Study on Identification for the Typical Pasture Based on Image Texture Features

Abstract

Aiming at the problems of pasture monitoring and low-level digitization in Inner Mongolia desert steppe, the texture feature extraction and image recognition for three typical pastures were represented in this paper so as to provide a basis for grass species identification and grassland management. Images of three typical pasture’s leaves (Herb of Shady Jerusalemsage, Cleistogenes songorica (Roshev.) and Ohwiand potentilla anserine) were preprocessed by using image processing technology, 7 kinds texture features were extracted by using Gray-Gradient Co-occurrence Matrix, and then a BP neural network was built for realizing the image recognition of these three pastures. An 84.7% of final overall recognition rate and an effective classification result of three pasture images were received. The experimental results indicate that the image classification were perfectly realized by using a BP neural network model based on texture features. The recognition for forage image provides a scientific basis for the monitoring of vegetation species diversity, grass degradation and pest control.