Invariant Object Recognition Based on Extended Fragments
Visual appearance of natural objects is profoundly affected by viewing conditions such as viewpoint and illumination. Human subjects can nevertheless compensate well for variations in these viewing conditions. The strategies that the visual system uses to accomplish this are largely unclear. Previou...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2012-08-01
|
| Series: | Frontiers in Computational Neuroscience |
| Subjects: | |
| Online Access: | http://journal.frontiersin.org/Journal/10.3389/fncom.2012.00056/full |
| _version_ | 1828422862885617664 |
|---|---|
| author | Evgeniy eBart Jay eHegdé |
| author_facet | Evgeniy eBart Jay eHegdé |
| author_sort | Evgeniy eBart |
| collection | DOAJ |
| description | Visual appearance of natural objects is profoundly affected by viewing conditions such as viewpoint and illumination. Human subjects can nevertheless compensate well for variations in these viewing conditions. The strategies that the visual system uses to accomplish this are largely unclear. Previous computational studies have suggested that in principle, certain types of object fragments (rather than whole objects) can be used for invariant recognition. However, whether the human visual system is actually capable of using this strategy remains unknown. Here, we show that human observers can achieve illumination invariance by using object fragments that carry the relevant information. To determine this, we have used novel, but naturalistic, 3-D visual objects called ‘digital embryos’. Using novel instances of whole embryos, not fragments, we trained subjects to recognize individual embryos across illuminations. We then tested the illumination-invariant object recognition performance of subjects using fragments. We found that the performance was strongly correlated with the mutual information (MI) of the fragments, provided that MI value took variations in illumination into consideration. This correlation was not attributable to any systematic differences in task difficulty between different fragments. These results reveal two important principles of invariant object recognition. First, the subjects can achieve invariance at least in part by compensating for the changes in the appearance of small local features, rather than of whole objects. Second, the subjects do not always rely on generic or pre-existing invariance of features (i.e., features whose appearance remains largely unchanged by variations in illumination), and are capable of using learning to compensate for appearance changes when necessary. These psychophysical results closely fit the predictions of earlier computational studies of fragment-based invariant object recognition. |
| first_indexed | 2024-12-10T15:52:53Z |
| format | Article |
| id | doaj.art-e2593c60b3a74ad89b3963a1900f7ee5 |
| institution | Directory Open Access Journal |
| issn | 1662-5188 |
| language | English |
| last_indexed | 2024-12-10T15:52:53Z |
| publishDate | 2012-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Computational Neuroscience |
| spelling | doaj.art-e2593c60b3a74ad89b3963a1900f7ee52022-12-22T01:42:44ZengFrontiers Media S.A.Frontiers in Computational Neuroscience1662-51882012-08-01610.3389/fncom.2012.0005622464Invariant Object Recognition Based on Extended FragmentsEvgeniy eBart0Jay eHegdé1Palo Alto Research CenterGeorgia Health Sciences UniversityVisual appearance of natural objects is profoundly affected by viewing conditions such as viewpoint and illumination. Human subjects can nevertheless compensate well for variations in these viewing conditions. The strategies that the visual system uses to accomplish this are largely unclear. Previous computational studies have suggested that in principle, certain types of object fragments (rather than whole objects) can be used for invariant recognition. However, whether the human visual system is actually capable of using this strategy remains unknown. Here, we show that human observers can achieve illumination invariance by using object fragments that carry the relevant information. To determine this, we have used novel, but naturalistic, 3-D visual objects called ‘digital embryos’. Using novel instances of whole embryos, not fragments, we trained subjects to recognize individual embryos across illuminations. We then tested the illumination-invariant object recognition performance of subjects using fragments. We found that the performance was strongly correlated with the mutual information (MI) of the fragments, provided that MI value took variations in illumination into consideration. This correlation was not attributable to any systematic differences in task difficulty between different fragments. These results reveal two important principles of invariant object recognition. First, the subjects can achieve invariance at least in part by compensating for the changes in the appearance of small local features, rather than of whole objects. Second, the subjects do not always rely on generic or pre-existing invariance of features (i.e., features whose appearance remains largely unchanged by variations in illumination), and are capable of using learning to compensate for appearance changes when necessary. These psychophysical results closely fit the predictions of earlier computational studies of fragment-based invariant object recognition.http://journal.frontiersin.org/Journal/10.3389/fncom.2012.00056/fullLightingmutual informationForm visionIllumination constancyInformative fragmentsInvariant recognition |
| spellingShingle | Evgeniy eBart Jay eHegdé Invariant Object Recognition Based on Extended Fragments Frontiers in Computational Neuroscience Lighting mutual information Form vision Illumination constancy Informative fragments Invariant recognition |
| title | Invariant Object Recognition Based on Extended Fragments |
| title_full | Invariant Object Recognition Based on Extended Fragments |
| title_fullStr | Invariant Object Recognition Based on Extended Fragments |
| title_full_unstemmed | Invariant Object Recognition Based on Extended Fragments |
| title_short | Invariant Object Recognition Based on Extended Fragments |
| title_sort | invariant object recognition based on extended fragments |
| topic | Lighting mutual information Form vision Illumination constancy Informative fragments Invariant recognition |
| url | http://journal.frontiersin.org/Journal/10.3389/fncom.2012.00056/full |
| work_keys_str_mv | AT evgeniyebart invariantobjectrecognitionbasedonextendedfragments AT jayehegde invariantobjectrecognitionbasedonextendedfragments |