The Research of Disease Spots Extraction Based on Evolutionary Algorithm

Abstract

According to the characteristics of maize disease spot performance in the image, this paper designs two-histogram segmentation method based on evolutionary algorithm, which combined with the analysis of image of maize diseases and insect pests, with full consideration of color and texture characteristic of the lesion of pests and diseases, the chroma and gray image, composed of two tuples to build a two-dimensional histogram, solves the problem of one-dimensional histograms that cannot be clearly divided into target and background bimodal distribution and improved the traditional two-dimensional histogram application in pest damage lesion extraction. The chromosome coding suitable for the characteristics of lesion image is designed based on second segmentation of the genetic algorithm Otsu. Determining initial population with analysis results of lesion image, parallel selection, optimal preservation strategy, and adaptive mutation operator are used to improve the search efficiency. Finally, by setting the fluctuation threshold, we continue to search for the best threshold in the range of fluctuations for implementation of global search and local search.

A Novel Image Classification Approach for Maize Diseases Recognition

“…In this study, two kinds of feature were selected for image processing and image recognition in order to improve the accuracy: one is SHV color features (such as first moment, second moment and third moment in SHV color space), and another is GLCM texture features (such as energy, entropy, contrast and inertia). We proposes a new image classification approach to recognizing corps diseases, which contains three phases: (1) To recognize maize diseases, the first image preprocessing phase aims to reduce the influence of light, image noise and irrelevant background, and to make the maize spot area easy to extract. The second phase is the image feature extraction, in which the HSV component histogram and its eigenvalues are used in combination with the texture parameters by GLCM method.…”

“…In China, crops are affected by pests and diseases all the time in the growth process (Li et al 2017). Traditionally, agricultural workers have to use their eyes to identify and diagnose crops diseases and make subjective judgments, which are time-consuming, tedious, and inaccurate.…”

Smart insects repeller

“…Honrado, D. B. Solpic, C. M. Favila, E. Tongson, G. L. Tangonan, N. J. C. Libatique from Manila University in Pihilipines, UAV Imaging with Low-cost Multispectral Imaging. The mission is to monitor in rice and corn field using aerial imaging which function as calibration points for extending the measurements over the whole image field [9] .This project implemented an Unmanned Aerial Vehicle (UAV) to run the experiment on agriculture sector. The objective proposed to improve on monitoring and managing regional agriculture.…”

Feature extraction model in systems of diagnostics of plant diseases by the leaf images

“…Over the last years the number of published works have been increased in the field of information systems creation, especially IMS almost in every direction of the agricultural science and production [1][2][3][4][5][6][7][8][9][10][11][12][13][14]. This fact is connected with information and analysis support of experts' intellectual activity that provides productivity in the subject area of industrial technology.…”

“…The source literature analysis, in particular [2][3][4][5][6][7][8][9][10][11][12][13][14], shows that the problem of crop disease diagnosis has not been enough studied. Therefore, the objectives associated with the questions of information extraction on the examined plants given in the form of leaves images are still important today.…”