Plant leaf recognition using a layered approach

The current work proposes an approach for the recognition of plants from their digital leaf images using multiple visual features to handle heterogeneous plant types. Recognizing the fact that plant leaves can have a variety of recognizable features like color (green and non-green) and shape (simple and compound) and texture (vein structure patterns), a single set of features may not be efficient enough for complete recognition of heterogeneous plant types. Accordingly a layered architecture is proposed where each layer handles a specific type of visual characteristics using its own set of features to create a customized data model. Features from various layers are subsequently fed to an array of custom classifiers for a more robust recognition. In this work we enumerate on the color and shape layers only. A dataset involving 600 leaf images divided over 30 classes and including green, non-green, simple and compound leaves, is used to test the performance and effectiveness of the approach.