Skip to Main Content
This paper investigates the local Gabor filters for facial expression recognition. The local Gabor filters can not only reduce the memory requirement but also lower the time of extracting Gabor features. By contracting among the recognition rates using different local Gabor filters, we can get that not each of the Gabor filters which choose different scales can provide the same power for facial expression recognition. The local Gabor filters choosing lower scales always provide higher power than the ones choosing higher scales does. The quantitative results clearly suggest that the proposed approach produces encouraging results and opens a promising direction for speeding facial expression recognition.