Based on the accurate analysis of cucumber disease images, the low level feature of images was effectively extracted, and Gaussian Mixture Model （GMM） for 8 common cucumber diseases was built. The parameters of GMM ...Based on the accurate analysis of cucumber disease images, the low level feature of images was effectively extracted, and Gaussian Mixture Model （GMM） for 8 common cucumber diseases was built. The parameters of GMM were estimated by the algorithm of expectation maximum （EM） to accurately charac- terize the feature distribution of 8 cucumber diseases, thus increased the correct identification of cucumber diseases and accurate grasping of damage conditions, and provided basis for achievement of real-time and accurate prediction of cucumber diseases.展开更多
Agriculture is an important research area in the field of visual recognition by computers.Plant diseases affect the quality and yields of agriculture.Early-stage identification of crop disease decreases financial loss...Agriculture is an important research area in the field of visual recognition by computers.Plant diseases affect the quality and yields of agriculture.Early-stage identification of crop disease decreases financial losses and positively impacts crop quality.The manual identification of crop diseases,which aremostly visible on leaves,is a very time-consuming and costly process.In this work,we propose a new framework for the recognition of cucumber leaf diseases.The proposed framework is based on deep learning and involves the fusion and selection of the best features.In the feature extraction phase,VGG(Visual Geometry Group)and Inception V3 deep learning models are considered and fine-tuned.Both fine-tuned models are trained using deep transfer learning.Features are extracted in the later step and fused using a parallel maximum fusion approach.In the later step,best features are selected usingWhale Optimization algorithm.The best-selected features are classified using supervised learning algorithms for the final classification process.The experimental process was conducted on a privately collected dataset that consists of five types of cucumber disease and achieved accuracy of 96.5%.A comparison with recent techniques shows the significance of the proposed method.展开更多
基金Supported by National Natural Science Foundation of China ( 60903066,0985244)Natural Science Foundation of Beijing City ( 4102049)+1 种基金 New Teacher Fund of Ministry of Education ( 20090009120006) Basic Scientific Research Expenses of Central College ( 20100008030)~~
文摘Based on the accurate analysis of cucumber disease images, the low level feature of images was effectively extracted, and Gaussian Mixture Model （GMM） for 8 common cucumber diseases was built. The parameters of GMM were estimated by the algorithm of expectation maximum （EM） to accurately charac- terize the feature distribution of 8 cucumber diseases, thus increased the correct identification of cucumber diseases and accurate grasping of damage conditions, and provided basis for achievement of real-time and accurate prediction of cucumber diseases.
基金The authors extend their appreciation to the Deanship of Scientific Research at King Saud University for funding this work through research group number RG-1441-425.
文摘Agriculture is an important research area in the field of visual recognition by computers.Plant diseases affect the quality and yields of agriculture.Early-stage identification of crop disease decreases financial losses and positively impacts crop quality.The manual identification of crop diseases,which aremostly visible on leaves,is a very time-consuming and costly process.In this work,we propose a new framework for the recognition of cucumber leaf diseases.The proposed framework is based on deep learning and involves the fusion and selection of the best features.In the feature extraction phase,VGG(Visual Geometry Group)and Inception V3 deep learning models are considered and fine-tuned.Both fine-tuned models are trained using deep transfer learning.Features are extracted in the later step and fused using a parallel maximum fusion approach.In the later step,best features are selected usingWhale Optimization algorithm.The best-selected features are classified using supervised learning algorithms for the final classification process.The experimental process was conducted on a privately collected dataset that consists of five types of cucumber disease and achieved accuracy of 96.5%.A comparison with recent techniques shows the significance of the proposed method.
