Bioinspired memory model for HTM face recognition

Olga Krestinskaya; Alex Pappachen James

doi:10.1109/ICACCI.2016.7732265

Bioinspired memory model for HTM face recognition

Olga Krestinskaya, Alex Pappachen James

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Scopus citations

Abstract

Inspired from the working principle of human memory, we propose a new algorithm for storing HTM features detected from images. The resulting features from the training set require lower memory than existing HTM training set. The proposed features are tested in a face recognition problem using the benchmark AR dataset. The simulation results show that the proposed algorithm gives higher face recognition accuracy, in comparison to the conventional methods.

Original language	English (US)
Title of host publication	2016 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1528-1532
Number of pages	5
ISBN (Print)	9781509020287
DOIs	https://doi.org/10.1109/ICACCI.2016.7732265
State	Published - Nov 2 2016
Externally published	Yes

Access to Document

10.1109/ICACCI.2016.7732265

Cite this

@inproceedings{8122726d59d44809a005997bb3172882,

title = "Bioinspired memory model for HTM face recognition",

abstract = "Inspired from the working principle of human memory, we propose a new algorithm for storing HTM features detected from images. The resulting features from the training set require lower memory than existing HTM training set. The proposed features are tested in a face recognition problem using the benchmark AR dataset. The simulation results show that the proposed algorithm gives higher face recognition accuracy, in comparison to the conventional methods.",

author = "Olga Krestinskaya and James, {Alex Pappachen}",

note = "Generated from Scopus record by KAUST IRTS on 2023-09-23",

year = "2016",

month = nov,

day = "2",

doi = "10.1109/ICACCI.2016.7732265",

language = "English (US)",

isbn = "9781509020287",

pages = "1528--1532",

booktitle = "2016 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

}

TY - GEN

T1 - Bioinspired memory model for HTM face recognition

AU - Krestinskaya, Olga

AU - James, Alex Pappachen

N1 - Generated from Scopus record by KAUST IRTS on 2023-09-23

PY - 2016/11/2

Y1 - 2016/11/2

N2 - Inspired from the working principle of human memory, we propose a new algorithm for storing HTM features detected from images. The resulting features from the training set require lower memory than existing HTM training set. The proposed features are tested in a face recognition problem using the benchmark AR dataset. The simulation results show that the proposed algorithm gives higher face recognition accuracy, in comparison to the conventional methods.

AB - Inspired from the working principle of human memory, we propose a new algorithm for storing HTM features detected from images. The resulting features from the training set require lower memory than existing HTM training set. The proposed features are tested in a face recognition problem using the benchmark AR dataset. The simulation results show that the proposed algorithm gives higher face recognition accuracy, in comparison to the conventional methods.

UR - http://ieeexplore.ieee.org/document/7732265/

UR - http://www.scopus.com/inward/record.url?scp=85007378855&partnerID=8YFLogxK

U2 - 10.1109/ICACCI.2016.7732265

DO - 10.1109/ICACCI.2016.7732265

M3 - Conference contribution

SN - 9781509020287

SP - 1528

EP - 1532

BT - 2016 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Bioinspired memory model for HTM face recognition

Abstract

Access to Document

Other files and links

Fingerprint

Cite this