Computer Aided Landscape Design and Image Recognition of Ornamental Grass Based on Ecological Aesthetics

The concept of landscape architecture has a long history, which existed before the computer appeared, such as the Western Palace landscape architecture and Chinese classical landscape architecture. But in the past, landscape designers could only rely on paper and pen to complete their work, so the work efficiency was very low. Quickly and effectively classifing and recognizing images is of great significance. This paper proposes an improved multi-layer perceptron model and introduces dropout to solve the over fitting problem. Experimental results show that Parzen classifier can effectively classify images, and the algorithm has good generalization performance.