Abstract
This research study proposes a novel method of inter-related problems in face recognition using the NeuCube neuromorphic computational platform. We investigated age classification and gender recognition. The well-known FG-NET and MORPH Album 2 image gallery were used and anthropometric features were extracted from landmark points on the face. The landmarks were preprocessed with the procrustes algorithm before feature extraction was performed. The Weka machine learning workbench was used to compare the performance of traditional techniques such as the K nearest neighbour (Knn) and Multi-Layer Perceptron (MLP) with NeuCube. Our empirical results show that NeuCube performed consistently better across both problem types that we investigated.
Original language | English |
---|---|
Pages (from-to) | 145-156 |
Number of pages | 11 |
Journal | Evolving Systems |
Volume | 9 |
Issue number | (2018) |
Early online date | 17 Feb 2017 |
DOIs | |
Publication status | Published (in print/issue) - 30 Jun 2018 |
Keywords
- Anthropometric model
- Age grpoup classification
- Geneder classification
- Spiking neural networks