Learning class-specific edges for object detection and segmentation
<p>Recent research into recognizing object classes (such as humans, cows and hands) has made use of edge features to hypothesize and localize class instances. However, for the most part, these edge-based methods operate solely on the geometric shape of edges, treating them equally and ignoring...
| Main Authors: | , , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
Springer
2006
|
| _version_ | 1824458972894068736 |
|---|---|
| author | Prasad, M Zisserman, A Fitzgibbon, A Kumar, MP Torr, PHS |
| author_facet | Prasad, M Zisserman, A Fitzgibbon, A Kumar, MP Torr, PHS |
| author_sort | Prasad, M |
| collection | OXFORD |
| description | <p>Recent research into recognizing object classes (such as humans, cows and hands) has made use of edge features to hypothesize and localize class instances. However, for the most part, these edge-based methods operate solely on the geometric shape of edges, treating them equally and ignoring the fact that for certain object classes, the appearance of the object on the “inside” of the edge may provide valuable recognition cues.</p>
<br>
<p>We show how, for such object classes, small regions around edges can be used to classify the edge into object or non-object. This classifier may then be used to prune edges which are not relevant to the object class, and thereby improve the performance of subsequent processing. We demonstrate learning class specific edges for a number of object classes — oranges, bananas and bottles — under challenging scale and illumination variation.</p>
<br>
<p>Because class-specific edge classification provides a low-level analysis of the image it may be integrated into any edge-based recognition strategy without significant change in the high-level algorithms. We illustrate its application to two algorithms: (i) chamfer matching for object detection, and (ii) modulating contrast terms in MRF based object-specific segmentation. We show that performance of both algorithms (matching and segmentation) is considerably improved by the class-specific edge labelling.</p> |
| first_indexed | 2025-02-19T04:34:23Z |
| format | Conference item |
| id | oxford-uuid:2eae2f05-49c0-45c0-b125-4a1ebce47811 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2025-02-19T04:34:23Z |
| publishDate | 2006 |
| publisher | Springer |
| record_format | dspace |
| spelling | oxford-uuid:2eae2f05-49c0-45c0-b125-4a1ebce478112025-01-28T15:34:56ZLearning class-specific edges for object detection and segmentationConference itemhttp://purl.org/coar/resource_type/c_5794uuid:2eae2f05-49c0-45c0-b125-4a1ebce47811EnglishSymplectic ElementsSpringer2006Prasad, MZisserman, AFitzgibbon, AKumar, MPTorr, PHS<p>Recent research into recognizing object classes (such as humans, cows and hands) has made use of edge features to hypothesize and localize class instances. However, for the most part, these edge-based methods operate solely on the geometric shape of edges, treating them equally and ignoring the fact that for certain object classes, the appearance of the object on the “inside” of the edge may provide valuable recognition cues.</p> <br> <p>We show how, for such object classes, small regions around edges can be used to classify the edge into object or non-object. This classifier may then be used to prune edges which are not relevant to the object class, and thereby improve the performance of subsequent processing. We demonstrate learning class specific edges for a number of object classes — oranges, bananas and bottles — under challenging scale and illumination variation.</p> <br> <p>Because class-specific edge classification provides a low-level analysis of the image it may be integrated into any edge-based recognition strategy without significant change in the high-level algorithms. We illustrate its application to two algorithms: (i) chamfer matching for object detection, and (ii) modulating contrast terms in MRF based object-specific segmentation. We show that performance of both algorithms (matching and segmentation) is considerably improved by the class-specific edge labelling.</p> |
| spellingShingle | Prasad, M Zisserman, A Fitzgibbon, A Kumar, MP Torr, PHS Learning class-specific edges for object detection and segmentation |
| title | Learning class-specific edges for object detection and segmentation |
| title_full | Learning class-specific edges for object detection and segmentation |
| title_fullStr | Learning class-specific edges for object detection and segmentation |
| title_full_unstemmed | Learning class-specific edges for object detection and segmentation |
| title_short | Learning class-specific edges for object detection and segmentation |
| title_sort | learning class specific edges for object detection and segmentation |
| work_keys_str_mv | AT prasadm learningclassspecificedgesforobjectdetectionandsegmentation AT zissermana learningclassspecificedgesforobjectdetectionandsegmentation AT fitzgibbona learningclassspecificedgesforobjectdetectionandsegmentation AT kumarmp learningclassspecificedgesforobjectdetectionandsegmentation AT torrphs learningclassspecificedgesforobjectdetectionandsegmentation |