This book mainly deals with grassland digitalization and recognition through computer vision, which will make contributions to implement of grass auto recognition and data acquisition. Taking advantage of computer vision, it focuses on intrinsic feature extraction to realize the functions such as auto recognition of forage seeds and microscope images mosaic. The book presents a new approach for identification of grass seeds, with clear figures and detailed tables. It enlightens reader by solving the traditional problems of pratacultural science through the aid of computer science.

Assists readers to solve the traditional problems of pratacultural science through computer science Focuses on intrinsic feature extraction of easily acquired common grass images instead of remote sensing images Realizes auto recognition of forage and microscope images mosaic by new application of artificial intelligence Inspires more investigators to get involved into the work of grassland digitization based on computer vision

Auteur

Dr. Xin Pan is a Professor of College of Computer and Information Engineering, Inner Mongolia Agricultural University. She received her Ph.D. in signal and information processing from Beijing Jiaotong University in 2009. Then she carried out her postdoctoral researches in Grassland Research Institute of Chinese Academy of Agricultural Sciences from 2010-2014. Dr. Pan Xin's research interest is image processing and pattern recognition. Her work focuses on solving the traditional problems of pratacultural science by the means of computer vision. She has published more than 30 papers, and is a member of professional organizations of China Institute of Communications and Chinese Grassland Society. Her research is an initial effort in the research of grassland digitization based on computer vision, especially focus on identification and mosaic of gramineous grass seeds, which provides a new approach for automated data acquisition of grassland.

Contenu
Introduction.- Forage Identification and Experimental Materials.- Identification of Gramineous Grass Seeds Using Gabor and Locality Preserving Projections.- Identification of Gramineous Grass Seeds Using Difference of Local Fractal Dimensions.- Identification of Gramineous Grass Seeds Using Local Similarity Pattern and Linear Discriminant Analysis.- Identification of Gramineous Grass Seeds Using Local Similarity Pattern and Gray Level Co-occurrence Matrix.- Microscopic Image Mosaic of Gramineous Grass Seeds.- Digital Information Platform of Grassland and Forage Based on Computer Vision.