obtained image representations are forwarded to a Support Vector Machine classifier for categorization. In addition, in order to improve the scene categorization performance further, we propose a method to select correlated visual words from large codebooks for constructing the two-dimensional table. Finally, for evaluating the proposed method, extensive experiments are implemented on datasets Scene Categories 8, Scene Categories 15 and MIT 67 Indoor Scene. It is demonstrated that the proposed method is effective for scene categorization.

Face recognition includes analysis of an image and extracting its facial features which will help to discriminate it from others. Scale invariant feature transform (SIFT) to extract distinctive invariant features from images can be used to perform reliable matching. The features extracted are invariant to rotation, image scale and illumination. Systematic investigation of face recognition using SIFT features has been done. Being high distinctive features, every feature can be matched correctly with high probability against a huge database of features from many images. Result shows that SIFT is flexible recognition algorithm as compared to Contour matching algorithm for heterogeneous images. Both the algorithms are experimentally evaluated on AT&T, YALE and IIT-KANPUR databases with moderate subject size. Though Contour matching provides computational simplicity, SIFT provides efficient face recognition technique under pose, expression and varying illumination condition. Experimentally it confirms that Contour matching outperforms when the database is small but for large databases Scale Invariant Feature Transform (SIFT) gives more than 90% recognition rate.

Iris feature extraction is the crucial stage of the whole iris recognition process. A brief introduction of iris recognition system is made firstly in this paper, then presented the method of iris feature extraction and matching using Scale Invariant Feature Transform (SIFT). Through analyzing iris feature extraction and matching method, we found in conventional iris recognition system, Iris features are not consistent because most feature extraction techniques are sensitive to the variations of captured iris image data, are impacted of natural illumination or other variant conditions easily. So this paper used SIFT feature which is invariant to image scaling and rotation, and partially invariant to change in illumination. They are also well localized in both the spatial and frequency domains. SIFT feature shows a higher feasibility in the iris feature extraction and matching process.

In this paper we propose a novel feature based on SIFT (Scale Invariant Feature Transform) algorithm1 for the robust representation of local visual contents. SIFT features have raised much interest for their power of description of visual content characterizing punctual information against variation of luminance and change of viewpoint and they are very useful to capture local information. For a single image hundreds of keypoints are found and they are particularly suitable for tasks dealing with image registration or image matching. In this work we stretched the spatial coverage of descriptors creating a novel feature as composition of keypoints present in an image region while maintaining the invariance properties of SIFT descriptors. The number of descriptors is reduced, limiting the computational weight, and at the same time a more abstract descriptor is achieved. The new feature is therefore suitable at describing objects and characteristic image regions. We tested the retrieval performance with a dataset used to test PCA SIFT2 and image matching capability among images processed with affine transformations. Experimental results are reported.

Visual words image representation has been very popular in tag ranking of social image. However, the descriptive power of detected features is not evaluated in traditional visual words model, resulting in many non-descriptive local features are clustered as visual words. Moreover, the time consumption will be increased during quantification phase due to compare with all visual words. To overcome these problems, the descriptive visual word tree is created for tag ranking of social image in this paper. Firstly, the social image saliency region is detected with visual attention model. Then, the descriptive visual word tree can be created by clustering the descriptive Scale Invariant Feature Transform (SIFT) features which consist of refined SIFT features and corner SIFT features extracted from saliency region. Finally, the tags of weighted neighbor images, which are found by descriptive visual word tree, are applied to rank the tags. Experimental results indicate that the proposed descriptive visual word tree can effectively improve the accuracy of tag ranking of social image as well as reduce the time of tag ranking.

At present, most of the existing seal image registration methods are based on shape, and most of the methods can't tolerate the image scale change. To overcome these problems, a general seal registration and identification approach is proposed in this paper. This method uses the classic scale invariant feature transform (SIFT) algorithm to extract the key points. To register the seal accurately, the Random Sample Consensus (RANSAC) algorithm and the Least Squares Method (LSM) are used to obtain the transformational matrix. Then the invariant features are extracted based on residual image. At last, the Normal Bayesian classifier (NBC), K-Nearest Neighbor classifier (K-NN) and the Support Vector Machine (SVM) are combined to classify the feature vector. The experiments demonstrate the identification ability of the proposed approach.

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 probability. We proposed to use SIFT to detect feature points and incorporate the Harris criterion to select the most stable feature points in the video sequence where image motion was happened due to vehicle or platform vibration. With these feature points, we use general feature descriptor and matching algorithm to achieve the image stabilization. Experimental results show that the proposed algorithm can not only bring down the probability of wrong matching and get more accurate matches, but also reduce the computation burden than SIFT effectively.

This paper uses the specific SIFT (Scale Invariant Feature Transform) feature and a fast kd-tree matching strategy combined with invariant feature to solve single face recognition problems. It transforms face image data into scale-invariant coordinates relative to local features. The similarity was computed using Euclidean distance and kd-tree search. Experiments show that the features are invariant to image scaling, translation, rotation, and change in viewpoint.

Indexing images represents a necessary tool for various domains related to computer vision such as video surveillance and movements analysis. Visual characteristics of image such as color, texture, shape are used to identify the content of these frames. The high increase of data (Big Data) makes us face a problem of curse of dimensionality. In this paper, we propose a cloud-based technique for images indexing images using PCA (Principal component analysis) and a binary tree. Our work consists of exploiting SIFT (Scale Invariant Feature Transform) and SURF (Speeded up Robust Features) descriptors as frames features, PCA as dimensionality reduction method of SIFT and SURF features and the binary tree representation of these images in order to accelerate the research phase and reduce the storage space. Our approach consists of developing a system based on three phases: indexing images with SIFT and SURF features, compression within the application of PCA and finally the image retrieval in the cloud.

In recent years, Ambient Intelligence (AmI) has attracted increased attention within the advanced technology industry in an effort to modernize and develop a more intelligent and reliable information system. Technologies to detect a specific object in images are expected to further expand to wide range of applications, such as car detection functions for Intelligent Transport System (ITS) and other systems. Computer vision and pattern recognition are emerging fast and will continue to grow together with local feature detection methods. In this paper, we propose an object detection and tracking system which is based on Scale Invariant Feature Transform (SIFT) and Speed Up Robust Features (SURF) feature extraction methods. From the evaluation results, we observe that the accuracy of matched keypoints of SURF algorithm are higher than SIFT.

Public health data indicate that breast cancer is a major health problem among women worldwide, measured by the occurrence, mortality, and economic cost of diagnosis. Digital Image Elasto Tomography (DIET) system is a non-invasive breast cancer screening approach based on induced mechanical sinusoidal vibrations to the breast surface. Fiducial markers were applied on the breast, and an array of five digital cameras captures surface oscillations. Scale Invariant Feature Transform (SIFT) algorithm used to extract interest points from the image for estimating the frequency of motion. After removing the background of pendant breast, SIFT features were extracted using the skin texture. The movement of the breast surface was tracked by using the SIFT points instead. Separate modal analysis was applied to the SIFT points for detecting the presence and location of the tumor. In the second case, separate modal analysis was applied using both SIFT points and fiducial markers on given clinical and phantoms data. Clinical data of two healthy and two affected patients with breast cancer were used for cancer detection by extracting SIFT features from the bare skin. Results were matching when compared with a clinical summary of the patient's details. Given results indicate the tumor's presence and location and removes empty spaces compared to only markers based system.