Sift and Deep Convolutional Features for Closeness-Based Leaf Image Recognition

Plant leaf recognition has been carried out widely using low level features. Scale invariant feature transform techniques have been used to extract the low level features. Leaves that match based on low level features but do not do so in the semantic perspective cannot not be recognized. To address that, global features have been extracted and used using convolutional neural networks. Even then there are issues like leaf images in various illuminations, rotations, taken in different angles, and so on. To address such issues, the closeness among low level features and global features are computed using multiple distance measures and a leaf recognition framework has been proposed. The matched patches are evaluated both quantitatively and qualitatively. Experimental results obtained are promising for the proposed closeness-based leaf recognition framework.