Sketch Based Image Retrieval with Cosine Similarity
Main Article Content
Abstract
In the present paper cosine similarity is used for similarity measurement in sketch to image retrieval with focus on image matching. Similarity measurement is very challenging task in sketches due to its variable dimensions in the edges. Median filters are used to minimize the noises occur in the images due to unknown reasons. After pre-processing of the images in the benchmark database, the features are extracted using Histogram of oriented gradients (HOG). Canny edge detection algorithm is discussed to detect the image edges in several directions. Later the sketch to image matching is calculated by similarity measurement algorithm cosine similarity. A Benchmark sketch image database is considered to prove the proposed algorithms is efficient and works effectively when compared with many existing techniques. It is very important to measure accurate similarity measurement in high dimensional space for information retrieving. This paper presents efficient cosine similarity measurement algorithm. In the present exertion extensive experimental work is carried out inorder to prove the state of art in association with Sketch Based Image Retrieval (SBIR). Keywords: Image retrieval, Cosine similarity, HOG, Canny edge detection, Median filter
Downloads
Download data is not yet available.
Article Details
Section
Articles
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.