Overview of handcrafted features and deep learning models for leaf recognition

In this study, an automated system for classification of leaf species based on the global and local features is presented by concentrating on a smart and unorthodox decision system. The utilized global features consist of 11 features and separated into two categories; gross shape features (7) and moment based features (4), respectively. In case of local features, only the curve points on Bézier curves are accepted as discriminative features. With the purpose of reducing the search space and improving the performance of the system, firstly the class label of leaf object is determined by conducting the global features with respect to predefined threshold values. Once the target class is determined, the local features have performed in order to assign the leaf species into a unique class. In classification stage, the k-nearest neighbor (k-nn) algorithm has utilized based on the Hausdorff distance. The proposed classification scheme provides high accuracy rate as achieving the 96.78% performance on Flavia and the 94.66% on SLID dataset. The results of the experimental study reveal that the combination of these features is more effective than preferring a single feature for leaf recognition task.