B
Byron L. D. Bezerra
Researcher at Universidade de Pernambuco
Publications - 67
Citations - 491
Byron L. D. Bezerra is an academic researcher from Universidade de Pernambuco. The author has contributed to research in topics: Recommender system & Image segmentation. The author has an hindex of 10, co-authored 64 publications receiving 363 citations. Previous affiliations of Byron L. D. Bezerra include Federal University of Pernambuco.
Papers
More filters
Journal ArticleDOI
A dynamic gesture recognition and prediction system using the convexity approach
Pablo Barros,Nestor T. Maciel-Junior,Bruno J. T. Fernandes,Byron L. D. Bezerra,Sergio Murilo Maciel Fernandes +4 more
TL;DR: This study proposes a system for dynamic gesture recognition and prediction using an innovative feature extraction technique, called the Convexity Approach, which generates a smaller feature vector to describe the hand shape with a minimal amount of data.
Proceedings ArticleDOI
A KNN-SVM hybrid model for cursive handwriting recognition
TL;DR: The hybrid MLP-SVM recognizer showed improvement, significant, in performance in terms of recognition rate compared with an MLP for a task of character recognition.
Journal ArticleDOI
A symbolic approach for content-based information filtering
TL;DR: This paper presents an approach through which each user profile is modelled using a set of modal symbolic descriptions that summarize the information taken from aSet of items the user has previously evaluated.
Proceedings ArticleDOI
Boosting the Deep Multidimensional Long-Short-Term Memory Network for Handwritten Recognition Systems
TL;DR: This paper proposes a handwriting recognition system based on a deep multidimensional long-short-term memory (MDLSTM) network within a hybrid hidden Markov model framework and investigates the trade-off between both these properties to obtain an optimal topology.
Journal ArticleDOI
Symbolic data analysis tools for recommendation systems
TL;DR: In these methods, the user profile is built up through symbolic data structures and the user and item correlations are computed through dissimilarity functions adapted from the symbolic data analysis (SDA) domain.