A Leaf Vein Extraction Method Based On Snakes Technique

Leaf vein extraction is a key step of modeling plant organs and living plant recognition. An efficient leaf vein extraction method is proposed in this paper by combining snakes technique with cellular neural networks (CNN). The active contours technique based on CNN provide high flexibility and control for the contour dynamics of the snakes. This approach has the advantage of applying a priori knowledge, puts similar characteristics from both the implicit and parametric models, to improve the precise and robustness of the segmentation. The experimental results have also shown that the proposed method can obtain satisfactory results of leaf segmentation (to extract leaf veins and outlines), for the subsequent modeling leaf and leaf recognition