Document Detail


Extended coding and pooling in the HMAX model.
MedLine Citation:
PMID:  23060335     Owner:  NLM     Status:  Publisher    
Abstract/OtherAbstract:
This paper presents an extension of the HMAX model: a neural network model for image classification. The HMAX model can be described as a four-level architecture with a first level consisting of multi-scale and multi-orientation local filters. We introduce two main contributions to this model. First, we improve the way the local filters at the first level are integrated into more complex filters at the last level, providing a flexible description of object regions, combining local information of multiple scales and orientations. These new filters are discriminative and yet invariant, two key aspects of visual classification. We evaluate their discriminative power and their level of invariance to geometrical transformations on a synthetic image set. Second, we introduce a multi-resolution spatial pooling. This pooling encodes both local and global spatial information to produce discriminative image signatures. Classification results are reported on three image data sets, Caltech101, Caltech256 and Fifteen Scenes. We show significant improvements over previous architectures using a similar framework.
Authors:
C Theriault; N Thome; M Cord
Related Documents :
23202845 - Multidimensional excitation pulses based on spatiotemporal encoding concepts.
23710465 - Exploiting gpus in virtual machine for biocloud.
24974045 - Open-source solutions for spimage processing.
24846605 - Power-constrained contrast enhancement algorithm using multi-scale retinex for oled dis...
20517605 - Real-time breath-hold triggering of myocardial perfusion imaging with a novel cadmium-z...
23202845 - Multidimensional excitation pulses based on spatiotemporal encoding concepts.
Publication Detail:
Type:  JOURNAL ARTICLE     Date:  2012-10-05
Journal Detail:
Title:  IEEE transactions on image processing : a publication of the IEEE Signal Processing Society     Volume:  -     ISSN:  1941-0042     ISO Abbreviation:  IEEE Trans Image Process     Publication Date:  2012 Oct 
Date Detail:
Created Date:  2012-10-12     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9886191     Medline TA:  IEEE Trans Image Process     Country:  -    
Other Details:
Languages:  ENG     Pagination:  -     Citation Subset:  -    
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Rank Minimization Code Aperture Design for Spectrally Selective Compressive Imaging.
Next Document:  Human Detection in Images via Piecewise Linear Support Vector Machines.