Single- and cross- database benchmarks for gender classification under unconstrained settings

Dago-Casas, Pablo; González-Jiménez, Daniel; Yu, Long; Alba-Castro, José Luis

doi:10.1109/iccvw.2011.6130514

Cited by 57 publications

(73 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For instance, the AdaBoost and the SVM algorithms have been widely used in the literature (Baluja and Rowley (2007); Shan (2012); Eidinger et al (2014)). In this spirit, an excellent comparison of gender recognition techniques using different methods can be found in Dago-Casas et al (2011).…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Local Deep Neural Networks for gender recognition

Mansanet

Albiol

Paredes

2016

Pattern Recognition Letters

116

View full text Add to dashboard Cite

Deep Learning methods are able to automatically discover better representations of the data to improve the performance of the classifiers. However, in computer vision tasks, such us the gender recognition problem, sometimes it is difficult to directly learn from the entire image. In this work we propose a new model called Local Deep Neural Network (Local-DNN), which is based on two key concepts: local features and deep architectures. The model learns from small overlapping regions in the visual field using discriminative feed-forward networks with several layers. We evaluate our approach on two well-known gender benchmarks, showing that our Local-DNN outperforms other deep learning methods also evaluated and obtains state-of-the-art results in both benchmarks.

show abstract

Section: Related Workmentioning

confidence: 99%

“…There is not an standard protocol for gender classification in Gallagher's DB, so we have used the same protocol proposed by Dago-Casas et al (2011). On that article, a new version of the dataset was created by removing several low resolution face images.…”

Section: Gallagher's Dbmentioning

confidence: 99%

Local Deep Neural Networks for gender recognition

Mansanet

Albiol

Paredes

2016

Pattern Recognition Letters

116

View full text Add to dashboard Cite

show abstract

“…Protocol Accuracy [19] LFW Subset 7443/13233 94.81% [20] LFW Subset 7443/13233 98.01% [7] LFW BEFIT protocol 97.23% [7] GROUPS Subset 15579/28231 84.55 − 86.61% [12] GROUPS Subset 22778/28231 86.4% [5] MORPH Subset 88% [17] MORPH Subset 97.1%…”

Section: Reference Datasetmentioning

confidence: 99%

Improving Gender Classification Accuracy in the Wild

Castrillón-Santana

Lorenzo-Navarro

Ramón-Balmaseda

2013

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

View full text Add to dashboard Cite

Abstract. In this paper, we focus on gender recognition in challenging large scale scenarios. Firstly, we review the literature results achieved for the problem in large datasets, and select the currently hardest dataset: The Images of Groups. Secondly, we study the extraction of features from the face and its local context to improve the recognition accuracy. Different descriptors, resolutions and classifiers are studied, overcoming previous literature results, reaching an accuracy of 89.8%.

show abstract

“…As we do not know in advance the best grid resolution configuration, and observing the input pattern dimensions, each descriptor is evaluated for different grid resolutions in the periocular area, from 1 × 1 up to 8 × 6 cells. A known experimental framework is used, the protocol described in [15], for better comparison of the results with previous literature.…”

Section: System Overviewmentioning

confidence: 99%

“…As mentioned above, the experimental evaluation follows the protocol defined by [15]. This protocol defines a 5-fold crossvalidation setup, containing the subset of faces belonging to GROUPS that present an inter-eye distance larger than 20 pixels.…”

Section: Experimental Evaluationmentioning

confidence: 99%