TITLE

An Efficient Interactive Mobile Visual Search Using Multipart Region based Matching (MRM) Algorithm

AUTHOR(S)
Sivakumar, P.; Perumal Sankar, S.; Praksh, M.; Malathi, S.; Duraisamy, A.; Muthukumar, S.
PUB. DATE
July 2014
SOURCE
Australian Journal of Basic & Applied Sciences;Jul2014, Vol. 8 Issue 10, p7
SOURCE TYPE
Academic Journal
DOC. TYPE
Article
ABSTRACT
Background: Searching is becoming pervasive and one of the most popular applications on mobile devices. Text, voice, sketches are used as query to search images on mobile devices. A multimodal interactive image search on mobile device is proposed to visual search which focuses on image composition instead of typical image retrieval. Search performance is the main constraint for any kind of search techniques. Objective: This system introduces "Joint search with Image, Speech, And World Plus" (JIGSAW+) for multimodal input and user interactions with mobile devices. Users may have pictures or images in their mind but have no idea to describe or names to address them. It can be resolved by speech. Results: The speech of the user is recognized as query by interactively composing a visual query using exemplary images. By using this user can easily find the desired images through a few interactions with mobile devices. The JIGSAW+ system is implemented in three modules. First the images are represented based on features of the images known as segment based image representation. Secondly relative position checking is used for finding images. Finally, inverted index are constructed for matching this system shows the user desired image is found easily and the search performance is improved significantly Conclusion: We have proposed an interactive mobile visual search system which allows the users to formulate their search through multimodal interactions with mobile devices. Mobile visual search takes the advantages of multimodal and multi touch functionalities on the phone. The proposed system provides a game-like interactive image search scheme with composition of multiple exemplars. The visual query generated by the user can be effectively used to retrieve similar images by the proposed method. Compared to textbased retrieval system the performance of the proposed system is boosted. The user's search experience on mobile device is thus significantly improved by this game-like image search system.
ACCESSION #
97368455

 

Related Articles

  • Compressed Sensing Image Processing Based on Stagewise Orthogonal Matching Pursuit. Kuangfeng Ning // Sensors & Transducers (1726-5479);Oct2014, Vol. 181 Issue 10, p134 

    This paper studies the compressed sensing image processing based on Stage-wise Orthogonal Matching Pursuit, the relative error, matching degree, and the running time of StOMP algorithm have been researched from the perspective of two-dimensional compressible signals. A simulation platform is...

  • A Defogging Algorithm Based on Statistical Region Merging. Zhiyuan Xu; Yongkai Wang; Xiaohong Su; Yi Liu // Applied Mechanics & Materials;2014, Issue 644-650, p2189 

    Different regions in Foggy images have different contrast attenuations. This paper presented a defogging algorithm based on Statistical Region Merging. Firstly, we segmented the image by Mean Shift; Secondly, we merged these divided regions through Statistical Region Merging; Finally, we...

  • Novel Methods for Non Uniform Patch Based Texture Synthesis Using Random Selection of Patches. S., Vinod Kumar R.; Arivazhagan, S. // International Review on Computers & Software;Jun2013, Vol. 8 Issue 6, p1390 

    Two simple image based methods of generating novel visual appearance in the synthesized texture are presented in the present paper. The synthesized output texture contains square patches of non uniform sizes. Two categories of non uniform patch based texture synthesis namely; row-wise patch...

  • IMAGE SEGMENTATION AVAILABLE TECHNIQUES, OPEN ISSUES AND REGION GROWING ALGORITHM. GHULE, A. G.; DESHMUKH, P. R. // Journal of Signal & Image Processing;2012, Vol. 3 Issue 1, p71 

    In areas such as computer vision and mage processing, image segmentation has been and still is a relevant research area due to its wide spread usage and application. This paper provides a survey of achievements, problems being encountered, and the open issues in the research area of image...

  • Methods to Define a Single Point in the Polygon. Sharma, Arun Kumar; Kaur Gill, Sandeep // International Journal of Computer Science & Information Technolo;2014, Vol. 5 Issue 3, p3429 

    In this paper we present the simple methods to define a single point problem. As we know polygon may be represented as a number of line segments connected end to end to form a polygon. Alternatively, it may be represented as the points where the sides of the polygon are connected. The line...

  • Mining Subspace Clusters in High Dimensional Data. Singh, Vijendra; Sahoo, Laxman; Kelkar, Ashwini // International Journal on Recent Trends in Engineering & Technolo;May2010, Vol. 3 Issue 1, p118 

    Clustering in high-dimensional spaces is a difficult problem, which is recurrent in many domains, for example in image analysis. The difficulty is due to the fact that high-dimensional data usually exist in different lowdimensional subspaces hidden in the original space. Conventional clustering...

  • Scale Invariant Feature Transform on the Sphere: Theory and Applications. Cruz-Mota, Javier; Bogdanova, Iva; Paquier, BenoĆ®t; Bierlaire, Michel; Thiran, Jean-Philippe // International Journal of Computer Vision;Jun2012, Vol. 98 Issue 2, p217 

    A SIFT algorithm in spherical coordinates for omnidirectional images is proposed. This algorithm can generate two types of local descriptors, Local Spherical Descriptors and Local Planar Descriptors. With the first ones, point matching between two omnidirectional images can be performed, and...

  • Fabric Defect Detection using Undecimated Wavelet Transform. Bi Mingde; Sun Zhigang // Information Technology Journal;Sep2011, Vol. 10 Issue 9, p1701 

    In this study, a new fabric defect detection algorithm base on undecimated wavelet transform is proposed. The selection scheme of wavelet decomposition scales is investigated to set the decomposition scales adaptively to the fabric texture. The objective of the scheme is to enhance the energy of...

  • A Multi-focus Image Fusion Method Based on Laplacian Pyramid. Wang, Wencheng; Chang, Faliang // Journal of Computers;Dec2011, Vol. 6 Issue 12, p2559 

    This paper presented a simple and efficient algorithm for multi-focus image fusion, which used a multi- resolution signal decomposition scheme called Laplacian pyramid method. The principle of Laplacian pyramid transform is introduced, and based on it the fusion strategy is described in detail....

Share

Read the Article

Courtesy of THE LIBRARY OF VIRGINIA

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

Try another library?
Sign out of this library

Other Topics