Cover Image

AMOR: an adaptive, multimodal architecture for visual object recognition

The general objective of this research was to develop a novel architecture for the difficult, but crucial, problem of recognising objects in visual scenes. An Adaptive, Multimodal architecture for Object Recognition (AMOR) was developed that extends existing unimodal (visual-only) systems in order t...

Full description

Saved in:
Bibliographic Details
Main Author: James Mountstephens
Format: Research Report
Language:English
Published: Universiti Malaysia Sabah 2014
Subjects:
NA Architecture
Online Access:https://eprints.ums.edu.my/id/eprint/24829/1/AMOR%20an%20adaptive%2C%20multimodal%20architecture%20for%20visual%20object%20recognition.pdf
https://eprints.ums.edu.my/id/eprint/24829/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.ums.eprints.24829
record_format eprints
spelling my.ums.eprints.248292020-02-03T02:29:10Z https://eprints.ums.edu.my/id/eprint/24829/ AMOR: an adaptive, multimodal architecture for visual object recognition James Mountstephens NA Architecture The general objective of this research was to develop a novel architecture for the difficult, but crucial, problem of recognising objects in visual scenes. An Adaptive, Multimodal architecture for Object Recognition (AMOR) was developed that extends existing unimodal (visual-only) systems in order to increase their accuracy. The specific objectives of this research were to design, implement and evaluate the proposed architecture. The architecture design was formalised mathematically and algorithmically in the form of "reclassification", implemented in custom Matlab code and evaluated by comparison to existing visual-only methods for object recognition. A scene dataset consisting of 8,750 visual scenes containing 575 object classes was developed and used for testing. Experiments demonstrated that when using a combination of SIFT visual features and an SVM classifier, AMOR could achieve an average of 30.5% accuracy in object recognition, which was a 5.5% improvem.ent over a standard visual-only approach. Also developed was a novel measure of 'compatibility' between visual confusion and object co-occurrence that attempts to quantify the extent to which context can compensate for visual confusion. A reasonable level of correlation was found between compatibility and adaptive multimodal improvement in performance. Objektif umum kajian ini adalah untuk membangunkan seni bina baru untuk masalah yang sukar, tetapi penting, mengiktiraf objek dalam adegan visual. Seni bina Adaptive, Multimodal untuk Objek Pengiktirafan (AMOR) telah dibangunkan yang merangkumi unimodal (visual sahaja) sistem yang sedia ada untuk meningkatkan ketepatan mereka. Objektif khusus kajian ini adalah untuk mereka bentuk, melaksana dan menilai seni bina yang dicadangkan. Reka bentuk seni bina telah dirasmikan secara matematik dan algorithmically dalam bentuk "Pengkelasan' Universiti Malaysia Sabah 2014 Research Report NonPeerReviewed text en https://eprints.ums.edu.my/id/eprint/24829/1/AMOR%20an%20adaptive%2C%20multimodal%20architecture%20for%20visual%20object%20recognition.pdf James Mountstephens (2014) AMOR: an adaptive, multimodal architecture for visual object recognition.
institution Universiti Malaysia Sabah
building UMS Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaysia Sabah
content_source UMS Institutional Repository
url_provider http://eprints.ums.edu.my/
language English
topic NA Architecture
spellingShingle NA Architecture
James Mountstephens
AMOR: an adaptive, multimodal architecture for visual object recognition
description The general objective of this research was to develop a novel architecture for the difficult, but crucial, problem of recognising objects in visual scenes. An Adaptive, Multimodal architecture for Object Recognition (AMOR) was developed that extends existing unimodal (visual-only) systems in order to increase their accuracy. The specific objectives of this research were to design, implement and evaluate the proposed architecture. The architecture design was formalised mathematically and algorithmically in the form of "reclassification", implemented in custom Matlab code and evaluated by comparison to existing visual-only methods for object recognition. A scene dataset consisting of 8,750 visual scenes containing 575 object classes was developed and used for testing. Experiments demonstrated that when using a combination of SIFT visual features and an SVM classifier, AMOR could achieve an average of 30.5% accuracy in object recognition, which was a 5.5% improvem.ent over a standard visual-only approach. Also developed was a novel measure of 'compatibility' between visual confusion and object co-occurrence that attempts to quantify the extent to which context can compensate for visual confusion. A reasonable level of correlation was found between compatibility and adaptive multimodal improvement in performance. Objektif umum kajian ini adalah untuk membangunkan seni bina baru untuk masalah yang sukar, tetapi penting, mengiktiraf objek dalam adegan visual. Seni bina Adaptive, Multimodal untuk Objek Pengiktirafan (AMOR) telah dibangunkan yang merangkumi unimodal (visual sahaja) sistem yang sedia ada untuk meningkatkan ketepatan mereka. Objektif khusus kajian ini adalah untuk mereka bentuk, melaksana dan menilai seni bina yang dicadangkan. Reka bentuk seni bina telah dirasmikan secara matematik dan algorithmically dalam bentuk "Pengkelasan'
format Research Report
author James Mountstephens
author_facet James Mountstephens
author_sort James Mountstephens
title AMOR: an adaptive, multimodal architecture for visual object recognition
title_short AMOR: an adaptive, multimodal architecture for visual object recognition
title_full AMOR: an adaptive, multimodal architecture for visual object recognition
title_fullStr AMOR: an adaptive, multimodal architecture for visual object recognition
title_full_unstemmed AMOR: an adaptive, multimodal architecture for visual object recognition
title_sort amor: an adaptive, multimodal architecture for visual object recognition
publisher Universiti Malaysia Sabah
publishDate 2014
url https://eprints.ums.edu.my/id/eprint/24829/1/AMOR%20an%20adaptive%2C%20multimodal%20architecture%20for%20visual%20object%20recognition.pdf
https://eprints.ums.edu.my/id/eprint/24829/
_version_ 1760230287988490240
score 13.211869

Similar Items