Mobile content based image retrieval architectures

Mobile device features such as camera and other sensors are evolving rapidly nowadays. Supported by a reliable communications network, it raises new methods in information retrieval. Mobile devices can capture an image with its camera and pass it to the retrieval systems to get the information needed. This system, called Mobile Content-Based Image Retrieval (MCBIR), generally consists of two parts: Offline Database Construction, which create image features database and indexing structure, and Online Image Search, that search images in the database that similar to the user inputs. MCBIR system, based on its computational load and resource needs, can be categorized into three architectural models: client-side, client-server and distributed. These three models were analyzed in three aspects: scalability, latency, and resources. The results show that each architecture has its own characteristics in terms of these aspects and should be considered in the architecture selection phase for MCBIR development.

[1]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[2]  Olivier Bodenreider,et al.  Using SPARQL to Test for Lattices: Application to Quality Assurance in Biomedical Ontologies , 2010, International Semantic Web Conference.

[3]  Ying Wu,et al.  Mobile Product Image Search by Automatic Query Object Extraction , 2012, ECCV.

[4]  Xian-Sheng Hua,et al.  Mobile Cloud Visual Media Computing , 2015, Springer International Publishing.

[5]  Andrew Zisserman,et al.  Video Google: a text retrieval approach to object matching in videos , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[6]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[7]  Tieniu Tan,et al.  Feature Coding in Image Classification: A Comprehensive Study , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Xing Xie,et al.  Distributed Architecture for Large Scale Image-Based Search , 2007, 2007 IEEE International Conference on Multimedia and Expo.

[9]  Dawei Li,et al.  EMOVIS: An Efficient Mobile Visual Search System for Landmark Recognition , 2013, 2013 IEEE 9th International Conference on Mobile Ad-hoc and Sensor Networks.

[10]  Bernd Girod,et al.  Mobile Visual Search: Architectures, Technologies, and the Emerging MPEG Standard , 2011, IEEE MultiMedia.

[11]  Bernd Girod,et al.  A Hybrid Mobile Visual Search System With Compact Global Signatures , 2015, IEEE Transactions on Multimedia.

[12]  Yimin Wu,et al.  SemView: A Semantic-sensitive Distributed Image Retrieval System , 2003, DG.O.

[13]  John Collins,et al.  A Comparative Study of Similarity Measures for Content-Based Medical Image Retrieval , 2012, CLEF.

[14]  Xian-Sheng Hua,et al.  Mobile Cloud Visual Media Computing: From Interaction to Service , 2015 .

[15]  Gaurav S. Sukhatme,et al.  OCRdroid: A Framework to Digitize Text Using Mobile Phones , 2009, MobiCASE.

[16]  Bernd Girod,et al.  Mobile Visual Search , 2011, IEEE Signal Processing Magazine.

[17]  Touradj Ebrahimi,et al.  On optimal solutions for mobile image retrieval applications , 2010 .

[18]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.