Loading...
Search for:
sift
0.006 seconds
A robust SIFT-based descriptor for video classification
, Article Proceedings of SPIE - The International Society for Optical Engineering, 19 November 2014 through 21 November 2014 ; Volume 9445 , November , 2015 , February ; 0277786X (ISSN) ; 9781628415605 (ISBN) ; Hosseini, M. A ; Karimian, M ; Kasaei, S ; Sharif University of Technology
SPIE
2015
Abstract
Voluminous amount of videos in today’s world has made the subject of objective (or semi-objective) classification of videos to be very popular. Among the various descriptors used for video classification, SIFT and LIFT can lead to highly accurate classifiers. But, SIFT descriptor does not consider video motion and LIFT is time-consuming. In this paper, a robust descriptor for semi-supervised classification based on video content is proposed. It holds the benefits of LIFT and SIFT descriptors and overcomes their shortcomings to some extent. For extracting this descriptor, the SIFT descriptor is first used and the motion of the extracted keypoints are then employed to improve the accuracy of...
Rigid Registration using Sparse Representation Descriptor in MR Images
, M.Sc. Thesis Sharif University of Technology ; Manzuri-Shalmani, Mohammad Taghi (Supervisor)
Abstract
In recent years, sparse representation has had a variety of applications in computer vision such as noise reduction, image reconstruction, classification and dimension reduction. In this project, we aim to provide a method of matching the keypoints obtained from the Scale Invariant feature Transform (SIFT) algorithm. In this algorithm is used descriptor instead of intensity . The proposed method, first, extracts the salient points from the images and learns a dictionary-based descriptors corresponding to the points. Then, using the dictionary, it obtains the sparse coefficients for each salient point by which, it determines the correspondence of the salient points in the two images using SVD...
A Study on Image Retrieval Methods
, M.Sc. Thesis Sharif University of Technology ; Razvan, Mohammad-Reza (Supervisor) ; Kamali-Tabrizi, Mostafa (Co-Supervisor)
Abstract
Image retrieval refers to the task of finding images related to a query image within an image set. Due to ever-increasing volumes of data, it has become increasingly necessary to find suitable and efficient methods for searching in massive databases. In this thesis, modern image retrieval techniques developed within the last 15 years have been studied, with an aim to satisfy three primary constraints of efficiency, accuracy, and low memory usage. Our focus has been on content-based retrieval; meaning that instead of using text and other information, we directly utilize image features for analysis and processing. To achieve this, we studied two established techniques, the bag-of-words model,...
Inertial Navigation System Error Correction by Combining IMU Unit Information and Consecutive Images in an Unknown Environment
,
M.Sc. Thesis
Sharif University of Technology
;
Nobahari, Hadi
(Supervisor)
;
Ghanbarpour Asl, Habib
(Supervisor)
Abstract
In this research, INS error will be corrected with the help of the unscented kalman filter, by combining the IMU sensors and flight consecutive images information. Measurement equation of the Kalman filter is the epipolar Constraint of geometry of two consecutive images of the camera. In epipolar Constraint, the common points of two consecutive images of the camera field of view have an important role. This points will be extracted by SIFT and SURF algorithms. These algorithms have many mistakes in the process of images matching, but in this research, a solution based on the error covariance of the position of the ground point corresponding to the two common points of two images is presented...