A framework for the recognition of scaled, translated and rotated objects using the short time Fourier transform

Recognition of objects in images regardless of their position, scale and orientation is considered. A framework is used to train and to recognize or classify a transformed object. A set of features obtained from the short-time Fourier transform of the object is used for position, scale and rotation invariant recognition. An analysis window is used to compute the short-time Fourier transform. The Fourier magnitudes in the polar domain constitute the position, scale and rotation invariant features. Since, short time sections are used in this method, features are more separable because of the localization of the window which is useful for discriminating variants of very similar objects. The recognition system is tested for different sets of translations, scales and rotations of several objects. This framework performed well for the range of translations, scales and translations of the objects considered. The framework is computationally efficient and showed robustness in the presence of noise. The tasks involved are simple and the framework can be used for real-time applications