A detail review on the processes and methods of automatic classification of power quality disturbances is presented in this paper. The development of artificial intelligence techniques has produced a strong foundation in recent literature for detecting power quality disturbances. Hence, this review gives scope to curious researchers to realize the recent trend of power quality disturbances classification. The commonly used feature extraction methods such as Fourier transform, short-time Fourier transform, wavelet transform and S-transform are discussed here. Automatic feature extraction techniques from image processing are reviewed. Extracted features are applied to the inputs of artificial intelligence based classifier such as artificial neural networks, convolutional neural networks, support vector machines, Fuzzy logic and expert system. Accuracy of the power quality disturbances classifier is improved by using optimization techniques such as genetic algorithm, particle swarm optimization and ant colony optimization. Different research papers from the power quality area are critically reviewed and classified.