A5101683316- Advanced Algorithms and Applications
- Remote Sensing and Land Use
- Remote-Sensing Image Classification
- Medical Image Segmentation Techniques
- Neural Networks and Applications
- Conducting polymers and applications
- Image Retrieval and Classification Techniques
- Advanced Image Fusion Techniques
- Advanced Measurement and Detection Methods
- Advanced Sensor and Control Systems
- Organic Electronics and Photovoltaics
- Soil, Finite Element Methods
- Organic Light-Emitting Diodes Research
Anhui University of Finance and Economics
2023
Xidian University
2019
Fudan University
2008
Zhejiang Sci-Tech University
2007
With the development of remote sensing imaging technology, images with high-resolution and complex structure can be acquired easily. The classification is always a hot challenging problem. In order to improve performance image classification, we propose an adaptive multiscale deep fusion residual network (AMDF-ResNet). AMDF-ResNet consists backbone network. including several blocks generates hierarchy features, which contain semantic information from low high levels. network, feature module...
An approach for pearl shape classification using fuzzy pattern recognition based on Zernike moments was proposed. After a series of preprocessing the image obtained, transformed it to polar coordinates, then calculated eighth-derivative means as each type typical 's characteristic parameter. The utilization achieved effective distinction single image, finally, by seeking and comparison characteristics through multi-angles view, realized classification. Experiment results indicated that,...
Consider three different types of non-homogeneous term for constant coefficient linear differential equation, set the corresponding special solution, then part function containing coefficients to be determined in solution is studied, equation that satisfies obtained. By using comparative method find and conclusions are given. This improves original comparing coefficient, calculation considerably simplified.