Age estimation based on face images plays an important role in a wide range of scenarios, including security and defense applications, border control, human-machine interaction in ambient intelligence applications, and recognition based on soft biometric information. Recent methods based on deep learning have shown promising performance in this field. Most of these methods use deep networks specifically designed and trained to cope with this problem. There are also some studies that focus on applying deep networks pre-trained for face recognition, which perform a fine-tuning to achieve accurate results. Differently, in this paper, we propose a preliminary study on increasing the performance of pre-trained deep networks by applying postprocessing strategies. The main advantage with respect to finetuning strategies consists of the simplicity and low computational cost of the post-processing step. To the best of our knowledge, this paper is the first study on age estimation that proposes the use of post-processing strategies for features extracted using pretrained deep networks. Our method exploits a set of pre-trained Convolutional Neural Networks (CNNs) to extract features from the input face image. The method then performs a feature level fusion, reduces the dimensionality of the feature space, and estimates the age of the individual by using a Feed-Forward Neural Network (FFNN). We evaluated the performance of our method on a public dataset (Adience Benchmark of Unfiltered Faces for Gender and Age Classification) and on a dataset of nonideal samples affected by controlled rotations, which we collected in our laboratory. Our age estimation method obtained better or comparable results with respect to state-of-the-art techniques and achieved satisfactory performance in non-ideal conditions. Results also showed that CNNs trained on general datasets can obtain satisfactory accuracy for different types of validation images, also without applying fine-tuning methods.

Age Estimation Based on Face Images and Pre-trained Convolutional Neural Networks / A. Anand, R. Donida Labati, A. Genovese, E. Munoz Ballester, V. Piuri, F. Scotti - In: Symposium Series on Computational Intelligence (SSCI)[s.l] : IEEE, 2017 Nov. - ISBN 978-1-5386-4058-6. - pp. 3357-3363 (( convegno SSCI CISDA Proceedings tenutosi a Honolulu nel 2017 [10.1109/SSCI.2017.8285381].

Age Estimation Based on Face Images and Pre-trained Convolutional Neural Networks

A. Anand;R. Donida Labati;A. Genovese;E. Munoz Ballester;V. Piuri;F. Scotti
2017-11

Abstract

Age estimation based on face images plays an important role in a wide range of scenarios, including security and defense applications, border control, human-machine interaction in ambient intelligence applications, and recognition based on soft biometric information. Recent methods based on deep learning have shown promising performance in this field. Most of these methods use deep networks specifically designed and trained to cope with this problem. There are also some studies that focus on applying deep networks pre-trained for face recognition, which perform a fine-tuning to achieve accurate results. Differently, in this paper, we propose a preliminary study on increasing the performance of pre-trained deep networks by applying postprocessing strategies. The main advantage with respect to finetuning strategies consists of the simplicity and low computational cost of the post-processing step. To the best of our knowledge, this paper is the first study on age estimation that proposes the use of post-processing strategies for features extracted using pretrained deep networks. Our method exploits a set of pre-trained Convolutional Neural Networks (CNNs) to extract features from the input face image. The method then performs a feature level fusion, reduces the dimensionality of the feature space, and estimates the age of the individual by using a Feed-Forward Neural Network (FFNN). We evaluated the performance of our method on a public dataset (Adience Benchmark of Unfiltered Faces for Gender and Age Classification) and on a dataset of nonideal samples affected by controlled rotations, which we collected in our laboratory. Our age estimation method obtained better or comparable results with respect to state-of-the-art techniques and achieved satisfactory performance in non-ideal conditions. Results also showed that CNNs trained on general datasets can obtain satisfactory accuracy for different types of validation images, also without applying fine-tuning methods.
classification; recognition
Settore INF/01 - Informatica
Settore ING-INF/05 - Sistemi di Elaborazione delle Informazioni
ABC GATES FOR EUROPE
Enforceable Security in the Cloud to Uphold Data Ownership
COntactlesS Multibiometric mObile System in the wild: COSMOS
Institute of Electrical and Electronics Engineers (IEEE)
IEEE Computational Intelligence Society
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
cisda17.pdf

accesso aperto

Descrizione: Articolo principale
Tipologia: Post-print, accepted manuscript ecc. (versione accettata dall'editore)
Dimensione 292.69 kB
Formato Adobe PDF
292.69 kB Adobe PDF Visualizza/Apri
Age_estimation_based_on_face_images_and_pre-trained_convolutional_neural_networks.pdf

non disponibili

Tipologia: Publisher's version/PDF
Dimensione 273.62 kB
Formato Adobe PDF
273.62 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/2434/527428
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 20
  • ???jsp.display-item.citation.isi??? 0
social impact