2026-09-18T23:37:42Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/770132022-01-13T07:54:29Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Tomaso Poggio and Victor Chan.
Hasan, Maysun Mazhar
Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2013-02-14T15:38:19Z
2013-02-14T15:38:19Z
2012
2012
http://hdl.handle.net/1721.1/77013
825764142
Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2012.
Cataloged from PDF version of thesis.
Includes bibliographical references (p. 48-49).
HMAX ("Hierarchical Model and X") system is among the best machine vision approaches developed today, in many object recognition tasks [1]. HMAX decomposes an image into features which are passed to a classifier. These features each capture information about a small section of the input image but might not have information about the overall structure of the image if there is not a significant number of overlapping features. Therefore it can produce a false-positive if two images from two different classes having sufficiently similar features profile but completely different structures. To demonstrate the problem this thesis aimed to show that the features of a given subject are not unique because they lack geometric information. Genetic algorithm (GA) was used to create an image with a similar feature profile as a subject but which clearly does not belong to the subject. Using GA, random pixel images converged to an image whose feature profile has a small Euclidian distance from a target profile. This generated GA image does not resemble the target image but has a similar profile which successfully fooled the classifier in most cases. This implies that the "binding problem" is a major issue in a HMAX model of the size tested. Furthermore, methods of improving the system were investigated.
by Maysun Mazhar Hasan.
M.Eng.
49 p.
eng
Massachusetts Institute of Technology
M.I.T. theses are protected by
copyright. They may be viewed from this source for any purpose, but
reproduction or distribution in any format is prohibited without written
permission. See provided URL for inquiries about permission.
http://dspace.mit.edu/handle/1721.1/7582
Electrical Engineering and Computer Science.
Using genetic algorithm to "fool" HMAX object recognition model
Using genetic algorithm to "fool" Hierarchical Model and X object recognition model
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="a216db59-f89d-4435-86c1-be07e01f22e5">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>Using genetic algorithm to "fool" HMAX object recognition model</Title>
<Subtitle>Using genetic algorithm to "fool" Hierarchical Model and X object recognition model</Subtitle>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2012</PublicationDate>
<Authors>
<Author>
<DisplayName>Hasan, Maysun Mazhar</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Electrical Engineering and Computer Science.</Keyword>
<Abstract>HMAX ("Hierarchical Model and X") system is among the best machine vision approaches developed today, in many object recognition tasks [1]. HMAX decomposes an image into features which are passed to a classifier. These features each capture information about a small section of the input image but might not have information about the overall structure of the image if there is not a significant number of overlapping features. Therefore it can produce a false-positive if two images from two different classes having sufficiently similar features profile but completely different structures. To demonstrate the problem this thesis aimed to show that the features of a given subject are not unique because they lack geometric information. Genetic algorithm (GA) was used to create an image with a similar feature profile as a subject but which clearly does not belong to the subject. Using GA, random pixel images converged to an image whose feature profile has a small Euclidian distance from a target profile. This generated GA image does not resemble the target image but has a similar profile which successfully fooled the classifier in most cases. This implies that the "binding problem" is a major issue in a HMAX model of the size tested. Furthermore, methods of improving the system were investigated.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>