Abstract
Plagiarism, as a crucial offense especially in academia, not only is well-known problem in text but also is becoming widespread in image. In this work, the performance of manifold-ranking, known as robust method among semi-supervised methods, has been investigated by using twelve different features. As its high performance is attributed to the quality of constructed graph, we applied robust k-regular nearest neighbor (k-RNN) graph in the framework of manifold-ranking based retrieval. Among all tested feature point detectors and descriptors, Root-SIFT, the feature point ones, due to it is invariant to an array of image transforms, is the most reliable feature for calculating image similarity. The database consisting of images from scientific papers containing four popular benchmark test images served to test these methods.
Highlights
With the spread of digital data, plagiarism is very important subject that has received much attention over the past decade
Extrinsic text plagiarism detection based on current state of art techniques, MultiLayer Self-Organizing Map (MLSOM) with tree-structured data, the Levenshtein distance and Smith-Waterman algorithm, a Nearest Neighbor (NN) search for measuring semantic similarity and text syntactical structures were used for text plagiarism detection in [1,2,3,4] and [5] respectively which are good examples in this area
This paper aims at evaluating the performance of manifold-ranking based in image retrieval systems by using k-regular nearest neighbor (k-RNN) graph to find identical images scaled and rotated
Summary
With the spread of digital data, plagiarism is very important subject that has received much attention over the past decade. Except a few research works [11, 12], conducted on image plagiarism in documents, there is an insufficient number of studies comparing the effect of different image features on the effectiveness of this algorithm. This paper aims at evaluating the performance of manifold-ranking based in image retrieval systems by using k-RNN graph to find identical images scaled and rotated. It investigates the effect of robust scale and rotation invariant features that are used to calculate the similarity between the images in the k-RNN graph. The feature detectors and descriptors are selected based on their application in finding similar images in a corpus of scientific documents using manifold-ranking and k-
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: International Journal of Engineering & Technology
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.