Hybrid Image Segmentation Algorithm for Leaf Recognition and Characterization

Plants play an important role in both human life and other lives that exist on the earth. Due to environmental deterioration and lack of awareness, many rare plant species are at the margins of extinction. Despite the great advances made in botany, there are many plants yet to be discovered, classified, and utilized; unknown plants are treasures waiting to be found. Leaf classification and recognition for plant identification plays a vital role in all these endeavors. There has been little work reported on leaves, flower and fruit image processing and recognition. In recent years, several researchers have dedicated their work to leaf characterisation. As an inherent trait, leaf vein definitely contains the important information for plant species recognition despite its complex modality. A new approach that combines a thresholding method and H-maxima transformation based method is proposed to extract the leaf veins. A preliminary segmentation based on the intensity histogram of leaf images is first carried out to coarsely determine vein regions using thresholding. This is followed by a fine segmentation using H maxima transformation based method for object pixel as its inputs. Compared with other methods, experimental results show that this combined approach is capable of extracting more accurate venation modality of the leaf for the subsequent vein pattern classification. The approach can also reduce the computing time compared with other approach.