| _version_ | 1866902309819121664 |
|---|---|
| author | Lisani, José Luis Ramis Guarinos, Silvia Perales Lopez, Francisco J. |
| author_facet | Lisani, José Luis Ramis Guarinos, Silvia Perales Lopez, Francisco J. |
| contents | <p>The a contrario framework is a statistical formulation of a perception principle that permits one to detect meaningful structures in data. It has been applied to the detection of lines and contours in images, moving objects in video, etc., but no attempt has been made to use it for the detection of faces. The goal of this paper is to show that the a contrario formulation can be adapted to the face detection method described by Viola and Jones in their seminal work. We propose an alternative to the cascade of classi ers proposed by the authors by introducing a stochastic a contrario model for the detections of a single classi er, from which adaptive detection thresholds may be inferred. The result is a single classi er whose detection rates are similar to those of a cascade of classi ers. Moreover, we show how a very short cascade of classi ers can be constructed, which improves the<br>accuracy of a classical cascade, at a much lower computational cost. The results prove the validity of the a contrario approach for face detection and suggest that the same principles might be used to improve the performance of state-of-the-art methods.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_1137_17M1118774 |
| institution | Zenodo |
| language | |
| publishDate | 2017 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | A Contrario Detection of Faces: A Case Example Lisani, José Luis Ramis Guarinos, Silvia Perales Lopez, Francisco J. <p>The a contrario framework is a statistical formulation of a perception principle that permits one to detect meaningful structures in data. It has been applied to the detection of lines and contours in images, moving objects in video, etc., but no attempt has been made to use it for the detection of faces. The goal of this paper is to show that the a contrario formulation can be adapted to the face detection method described by Viola and Jones in their seminal work. We propose an alternative to the cascade of classi ers proposed by the authors by introducing a stochastic a contrario model for the detections of a single classi er, from which adaptive detection thresholds may be inferred. The result is a single classi er whose detection rates are similar to those of a cascade of classi ers. Moreover, we show how a very short cascade of classi ers can be constructed, which improves the<br>accuracy of a classical cascade, at a much lower computational cost. The results prove the validity of the a contrario approach for face detection and suggest that the same principles might be used to improve the performance of state-of-the-art methods.</p> |
| title | A Contrario Detection of Faces: A Case Example |
| url | https://doi.org/10.1137/17M1118774 |