The feature parallelism model of visual recognition

In this work, the Feature Parallelism Model of visual recognition, which addresses the parallel nature of the human brain compared to the hierarchal (serial) brain model, was studied. First, its accuracy rate and training time were compared to those of DeepFace, a leading industry algorithm for f...

Full description

Bibliographic Details
Main Authors:	Hassan, Marwa Yousif, Shuriye, Abdi Omar, Hassan Abdalla Hashim, Aisha, Salami, Momoh Jimoh Eyiomika, Khalifa, Othman Omran
Format:	Article
Language:	English
Published:	Science & Engineering Research Support Society (SERSC) 2017
Subjects:	T Technology (General)
Online Access:	http://irep.iium.edu.my/56655/ http://irep.iium.edu.my/56655/ http://irep.iium.edu.my/56655/ http://irep.iium.edu.my/56655/1/The%20Feature%20Parallelism%20Model%20of%20Visual%20Recognition.pdf

id	iium-56655
recordtype	eprints
spelling	iium-566552018-01-31T17:08:36Z http://irep.iium.edu.my/56655/ The feature parallelism model of visual recognition Hassan, Marwa Yousif Shuriye, Abdi Omar Hassan Abdalla Hashim, Aisha Salami, Momoh Jimoh Eyiomika Khalifa, Othman Omran T Technology (General) In this work, the Feature Parallelism Model of visual recognition, which addresses the parallel nature of the human brain compared to the hierarchal (serial) brain model, was studied. First, its accuracy rate and training time were compared to those of DeepFace, a leading industry algorithm for face recognition. Both models were trained using ImageNet object recognition dataset. Accuracy rates were almost the same, around 57% top-1 error rate and 33% top-5 error rate. Training time for feature parallelism model has dropped to 21% less than that of Deep Face. Second, we have investigated feature parallelism model under depth, i.e., when adding more layers along the horizontal axis. We have tested the model with 5, 6, 7, and 8 layers respectively; we found that the best results both in terms of accuracy rates and training time were obtained with the sixlayered model. Although the training time enhancement was only a few milliseconds when going from 5 to 6 layers, it has worsened significantly when going from 6 to 7 layers. In fact the training time has tripled, i.e., training time of the 7- layers model is three times of that of the 6- layers model. It continues to worsen by a fewer rate with the 8- layers model. Similarly, accuracy rate was better with the 6- layers model by about 1% of that of the 5- layers model; however, it has worsened by more than 5% whenever we add more layers above six. We consider those results are biologically plausible, as they conform to the biological fact that the cerebral cortex is organized in 6- layers. We’ve concluded that the organization of parallel processing units into 6- layers, either in our brains or in artificial vision systems, may enhance both processing time and accuracy rates. Science & Engineering Research Support Society (SERSC) 2017 Article PeerReviewed application/pdf en http://irep.iium.edu.my/56655/1/The%20Feature%20Parallelism%20Model%20of%20Visual%20Recognition.pdf Hassan, Marwa Yousif and Shuriye, Abdi Omar and Hassan Abdalla Hashim, Aisha and Salami, Momoh Jimoh Eyiomika and Khalifa, Othman Omran (2017) The feature parallelism model of visual recognition. International Journal of Multimedia and Ubiquitous Engineering, 12 (2). pp. 171-186. ISSN 1975-0080 http://www.sersc.org/journals/IJMUE/vol12_no2_2017/13.pdf 10.14257/ijmue.2017.12.2.13
repository_type	Digital Repository
institution_category	Local University
institution	International Islamic University Malaysia
building	IIUM Repository
collection	Online Access
language	English
topic	T Technology (General)
spellingShingle	T Technology (General) Hassan, Marwa Yousif Shuriye, Abdi Omar Hassan Abdalla Hashim, Aisha Salami, Momoh Jimoh Eyiomika Khalifa, Othman Omran The feature parallelism model of visual recognition
description	In this work, the Feature Parallelism Model of visual recognition, which addresses the parallel nature of the human brain compared to the hierarchal (serial) brain model, was studied. First, its accuracy rate and training time were compared to those of DeepFace, a leading industry algorithm for face recognition. Both models were trained using ImageNet object recognition dataset. Accuracy rates were almost the same, around 57% top-1 error rate and 33% top-5 error rate. Training time for feature parallelism model has dropped to 21% less than that of Deep Face. Second, we have investigated feature parallelism model under depth, i.e., when adding more layers along the horizontal axis. We have tested the model with 5, 6, 7, and 8 layers respectively; we found that the best results both in terms of accuracy rates and training time were obtained with the sixlayered model. Although the training time enhancement was only a few milliseconds when going from 5 to 6 layers, it has worsened significantly when going from 6 to 7 layers. In fact the training time has tripled, i.e., training time of the 7- layers model is three times of that of the 6- layers model. It continues to worsen by a fewer rate with the 8- layers model. Similarly, accuracy rate was better with the 6- layers model by about 1% of that of the 5- layers model; however, it has worsened by more than 5% whenever we add more layers above six. We consider those results are biologically plausible, as they conform to the biological fact that the cerebral cortex is organized in 6- layers. We’ve concluded that the organization of parallel processing units into 6- layers, either in our brains or in artificial vision systems, may enhance both processing time and accuracy rates.
format	Article
author	Hassan, Marwa Yousif Shuriye, Abdi Omar Hassan Abdalla Hashim, Aisha Salami, Momoh Jimoh Eyiomika Khalifa, Othman Omran
author_facet	Hassan, Marwa Yousif Shuriye, Abdi Omar Hassan Abdalla Hashim, Aisha Salami, Momoh Jimoh Eyiomika Khalifa, Othman Omran
author_sort	Hassan, Marwa Yousif
title	The feature parallelism model of visual recognition
title_short	The feature parallelism model of visual recognition
title_full	The feature parallelism model of visual recognition
title_fullStr	The feature parallelism model of visual recognition
title_full_unstemmed	The feature parallelism model of visual recognition
title_sort	feature parallelism model of visual recognition
publisher	Science & Engineering Research Support Society (SERSC)
publishDate	2017
url	http://irep.iium.edu.my/56655/ http://irep.iium.edu.my/56655/ http://irep.iium.edu.my/56655/ http://irep.iium.edu.my/56655/1/The%20Feature%20Parallelism%20Model%20of%20Visual%20Recognition.pdf
first_indexed	2023-09-18T21:19:58Z
last_indexed	2023-09-18T21:19:58Z
_version_	1777411815923253248

The feature parallelism model of visual recognition

Similar Items