A5114348281- Advanced Algorithms and Applications
- Medical Image Segmentation Techniques
- Chaos-based Image/Signal Encryption
- Retinal Imaging and Analysis
- Advanced Image Processing Techniques
- Traditional Chinese Medicine Studies
- Advanced Measurement and Detection Methods
- Simulation and Modeling Applications
- Underwater Acoustics Research
- Digital Media Forensic Detection
- Cryptographic Implementations and Security
- Cardiac Imaging and Diagnostics
- Advanced Vision and Imaging
- Advanced SAR Imaging Techniques
- Remote Sensing and Land Use
- Advanced Neural Network Applications
- Image Retrieval and Classification Techniques
Northwestern Polytechnical University
2005-2025
Tianjin University of Technology
2012
Synthetic Aperture Radar (SAR) has the characteristics of all-weather and all-time operation, which can achieve uninterrupted detection targets on sea surface. Currently, small-sized ship in SAR images are difficult to detect complex backgrounds due limited pixel information, unclear azimuth weak signals after imaging. This makes it challenging small-scale images. In this paper, we proposed an Enhanced Cascade R-CNN algorithm for detecting To enhance multi-scale expression ability network,...
<title>Abstract</title> The neural network-based differential distinguisher has attracted significant interest from researchers due to its high efficiency in cryptanalysis since introduction by Gohr 2019. However, the accuracy of existing distinguishers remains limited for high-round-reduced cryptosystems. In this work, we explore design principles networks and propose a novel based on multi-scale convolutional block dense residual connections. Two different ablation schemes are designed...
The classic Mean-Shift algorithm lacks the necessary template update, because window size remains same in tracking process, will fail when scale change, track be ineffective is faster, feature of histogram seems simple object color characteristic described aspects and space information. This paper presents a Cam-Shift clustering algorithm, regarding centroid position moving which detected as first iteration input frame, narrowing visual search range, shortening matching time. Through update...