Duplicate Image Retrieval with Cascade Similarity Measurements

Yudong Ca
June 2012
International Journal of Advancements in Computing Technology;Jun2012, Vol. 4 Issue 10, p228
Academic Journal
In this paper, a cascade detection method using two different similarity measurements is presented. Given a query, the first level detection filters out the most of non-duplicate images and remains most of duplicate images. Then, the second level detection with epipolar geometry is applied only on the remained images so it can remove large number offalse positives and false negatives further. In the second level detection, the spatial location relationship is considered in the similarity measure. In this experiment we represent images with a combination of local features, i.e., SIFT (Scale-invariant feature transform) and MSER (Maximally Stable Extremal Region) which increases discrimination and saves storage space than using SIFT alone. Finally the experiments show the promising results of the proposed method on the benchmarked Flickr dataset and INRIA dataset.


Related Articles

  • Fixed Representative Colors Feature Extraction Algorithm for Moving Picture Experts Group-7 Dominant Color Descriptor. Ibrahim, Ahmed; Ala'a Al-Zou'bi; Sahawneh, Raed; Makhadmeh, Maria // Journal of Computer Science;2009, Vol. 5 Issue 11, p773 

    Problem statement: MPEG-7 has defined a set of color descriptors for the multimedia contents; one of these descriptors is the Dominant Color Descriptor (DCD). The DCD adopted the Generalized Lloyd Algorithm (GLA) as a feature extraction technique. However, using this algorithm in image retrieval...

  • A fully automatic registration approach based on contour and SIFT for HJ-1 images. Ni, XiLiang; Cao, ChunXiang; Ding, Lin; Jiang, Tao; Zhang, Hao; Jia, HuiCong; Li, GuangHe; Zhao, Jian; Chen, Wei; Ji, Wei; Xu, Min; Gao, MengXu; Zheng, Sheng; Tian, Rong; Liu, Cheng; Li, Sha // SCIENCE CHINA Earth Sciences;Oct2012, Vol. 55 Issue 10, p1679 

    To achieve a fully automatic registration between HJ-1 CCD images and HJ-1 infrared images is a difficult task as it must deal with the varying illuminations and resolutions of the images, different perspectives, and the local deformations within the images. In this paper, aimed at those...

  • View Synthesizing for a Large-Scale Object in a Scene. Thein, Thin Lai Lai; Sein, Myint Myint // Telkomnika;2012, Vol. 10 Issue 4, p795 

    A robust method for panorama view reconstruction of a scene is presented. The images of a scene are acquired by moving a camera to multiple viewpoints. We present a robust method of panorama synthesizing based on image mosaicing approach. The edge detection and feature points extraction are...

  • Research on speeded-up robust features with RANSAC. KONG Jun; JIANG Min; Alimujiang Yiming // International Journal of Advancements in Computing Technology;Apr2013, Vol. 5 Issue 8, p777 

    SURF (Speeded-Up Robust Features) algorithm well solves the problems of calculation time and operation speed in image registration. But it has such shortcomings as accuracy and reliability. Especially, with the increase of matching threshold, the error-matched will turn more serious. In order to...

  • Assigning Main Orientation to an EOH Descriptor on Multispectral Images. Yong Li; Xiang Shi; LijunWei; Junwei Zou; Fang Chen // Sensors (14248220);Jul2015, Vol. 15 Issue 7, p15595 

    This paper proposes an approach to compute an EOH (edge-oriented histogram) descriptor with main orientation. EOH has a better matching ability than SIFT (scale-invariant feature transform) on multispectral images, but does not assign a main orientation to keypoints. Alternatively, it tends to...

  • IMAGE RETRIEVAL USING COLOR-SIZE MOMENTS AND WAVELET FEATURES. PUVIARASAN, N.; BHAVANI, R.; ARTHI, T. S. // Journal of Theoretical & Applied Information Technology;Jun2014, Vol. 64 Issue 2, p495 

    The rapid growth of digital imaging techniques and versatility among the images has motivated the development of Content Based Image Retrieval (CBIR). CBIR is the application of computer vision techniques which uses the visual contents to retrieve relevant images from large databases according...

  • Content Based Image Retrieval Genetic Algorithm for Relevance Feedback. Hatwar, Nikita R.; Hatwar, Rajendra F. // International Journal of Advanced Computer Research;Dec2012, Vol. 2 Issue 6, p381 

    Image retrieval using content has become a hot topic in the field of Digital Image Processing and Computer Vision. In this proposed work, we focus on the problem of image retrieval using genetic algorithm for relevance feedback. Texture and Color are the important features in CBIR. Texture and...

  • Improved Image Retrieval Performance Based on Fuzzy C-means Clustering Algorithm.  // International Journal of Advancements in Computing Technology;May2012, Vol. 4 Issue 8, p52 

    Most traditional and common methods of image retrieval utilize method of adding metadata, for example, captioning, keywords, or descriptions to the images, this method makes retrieval can be performed over the annotation, this paper proposes improved image retrieval performance based on fuzzy...

  • An Adequate Approach to Image Retrieval Based on Local Level Feature Extraction. KHAN, SUMAIRA MUHAMMAD HAYAT; HUSSAIN, AYYAZ; AL SHAIKHLI, IMAD FAKHRI TAHA // Mehran University Research Journal of Engineering & Technology;Oct2015, Vol. 34 Issue 4, p337 

    Image retrieval based on text annotation has become obsolete and is no longer interesting for scientists because of its high time complexity and low precision in results. Alternatively, increase in the amount of digital images has generated an excessive need for an accurate and efficient...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics