Gender classification from face images using central difference convolutional networks

Fathollahi, Mohammadreza Sheikh; Heidari, Rezvan

doi:10.1007/s13735-022-00259-0

Cited by 7 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [11], the authors implement a model to combine handcrafted features with CNN to overcome challenges such as illumination, pose variations and the necessity of voluminous training sets. Proposing two convolutional neural networks using the central difference convolution layer and the vanilla convolution layer is considered in [12] to predict gender of face images. The authors of [13] introduce a CNN-based approach for gender classification of face images to construct the feature images first using raw patterns to represent a set of salient features for a CNN-based network as input to extract more salient features.…”

Section: Introductionmentioning

confidence: 99%

Gender Classification through Fusion of Holistic and Region-based Facial Patterns

Eskandarı

2024

Çukurova Üniversitesi Mühendislik Fakültesi Dergisi

View full text Add to dashboard Cite

In this study, a robust gender prediction system is proposed to fuse global and regional facial representations through score and feature level fusion. In order to extract facial features for gender classification, Binarized Statistical Image Features (BSIF) approach is applied on holistic and regional features of face images. The extracted features are then concatenated to combine the region-based information at feature level fusion. Then the optimized sub-set of features is selected using Particle Swarm Optimization (PSO) method. Finally, the holistic and regional features are combined at score level fusion to produce the final set of scores for gender classification. This study applies Weighted Sum (WS) rule strategy for score level fusion. The experimental results are performed on Multiple Biometric Grand Challenge (MBGC) and CASIA-Iris-Distance databases with consideration of subject-disjoint training and testing evaluation to testify the validity of the proposed gender classification system. The experimental results of the study demonstrate the success of the proposed scheme for gender prediction.

show abstract

Section: Introductionmentioning

confidence: 99%