A feature extraction unit (23) extracts features of an object of interest included in an image. A local region setting unit (24) sets a local region that includes a feature group required to obtain the shape of the object and a local region that includes a feature group required to obtain the positional relationship. A feature vector generation unit (25) calculates feature vector data in the set local regions. An object recognition unit (26) determines which of different objects the object of interest is, on the basis of the feature vectors.