What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Algorithm
Horst Bunke focuses on Artificial intelligence, Pattern recognition, Speech recognition, Hidden Markov model and Handwriting recognition.
His Artificial intelligence research is multidisciplinary, relying on both Graph operations and Natural language processing.
His studies deal with areas such as Lattice graph, Data mining and Cluster analysis as well as Pattern recognition.
Horst Bunke has researched Speech recognition in several fields, including Optical character recognition, Word recognition, Handwriting, Whiteboard and Intelligent character recognition.
His research integrates issues of Language model, Word and Markov model in his study of Hidden Markov model.
Horst Bunke combines subjects such as Recurrent neural network and Spotting with his study of Handwriting recognition.
His most cited work include:
- A Novel Connectionist System for Unconstrained Handwriting Recognition (1243 citations)
- The IAM-database: an English sentence database for offline handwriting recognition (874 citations)
- An experimental comparison of range image segmentation algorithms (754 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of study are Artificial intelligence, Pattern recognition, Speech recognition, Handwriting recognition and Hidden Markov model.
His Artificial intelligence research focuses on subjects like Natural language processing, which are linked to Word.
His Pattern recognition research is multidisciplinary, incorporating elements of Feature, Edit distance and Cluster analysis.
The study incorporates disciplines such as Wagner–Fischer algorithm, Graph, Line graph and Matching in addition to Edit distance.
He focuses mostly in the field of Speech recognition, narrowing it down to topics relating to Intelligent character recognition and, in certain cases, Signature recognition.
His Handwriting recognition research includes themes of Artificial neural network, Recurrent neural network and Transcription.
He most often published in these fields:
- Artificial intelligence (61.43%)
- Pattern recognition (33.04%)
- Speech recognition (20.71%)
What were the highlights of his more recent work (between 2010-2020)?
- Artificial intelligence (61.43%)
- Pattern recognition (33.04%)
- Line graph (9.46%)
In recent papers he was focusing on the following fields of study:
Horst Bunke spends much of his time researching Artificial intelligence, Pattern recognition, Line graph, Theoretical computer science and Edit distance.
His work deals with themes such as Speech recognition and Natural language processing, which intersect with Artificial intelligence.
His research in Pattern recognition intersects with topics in Data mining and Graph embedding.
He interconnects Matching, Computational complexity theory and Pairwise comparison in the investigation of issues within Theoretical computer science.
His work in Hidden Markov model addresses issues such as Feature extraction, which are connected to fields such as Image segmentation.
His study in Handwriting recognition is interdisciplinary in nature, drawing from both Semi-supervised learning, Machine learning, Language model, Handwriting and Intelligent character recognition.
Between 2010 and 2020, his most popular works were:
- A Novel Word Spotting Method Based on Recurrent Neural Networks (231 citations)
- Lexicon-free handwritten word spotting using character HMMs (218 citations)
- Recent advances in graph-based pattern recognition with applications in document analysis (120 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Algorithm
Horst Bunke mostly deals with Artificial intelligence, Handwriting recognition, Speech recognition, Pattern recognition and Hidden Markov model.
His biological study deals with issues like Machine learning, which deal with fields such as Existential quantification.
His work carried out in the field of Handwriting recognition brings together such families of science as Edit distance, Time complexity, Blossom algorithm, Hungarian algorithm and Hausdorff distance.
The Speech recognition study combines topics in areas such as Artificial neural network, Recurrent neural network, Intelligent character recognition and Transcription.
His biological study spans a wide range of topics, including Salient, Contextual image classification, Graph embedding, Vector space and Selection method.
The concepts of his Hidden Markov model study are interwoven with issues in Language model and Natural language processing.
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.
