Research on Edge Detection of Agricultural Pest and Disease Leaf Image Based on LvQ Neural Network

Background: Roberts, Sobel, Prewitt and other operators are commonly used in image edge detection, but because of the complex background of agricultural pests and diseases, the efficiency of using these operators to detect is not ideal. Objective: To improve the accuracy of crop disease image edge detection, the method of using LVQ neural network to detect crop disease image edge was studied. Method: It is proposed to use LVQ1 neural network to detect the edge of the image. The commonly used median feature quantity, directional information feature quantity and Krisch operator direction feature quantity are used as the input signal of LVQ1 neural network for network training. On the basis of simulation, An image feature vector that solves the image pixel neighborhood consistency is added, and an algorithm for edge detection using LVQ2 neural network is proposed. Computer simulations show that the improved algorithm makes the edge image continuity of the output significantly improved. Results: Lvq2 neural network can complete the edge detection of gray-scale image better, the output edge image has good continuity, clear contour and keeps most of the original image information. Compared with the lvq1 neural network detection results, the edge image detected by lvq2 neural network has obvious improvement in the processing of small edge, and the contour is clearer. It shows that the training method can make the network better convergence and obtain more ideal output results. Conclusion: The simulation comparison is carried out under the Matlab platform. The results show that based on the LVQ2 neural network, the four image feature quantities are used as the input signal detection algorithm, which makes the output edge image continuity significantly improved, compared with the traditional Sobel algorithm and LVQ1 nerve. The network is more superior, robust and generalized.

Comb Former Parameters for a Cotton Seeder

Success in cultivating cotton largely depends on the timing and quality of soil preparation for sowing and sowing, and the latter, in turn, depends on how it is carried out and on the perfect design of the machines. The aim of the study is to justify the shape of the ridges and the parameters of the moulder to the cotton seeder. The authors proposed a new technology for sowing with the simultaneous formation of ridges. The shape and parameters of the ridge are theoretically substantiated. When performing the shape of the ridge in the form of an isosceles trapezoid and, accordingly, with a height and width of the ridge surface of at least 100 mm and 160 mm, the seed bed is protected from flooding by rain streams. The design of the developed comb moulder to a cotton seeder for the implementation of the proposed technology is given. Theoretically substantiated the main parameters of the crest moulder. It was found that when the input edge of the moulder is 290-320 mm wide, the output edge is 160 mm, the angle of inclination of the side blade to the direction of movement is 20°, the length of the runner of the moulder is 203-215 mm, the height of the side blade is 100 mm and the angle of installation of the side blade to horizon 42-45° ensures highquality implementation of the technological process of formation of ridges. When sowing cotton seeds on the ridges with the simultaneous formation of the ridge, the seedlings of the plants increase, and the cotton yield increases compared to the smooth sowing method of 9.9%.