What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Algorithm
- Computer vision
Huazhong Shu spends much of his time researching Artificial intelligence, Computer vision, Velocity Moments, Algorithm and Robustness.
His Artificial intelligence study incorporates themes from Quaternion and Pattern recognition.
In his study, which falls under the umbrella issue of Pattern recognition, Iterative reconstruction is strongly linked to Image processing.
His work deals with themes such as Deep learning and Streak, which intersect with Computer vision.
The Computational complexity theory research Huazhong Shu does as part of his general Algorithm study is frequently linked to other disciplines of science, such as Electronic mail, therefore creating a link between diverse domains of science.
Huazhong Shu combines subjects such as Watermark, Legendre polynomials, Mathematical optimization and Digital watermarking with his study of Robustness.
His most cited work include:
- Color Image Analysis by Quaternion-Type Moments (202 citations)
- Artifact suppressed dictionary learning for low-dose CT image processing. (199 citations)
- Image analysis by discrete orthogonal Racah moments (140 citations)
What are the main themes of his work throughout his whole career to date?
The scientist’s investigation covers issues in Artificial intelligence, Algorithm, Computer vision, Pattern recognition and Iterative reconstruction.
Deep learning, Segmentation, Image processing, Robustness and Feature extraction are the primary areas of interest in his Artificial intelligence study.
In his research, Legendre polynomials is intimately related to Velocity Moments, which falls under the overarching field of Algorithm.
His work in Computer vision addresses issues such as Quaternion, which are connected to fields such as Color image.
His Pattern recognition study also includes fields such as
- Feature that connect with fields like Discriminative model,
- Image quality, which have a strong connection to Streak.
The concepts of his Iterative reconstruction study are interwoven with issues in Iterative method, Projection, Computed tomography and Regularization.
He most often published in these fields:
- Artificial intelligence (53.85%)
- Algorithm (35.66%)
- Computer vision (29.72%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (53.85%)
- Segmentation (12.24%)
- Deep learning (10.84%)
In recent papers he was focusing on the following fields of study:
His primary areas of investigation include Artificial intelligence, Segmentation, Deep learning, Pattern recognition and Algorithm.
The Artificial intelligence study combines topics in areas such as Weighting, Computer vision and Code.
Computer vision is closely attributed to Structure in his work.
His Deep learning research incorporates elements of Feature extraction and Grayscale.
He has researched Pattern recognition in several fields, including Image quality, Representation and Feature.
A large part of his Algorithm studies is devoted to Tree structure.
Between 2019 and 2021, his most popular works were:
- Deep octonion networks (6 citations)
- Deep octonion networks (6 citations)
- Compressed sensing MR image reconstruction via a deep frequency-division network (5 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Algorithm
- Machine learning
His main research concerns Artificial intelligence, Field, Artificial neural network, Segmentation and Mixture model.
As part of his studies on Artificial intelligence, Huazhong Shu often connects relevant subjects like Pattern recognition.
His research integrates issues of Weighting, Face, Iterative reconstruction and Compressed sensing in his study of Pattern recognition.
His work carried out in the field of Artificial neural network brings together such families of science as Image quality, Quaternion and Theoretical computer science.
The various areas that Huazhong Shu examines in his Segmentation study include Tree, Autoencoder, Feature and Anatomy.
His research in Mixture model intersects with topics in Line search, Maximization, Conjugate gradient method and Expectation–maximization algorithm.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
