Feature Extraction of Leaf Images for Mite Disease in Cotton Fields

Zhi Hua Diao; Yin Mao Song; Yun Peng Wang; Huan Wang

doi:10.4028/www.scientific.net/AMR.605-607.919

Paper Titles

Research on the Computational Algorithms for Layer Wound Linear Variable Differential Transformers
p.899

Classification of Floral Origins of Honey by NIR and Chemometrics
p.905

Modeling and Simulation of the Dissolved Oxygen Monitoring System in Aquaculture
p.910

Researches on the Size Measurement of Mechanical Parts Based on Image Processing
p.915

Feature Extraction of Leaf Images for Mite Disease in Cotton Fields
p.919

Research of Ultrasonic Flow Detection Method Based on Hydrodynamics Analysis
p.923

Research on Non-Invasive Measurement of Optical Parameters of the Tissues by Support Vector Machine
p.929

Determination of Trimethylamine in Air by Cataluminescence-Based Gas Sensor
p.933

Monitoring and Research of Power Ultrasonic Honing Vibration Frequency
p.937

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 605-607Feature Extraction of Leaf Images for Mite Disease...

Feature Extraction of Leaf Images for Mite Disease in Cotton Fields

Abstract:

To realize timely and reliable diagnosis of the cotton mite disease, the leaves image features of mite disease were extracted by using computer image processing technology. First the average value and variance of the hue H and G/R as the color features were extracted by the histogram. Secondly, the entropy and inertia value were extracted by the algorithm of co- matrix. Then, according to the binary images of leaves for mite disease, two morphological features of leaf lesion, such as circularity and elongation were extracted. Experiments results indicated that the characteristic values could distinguish the cotton mite disease leaves and normal leaves better. The method which was applied to diagnose the cotton mite disease would improve the accuracy of disease identification and achieve effective governance of cotton mite disease.