A Crop Pests Image Classification Algorithm Based on Deep Convolutional Neural Network
Abstract: Conventional pests
image classification methods may not be accurate due to the complex farmland
background, sunlight and pest gestures. To raise the accuracy, the deep
convolutional neural network (DCNN), a concept from Deep Learning, was used in
this study to classify crop pests image. On the ground of our experiments, in
which LeNet-5 and AlexNet were used to classify pests image, we have analyzed
the effects of both convolution kernel and the number of layers on the network,
and redesigned the structure of convolutional neural network for crop pests.
Further more, 82 common pest types have been classified, with the accuracy
reaching 91%. The comparison to conventional classification methods proves that
our method is not only feasible but preeminent.
Author: RuJing Wang
Journal Code: jptkomputergg170179
Artikel Terkait :
Jp Teknik Komputer gg 2017
- Social Media Success Model for Knowledge Sharing (Scale Development and Validation)
- Histogram Equalization for Improving Quality of Low-Resolution Ultrasonography Images
- Research and Application of Development Model of Information Service for IOT of Oil and Gas Production Based on Cloud Architecture
- A Customized Reconfiguration Controller with Remote Direct ICAP Access for Dynamically Reconfigurable Platform
- Design LTE Microstrip Antenna Rectangular Patch with Beetle-Shaped Slot
- Design of Circular Patch with Double C-Shaped Slot Microstrip Antenna for LTE 1800 MHz
- A Three-Phase Grid-Connected PV System Based on SAPF for Power Quality Improvement
- Direct Torque Control: Stator Flux Regulation Improvement at Low Speed
- Brown’s Weighted Exponential Moving Average Implementation in Forex Forecasting
- Hierarchical Gaussian Scale-Space on Androgenic Hair Pattern Recognition
- The Pessimistic Investor Sentiments Indicator in Social Networks
- 94 GHz Millimeter Wave Conducted Speech Enhancement
- Automatic Image Annotation Using CMRM with Scene Information
- Managers Perceptions towards the Success of E-performance Reporting System
- Binarization of Ancient Document Images based on Multipeak Histogram Assumption
- Automatic Summarization in Chinese Product Reviews
- Progressive Mining of Sequential Patterns Based on Single Constraint
- A Novel Space-time Discontinuous Galerkin Method for Solving of One-dimensional Electromagnetic Wave Propagations
- Development of Ammonia Gas Leak Detection and Location Method
- Compact Power Divider Integrated with Coupler and Microstrip Cavity Filter for X-band Surveillance Radar System
- Performance of Groundplane Shaping in Four-Element Dualband MIMO Antenna
- A Mamdani Fuzzy Model to Choose Eligible Student Entry
- Potential Usage Estimation of Ground Water using Spatial Association Rule Mining
- Investigation Study of Three-Level Cascaded H-bridge Multilevel Inverter