Combining flash memory and FPGAs to efficiently implement a massively parallel algorithm for content-based image retrieval

With ever larger and more affordable storage capabilities, individuals and companies can now collect huge amounts of multimedia data, especially images. Searching such databases is still an open problem, known as content-based image retrieval (CBIR). In this paper, we present a hardware architecture based on FPGAs which aims at speeding-up visual CBIR. Our architecture is based on the unique combination of reconfigurable resources combined to Flash memory, and allows for a speed-up of 45 as compared to existing software solutions.

[1]  Christoforos E. Kozyrakis,et al.  A case for intelligent RAM , 1997, IEEE Micro.

[2]  Christos Faloutsos,et al.  Searching Multimedia Databases by Content , 1996, Advances in Database Systems.

[3]  Viktor K. Prasanna,et al.  Analysis of high-performance floating-point arithmetic on FPGAs , 2004, 18th International Parallel and Distributed Processing Symposium, 2004. Proceedings..

[4]  Cordelia Schmid,et al.  A Performance Evaluation of Local Descriptors , 2005, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Keith R. Dimond,et al.  A Hardware Implementation of a Content Based Image Retrieval Algorithm , 2004, FPL.

[6]  Patrice Quinton,et al.  Acceleration ofaContent-Based Image-Retrieval Application ontheRDISK Cluster * , 2006 .

[7]  Herwig Lejsek.  A case-study of scoring schemes for the PvS-index , 2005, CVDB '05.

[8]  Dominique Lavenier,et al.  Seed-based genomic sequence comparison using a FPGA/FLASH accelerator , 2006, 2006 IEEE International Conference on Field Programmable Technology.

[9]  Ioannis Andreadis,et al.  Parallel Local Histogram Comparison Hardware Architecture for Content-Based Image Retrieval , 2004, J. Intell. Robotic Syst..

[10]  Luis Pastor,et al.  Performance analysis of a CBIR system on shared-memory systems and heterogeneous clusters , 2005, Seventh International Workshop on Computer Architecture for Machine Perception (CAMP'05).

[11]  Scott McMillan,et al.  A re-evaluation of the practicality of floating-point operations on FPGAs , 1998, Proceedings. IEEE Symposium on FPGAs for Custom Computing Machines (Cat. No.98TB100251).

[12]  Dominique Lavenier,et al.  Cluster of re-configurable nodes for scanning large genomic banks , 2005, Parallel Comput..

[13]  Patrick Gros,et al.  Content-based Retrieval Using Local Descriptors: Problems and Issues from a Database Perspective , 2001, Pattern Analysis & Applications.

[14]  Koji Nakano,et al.  An image retrieval system using FPGAs , 2003, ASP-DAC '03.

[15]  Kenneth E. Batcher,et al.  Sorting networks and their applications , 1968, AFIPS Spring Joint Computing Conference.