A considerable work is proposed in the area of leaf-based plant recognition during the last decade using image processing and computer vision methods. Kadir et al. (2011) have presented a probabilistic neural network-based classification model for 60 types of foliage plants. This work has used mean, standard deviation, skewness as colour moments, shape features, grey level co-occurrence matrix-based texture features and Polar Fourier Transform. Vein features also added to increase the accuracy of the system. The result displays that the system provides mean accuracy of 93.0833%. In a similar type of another work, Kadir et al. (211) have utilized shape, texture, vein and colour features for plant classification Flavia dataset. This dataset consists of 32 types of leaves. A neural network model is designed with these features. The average accuracy of 93.75% is attained in this work.