Beta
ManageSearchChatDiscover
311995

Representation Learning Framework of Object Recognition via Feature Construction

Article

Last updated: 28 Dec 2024

OverviewSimilar Items

Subjects

-

Tags

-

Abstract

 In this paper, we recognize objects within images by collecting information from a large number of random-size
patches of the image. The different backgrounds accompany the foreground object demand to have a learning system to
identify each patch as belonging to the object category or to the background category. We strengthen a recent method
called Evolution-COnstructed (ECO), which is based on the ensemble learning approach which combines several weak
classifier. The improvement is relying on decreasing the overfitting problem. Two different improving ideas are
proposed: 1) Pooling operation, which is applied to the weak classifiers data, 2) Random Forest algorithm, which combines the weak classifiers outcomes. Experimental results are reported for classification of 9 categories of Caltech-101 data sets and proved that our modifications boost the performance over the base method and other existing methods 

DOI

10.21608/mjcis.2018.311995

Keywords

Object Recognition, ECO features, adaboost, Random Forest, pooling, Genetic Algorithm

Authors

First Name

Muhammad

Last Name

H. Zayyan

MiddleName

-

Affiliation

Faculty of computers and information systems , C.S dep. Mansoura University, Egypt

Email

-

City

-

Orcid

-

First Name

Samir

Last Name

Elmougy

MiddleName

-

Affiliation

Faculty of computers and information systems , C.S dep. Mansoura University, Egypt

Email

mougy@mans.edu.eg

City

-

Orcid

-

First Name

Mohammed

Last Name

F. Alrahmawy

MiddleName

-

Affiliation

Faculty of computers and information systems , C.S dep. Mansoura University, Egypt

Email

-

City

-

Orcid

-

Volume

14

Article Issue

1

Related Issue

42819

Issue Date

2018-06-01

Receive Date

2023-08-10

Publish Date

2018-06-01

Page Start

37

Page End

42

Print ISSN

2090-1666

Online ISSN

2090-1674

Article File

MJCIS_Volume 14_Issue 1_Pages 37-42.pdf

PDF . 682.1kB

Link

https://mjcis.journals.ekb.eg/article_311995.html

Detail API

https://mjcis.journals.ekb.eg/service?article_code=311995

Order

311,995

Type

Original Research Articles.

Type Code

1,784

Publication Type

Journal

Publication Title

Mansoura Journal for Computer and Information Sciences

Publication Link

https://mjcis.journals.ekb.eg/

MainTitle

Representation Learning Framework of Object Recognition via Feature Construction

Details

Type

Article

Created At

28 Dec 2024