A study of CNN outside of training conditions

Dahia, Gabriel; Santos, Matheus; Segundo, Maurício Pamplona

doi:10.1109/icip.2017.8296997

Cited by 4 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While the IIT ear images are not unconstrained, they can be used to detect overfitting to the wild scenarios (i.e. using images from easier databases should always result in higher accuracy), a problem that was already observed in works that recognize faces in the wild [17]. Although all the remaining databases are unconstrained, based on their descriptive characteristics, we conclude that WPUTE and UERC are respectively the least and the most challenging unconstrained image sets, while AWE and ITWE have a similar difficulty level.…”

Section: Discussionmentioning

confidence: 99%

Employing fusion of learned and handcrafted features for unconstrained ear recognition

2018

View full text Add to dashboard Cite

We present an unconstrained ear recognition framework that outperforms state-of-the-art systems in different publicly available image databases. To this end, we developed CNN-based solutions for ear normalization and description, we used well-known handcrafted descriptors, and we fused learned and handcrafted features to improve recognition. We designed a two-stage landmark detector that successfully worked under untrained scenarios. We used the results generated to perform a geometric image normalization that boosted the performance of all evaluated descriptors. Our CNN descriptor outperformed other CNN-based works in the literature, specially in more difficult scenarios. The fusion of learned and handcrafted matchers appears to be complementary as it achieved the best performance in all experiments. The obtained results outperformed all other reported results for the UERC challenge, which contains the most difficult database nowadays.

show abstract

Section: Discussionmentioning

confidence: 99%