Limitations of using bags of complex features: Hierarchical higher-order filters fail to capture spatial configurations
| Main Author: | |
|---|---|
| Language: | English |
| Published: |
The Ohio State University / OhioLINK
2011
|
| Subjects: | |
| Online Access: | http://rave.ohiolink.edu/etdc/view?acc_num=osu1306869257 |
| id |
ndltd-OhioLink-oai-etd.ohiolink.edu-osu1306869257 |
|---|---|
| record_format |
oai_dc |
| spelling |
ndltd-OhioLink-oai-etd.ohiolink.edu-osu13068692572021-08-03T06:02:58Z Limitations of using bags of complex features: Hierarchical higher-order filters fail to capture spatial configurations Van Horn, Nicholas M. Behavioral Psychology Behavioral Sciences Cognitive Psychology object recognition features vision model HMAX One common method of representing images is to reduce an image to a collection of features. Many simple features have been proposed, such as pixel intensities and wavelet responses, but these choices are fundamentally unsuitable for capturing the configural relations of objects and object parts, as spatial information associated with each feature is lost. Another recent strategy, known as "feature-hierarchy" modeling, involves the use of overlapping, redundant features. These features are obtained by processing an image across a hierarchy of units tuned to progressively more complex properties. An open question is whether such approaches produce data structures rich enough for implicitly capturing configural relations. We implemented three experiments and severalcomputer simulations to address this issue. Our method involved the use of four classes of objects, each derived from the simple spatial relationships present in classic Vernier and bisection acuity tasks. All human observers achieved near perfect categorization performance after relatively few exposures to each stimulus class. This ability also transferred across several dimensions, including orientation and background context. By contrast, simulations on a feature-hierarchy model revealed poor performance for this class of models. Furthermore, themoderate categorization accuracy achieved did not transfer across even the simplest of dimensions. These results indicate that this approach to image representation lacks a fundamental property necessary for encoding the spatial configurations of object parts. 2011-07-28 English text The Ohio State University / OhioLINK http://rave.ohiolink.edu/etdc/view?acc_num=osu1306869257 http://rave.ohiolink.edu/etdc/view?acc_num=osu1306869257 unrestricted This thesis or dissertation is protected by copyright: all rights reserved. It may not be copied or redistributed beyond the terms of applicable copyright laws. |
| collection |
NDLTD |
| language |
English |
| sources |
NDLTD |
| topic |
Behavioral Psychology Behavioral Sciences Cognitive Psychology object recognition features vision model HMAX |
| spellingShingle |
Behavioral Psychology Behavioral Sciences Cognitive Psychology object recognition features vision model HMAX Van Horn, Nicholas M. Limitations of using bags of complex features: Hierarchical higher-order filters fail to capture spatial configurations |
| author |
Van Horn, Nicholas M. |
| author_facet |
Van Horn, Nicholas M. |
| author_sort |
Van Horn, Nicholas M. |
| title |
Limitations of using bags of complex features: Hierarchical higher-order filters fail to capture spatial configurations |
| title_short |
Limitations of using bags of complex features: Hierarchical higher-order filters fail to capture spatial configurations |
| title_full |
Limitations of using bags of complex features: Hierarchical higher-order filters fail to capture spatial configurations |
| title_fullStr |
Limitations of using bags of complex features: Hierarchical higher-order filters fail to capture spatial configurations |
| title_full_unstemmed |
Limitations of using bags of complex features: Hierarchical higher-order filters fail to capture spatial configurations |
| title_sort |
limitations of using bags of complex features: hierarchical higher-order filters fail to capture spatial configurations |
| publisher |
The Ohio State University / OhioLINK |
| publishDate |
2011 |
| url |
http://rave.ohiolink.edu/etdc/view?acc_num=osu1306869257 |
| work_keys_str_mv |
AT vanhornnicholasm limitationsofusingbagsofcomplexfeatureshierarchicalhigherorderfiltersfailtocapturespatialconfigurations |
| _version_ |
1719430039399825408 |