Gender recognition: A multiscale decision fusion approach

Gender recognition from face images has many applications and is thus an important research topic. This paper presents an approach to gender recognition based on shape, texture and plain intensity features gathered at different scales. We also propose a new dataset for gender evaluation based on images from the UND database. This allows for precise comparison of different algorithms over the same data. The experiments showed that information from different scales, even if just from a single feature, is more important than having information from different features at a single scale. The presented approach is quite competitive with above 90% accuracy in both evaluated datasets.