Automatic digital plant classification and retrieval can be achieved by extracting features from its leaves. There are various opportunities to improve plant species identification due to computerization through the designing of a convenient automatic plant recognition system. Many different approaches consist of some major parts. First, images of leaf are acquired with di gital camera or scanners. Then the user can selects the base point of the leaf and a few reference points on the leaf blades or done this automatically. Then several morphological features are extracted. These features are used as inputs to the classifier system for discrimination as probabilistic neural network. The network was trained with leaves from different plant species. Then the recognition accuracy of the propo sed method has been tested. The method works only for the plants with broad flat leaves w hich are more or less two dimensional in nature. This paper presented various effective algorithms used for plant classification using leaf images and review the main computational, morphological and image processing methods that have been used in recent y ears and we conclude with a discussion of ongoing work and outstanding problems in the area.
展开▼
