Fast and Scalable 2D Convolutions and Cross-correlations for Processing Image Databases and Videos on CPUs

Cesar Carranza, Daniel Llamocca, Marios Pattichis

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The dominant use of Convolutional Neural Networks (CNNs) in several image and video analysis tasks necessitates a careful re-evaluation of the underlying software libraries for computing them for large-scale image and video databases. We focus our attention on developing methods that can be applied to large image databases or videos of large image sizes.We develop a method that maximizes throughput through the use of vector-based memory I/O and optimized 2D FFT libraries that run on all available physical cores. We also show how to decompose arbitrarily large images into smaller, optimal blocks that can be effectively processed through the use of overlap-and-add. Our approach outperforms Tensorflow for 5 × 5 kernels and significantly outperforms Tensorflow for 11 × 11 kernels.

Original languageEnglish
Title of host publication2020 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2020 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages70-73
Number of pages4
ISBN (Electronic)9781728157450
DOIs
StatePublished - Mar 2020
Event2020 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2020 - Santa Fe, United States
Duration: 29 Mar 202031 Mar 2020

Publication series

NameProceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation
Volume2020-March

Conference

Conference2020 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2020
Country/TerritoryUnited States
CitySanta Fe
Period29/03/2031/03/20

Keywords

  • Convolution
  • CPU
  • Image Processing
  • MIMD
  • Parallel Processing
  • SIMD

Fingerprint

Dive into the research topics of 'Fast and Scalable 2D Convolutions and Cross-correlations for Processing Image Databases and Videos on CPUs'. Together they form a unique fingerprint.

Cite this