What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Statistics
- Machine learning
His main research concerns Artificial intelligence, Algorithm, Computer vision, Pattern recognition and Point set registration.
The Algorithm study combines topics in areas such as Correspondence problem, Outlier, Robustness and Relaxation.
His Outlier research integrates issues from Point and Spline.
His work in Computer vision addresses issues such as Mutual information, which are connected to fields such as Entropy, Density estimation and Joint probability distribution.
Anand Rangarajan interconnects Higher-order singular value decomposition, Image retrieval, Geometric alignment and Maximum a posteriori estimation in the investigation of issues within Pattern recognition.
His work carried out in the field of Point set registration brings together such families of science as Feature and Affine transformation.
His most cited work include:
- A new point matching algorithm for non-rigid registration (1305 citations)
- A graduated assignment algorithm for graph matching (1012 citations)
- The concave-convex procedure (921 citations)
What are the main themes of his work throughout his whole career to date?
Anand Rangarajan mostly deals with Artificial intelligence, Algorithm, Pattern recognition, Computer vision and Mathematical optimization.
His Algorithm research includes elements of Point, Point set registration, Iterative reconstruction and Outlier.
His study looks at the intersection of Iterative reconstruction and topics like Prior probability with Piecewise.
His research investigates the connection with Pattern recognition and areas like Cluster analysis which intersect with concerns in Diffeomorphism.
He mostly deals with Image processing in his studies of Computer vision.
His study in Mathematical optimization is interdisciplinary in nature, drawing from both Monotonic function, Applied mathematics and Maxima and minima.
He most often published in these fields:
- Artificial intelligence (51.20%)
- Algorithm (30.00%)
- Pattern recognition (28.40%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (51.20%)
- Pattern recognition (28.40%)
- Computer vision (21.60%)
In recent papers he was focusing on the following fields of study:
His primary areas of investigation include Artificial intelligence, Pattern recognition, Computer vision, Convolutional neural network and Deep learning.
His Artificial intelligence research is multidisciplinary, relying on both Machine learning, Overhead and Trailer.
His Pattern recognition study frequently draws parallels with other fields, such as Conditional probability distribution.
The Object research Anand Rangarajan does as part of his general Computer vision study is frequently linked to other disciplines of science, such as Near miss, therefore creating a link between diverse domains of science.
The various areas that he examines in his Convolutional neural network study include Transfer of learning, Laplacian matrix and Feature selection.
His Deep learning research includes themes of Point cloud, Asynchronous communication and Parallel computing.
Between 2017 and 2021, his most popular works were:
- A Gaussian Mixture Model Representation of Endmember Variability in Hyperspectral Unmixing. (42 citations)
- Visual Explanations From Deep 3D Convolutional Neural Networks for Alzheimer's Disease Classification. (33 citations)
- Global Model Interpretation Via Recursive Partitioning (14 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Machine learning
The scientist’s investigation covers issues in Artificial intelligence, Pattern recognition, Pixel, Segmentation and Convolutional neural network.
His Artificial intelligence study deals with Computer vision intersecting with Transformation.
His biological study spans a wide range of topics, including Conditional probability distribution, Maximum a posteriori estimation and Expectation–maximization algorithm.
His work deals with themes such as Downscaling, Random variable and Synthetic data, which intersect with Pixel.
His research integrates issues of Optical flow, Visualization and Benchmark in his study of Segmentation.
His studies in Convolutional neural network integrate themes in fields like Overhead, Leverage, Video tracking, Object detection and Frame rate.
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.
