Sal-HMAX: An Enhanced HMAX Model in Conjunction With a Visual Attention Mechanism to Improve Object Recognition Task

The Hierarchical Max-pooling models (HMAX) have demonstrated excellent outperformance when integrated with various computer vision algorithms for the purpose of recognizing objects in images. However, the conventional HMAX model has two main problems: 1) it is computationally expensive to learn base...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Zahra Sadat Shariatmadar, Karim Faez, Akbar Siami Namin
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	HMAX model saliency map object recognition entropy retinal ganglion cell Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/8616253ce68b4f239bdef27d07419def
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:8616253ce68b4f239bdef27d07419def
record_format	dspace
spelling	oai:doaj.org-article:8616253ce68b4f239bdef27d07419def2021-11-25T00:00:39ZSal-HMAX: An Enhanced HMAX Model in Conjunction With a Visual Attention Mechanism to Improve Object Recognition Task2169-353610.1109/ACCESS.2021.3127928https://doaj.org/article/8616253ce68b4f239bdef27d07419def2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9614121/https://doaj.org/toc/2169-3536The Hierarchical Max-pooling models (HMAX) have demonstrated excellent outperformance when integrated with various computer vision algorithms for the purpose of recognizing objects in images. However, the conventional HMAX model has two main problems: 1) it is computationally expensive to learn base matrixes, especially at layer S2 (matching layer), and 2) the patch selection in the standard HMAX model is randomly selected resulting in generating redundant and uninformed extracted patches. In this paper, a combination of the HMAX model and a selective attention mechanism is proposed to address the aforementioned drawbacks of HMAX models. Applying a selective mechanism of attention filters out unnecessary information and highlights more important and significant parts of a given image., An attention function is used to increase the matching velocity at the S2 layer, since through attention we only consider patches with more details. On the other hand, high operational precision is expected due to the extraction of distinct patches in the training phase of the S2 layer. The results of experiments show that the proposed model outperforms the conventional HMAX model. The proposed model establishes a mean accuracy of 93.7% on the first ten best-classified categories using the Caltech-101 dataset.Zahra Sadat ShariatmadarKarim FaezAkbar Siami NaminIEEEarticleHMAX modelsaliency mapobject recognitionentropyretinal ganglion cellElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 154396-154412 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	HMAX model saliency map object recognition entropy retinal ganglion cell Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	HMAX model saliency map object recognition entropy retinal ganglion cell Electrical engineering. Electronics. Nuclear engineering TK1-9971 Zahra Sadat Shariatmadar Karim Faez Akbar Siami Namin Sal-HMAX: An Enhanced HMAX Model in Conjunction With a Visual Attention Mechanism to Improve Object Recognition Task
description	The Hierarchical Max-pooling models (HMAX) have demonstrated excellent outperformance when integrated with various computer vision algorithms for the purpose of recognizing objects in images. However, the conventional HMAX model has two main problems: 1) it is computationally expensive to learn base matrixes, especially at layer S2 (matching layer), and 2) the patch selection in the standard HMAX model is randomly selected resulting in generating redundant and uninformed extracted patches. In this paper, a combination of the HMAX model and a selective attention mechanism is proposed to address the aforementioned drawbacks of HMAX models. Applying a selective mechanism of attention filters out unnecessary information and highlights more important and significant parts of a given image., An attention function is used to increase the matching velocity at the S2 layer, since through attention we only consider patches with more details. On the other hand, high operational precision is expected due to the extraction of distinct patches in the training phase of the S2 layer. The results of experiments show that the proposed model outperforms the conventional HMAX model. The proposed model establishes a mean accuracy of 93.7% on the first ten best-classified categories using the Caltech-101 dataset.
format	article
author	Zahra Sadat Shariatmadar Karim Faez Akbar Siami Namin
author_facet	Zahra Sadat Shariatmadar Karim Faez Akbar Siami Namin
author_sort	Zahra Sadat Shariatmadar
title	Sal-HMAX: An Enhanced HMAX Model in Conjunction With a Visual Attention Mechanism to Improve Object Recognition Task
title_short	Sal-HMAX: An Enhanced HMAX Model in Conjunction With a Visual Attention Mechanism to Improve Object Recognition Task
title_full	Sal-HMAX: An Enhanced HMAX Model in Conjunction With a Visual Attention Mechanism to Improve Object Recognition Task
title_fullStr	Sal-HMAX: An Enhanced HMAX Model in Conjunction With a Visual Attention Mechanism to Improve Object Recognition Task
title_full_unstemmed	Sal-HMAX: An Enhanced HMAX Model in Conjunction With a Visual Attention Mechanism to Improve Object Recognition Task
title_sort	sal-hmax: an enhanced hmax model in conjunction with a visual attention mechanism to improve object recognition task
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/8616253ce68b4f239bdef27d07419def
work_keys_str_mv	AT zahrasadatshariatmadar salhmaxanenhancedhmaxmodelinconjunctionwithavisualattentionmechanismtoimproveobjectrecognitiontask AT karimfaez salhmaxanenhancedhmaxmodelinconjunctionwithavisualattentionmechanismtoimproveobjectrecognitiontask AT akbarsiaminamin salhmaxanenhancedhmaxmodelinconjunctionwithavisualattentionmechanismtoimproveobjectrecognitiontask
_version_	1718414703049310208

Sal-HMAX: An Enhanced HMAX Model in Conjunction With a Visual Attention Mechanism to Improve Object Recognition Task

Ejemplares similares