Plant Leaf Identification Using Multi-scale Fractal Dimension

摘要: Taxonomical classification of plants is a very complex and time-consuming task. This mostly due to the great biodiversity species fact most measures extracted from are traditionally performed manually. paper presents novel approach plant identification based on leaf texture. Initially, texture modelled as surface, so complexity analysis using Multi-scale fractal dimension can be over generated resulting in feature vector which represents terms spatial scale. Yielded results show potential approach, overcomes traditional methods, such Co-occurrence matrices, Gabor filters Fourier descriptors.