A hybrid approach combining extreme learning machine and sparse representation for image classification

Two well-known techniques, extreme learning machine (ELM) and sparse representation based classification (SRC) method, have attracted significant attention due to their respective performance characteristics in computer vision and pattern recognition. In general, ELM has speed advantage and SRC has accuracy advantage. However, there also remain drawbacks that limit their practical application. Actually, in the field of image classification, ELM performs extremely fast while it cannot handle noise well, whereas SRC shows notable robustness to noise while it suffers high computational cost. In order to incorporate their respective advantages and also overcome their respective drawbacks, this work proposes a novel hybrid approach combining ELM and SRC for image classification. The new approach is applied to handwritten digit classification and face recognition, experiments results demonstrate that it not only outperforms ELM in classification accuracy but also has much less computational complexity than SRC.