Two Fuzzy Lattice Reasoning (FLR) Classifiers and their Application for Human Facial Expression Recognition
S.E. Papadakis, V.G. Kaburlasos and G.A. Papakostas
We deal with the problem of human facial expression recognition from digital images. A digital image is preprocessed for feature extraction using moment descriptors; then, it is represented in the product lattice (F100, ≤) of Intervals’ Numbers (INs). Learning as well as generalization are carried out in space (F100, ≤) by two different Fuzzy Lattice Reasoning (FLR) classifiers based on an inclusion measure function σ : F100 x F100 → [0, 1]. We pursue both a stochastic optimization and a parallel implementation of the proposed techniques. Comparative experimental results on three benchmark data sets demonstrate a superior performance of the proposed FLR classification schemes.
Keywords: Parallel processing; GPU computing; stochastic optimization; particle swarm; PSO; fuzzy lattice reasoning; intervals’ number; inclusion measure; facial expression recognition.