On Improving Face Detection Performance by Modelling Contextual Information
| Type of publication: | Idiap-RR |
| Citation: | Atanasoaei_Idiap-RR-43-2010 |
| Number: | Idiap-RR-43-2010 |
| Year: | 2010 |
| Month: | 12 |
| Institution: | Idiap |
| Abstract: | In this paper we present a new method to enhance object detection by removing false alarms and merging multiple detections in a principled way with few parameters. The method models the output of an object classiï¬er which we consider as the context. A hierarchical model is built using the detection distribution around a target sub-window to discriminate between false alarms and true detections. Next the context is used to iteratively reï¬ne the detections. Finally the detections are clustered using the Adaptive Mean Shift algorithm. The speciï¬c case of face detection is chosen for this work as it is a mature ï¬eld of research. We report results that are better than baseline method on XM2VTS, BANCA and MIT+CMU face databases. We signiï¬cantly reduce the number of false acceptances while keeping the detection rate at approximately the same level and in certain conditions we recover miss-aligned detections. |
| Keywords: | |
| Projects: |
Idiap MOBIO |
| Authors: | |
| Added by: | [ADM] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
