Image cropping is a technique that is used to select the most relevant areas of an image and discarding the useless parts. Handmade selection, especially in case of large photo collections, is a time consuming task. Automatic image cropping techniques may help users, suggesting to them which part of the image is the most relevant, according to specific criteria. In this paper we suppose that the most visually salient areas of a photo are also the most relevant ones to the users. We compare three different saliency detection methods within an automatic image cropping system, to study the effectiveness of the related saliency maps for this task. We furthermore extended one of the three methods (our previous work), which is based on the extraction of keypoints from the image. Tests have been conducted onto an online available dataset, made of 5000 images which have been manually labeled by 9 users.
Ardizzone, E., Bruno, A., & Mazzola, G. (2013). Saliency Based Image Cropping. In IMAGE ANALYSIS AND PROCESSING (ICIAP 2013), PT 1 (pp.773-782). Petrosino, Alfredo.
|Autori:||Ardizzone, E.; Bruno, A.; Mazzola, G.|
|Titolo:||Saliency Based Image Cropping|
|Settore Scientifico Disciplinare:||Settore ING-INF/05 - Sistemi Di Elaborazione Delle Informazioni|
|Nome del convegno:||International Conference of Image Analysis and Processing|
|Luogo del convegno:||Naples, Italy|
|Anno del convegno:||19-23/09/2013|
|Data di pubblicazione:||2013|
|Numero di pagine:||10|
|Citazione:||Ardizzone, E., Bruno, A., & Mazzola, G. (2013). Saliency Based Image Cropping. In IMAGE ANALYSIS AND PROCESSING (ICIAP 2013), PT 1 (pp.773-782). Petrosino, Alfredo.|
|Tipologia:||0 - Proceedings (TIPOLOGIA NON ATTIVA)|
|Appare nelle tipologie:||0 - Proceedings (TIPOLOGIA NON ATTIVA)|