Juan P. Martinez-Esteso

Juan P. Martinez-Esteso

Auto-generated profile, based on publicly available information

Juan P. Martinez-Esteso

University of Alicante

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 November 2024 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Open access
JMJuan P. Martinez-Esteso
Juan P. Martinez-Esteso
FRFrancisco José Castellanos Regalado
Francisco José Castellanos Regalado
ARAdrian Rosello
Adrian Rosello
JCJorge Calvo-Zaragoza
Jorge Calvo-Zaragoza
Antonio Javier Gallego SánchezAntonio Javier Gallego Sánchez
Antonio Javier Gallego Sánchez

20 June 2025 in International Journal on Document Analysis and Recognition (IJDAR)
Verified
Journal Article
Open access
PDF file
SOSamuel B. Oliva-Bulpitt
Samuel B. Oliva-Bulpitt
JMJuan P. Martinez-Esteso
Juan P. Martinez-Esteso
AGAlejandro Galan-Cuenca
Alejandro Galan-Cuenca
FRFrancisco José Castellanos Regalado
Francisco José Castellanos Regalado
Antonio Javier Gallego SánchezAntonio Javier Gallego Sánchez
Antonio Javier Gallego Sánchez
Layout Analysis (LA) is a critical process for detecting and isolating different components within a scanned document, allowing for more straightforward and precise processing of each part independently. In Optical Music Recognition (OMR), LA is essential for identifying and extracting music staves, which enables effective music notation recognition and processing. While the literature includes several studies exploring methods for staff retrieval, there remains room for improvement in terms of robustness and accuracy. In this work, we introduce a methodology that integrates Monte Carlo Dropout (MCD) into a neural network model in order to improve reliability in staff retrieval from scanned sheet music. Our approach leverages multiple non-deterministic predictions using standard dropout layers during inference and aggregates them through pixel-level combination policies. We extend the MCD technique, originally designed for classification and regression tasks using averaged predictions, to the LA task and introduce new combination strategies: maximum and voting criteria. Experiments on three diverse music score corpora, including printed and handwritten documents, demonstrated the effectiveness of our approach. The averaging and voting (with 25% and 50% of votes) criteria reduced the relative error by 63.6% compared to the baseline and achieved a 32.1% improvement over state-of-the-art methods. Our methodology notably enhanced detection accuracy without requiring modifications to the neural architecture, especially at the edges of staves, where conventional models tend to show higher error rates.

16 December 2025 in Expert Systems with Applications
Verified
Journal Article
Open access
JMJuan P. Martinez-Esteso
Juan P. Martinez-Esteso
FRFrancisco José Castellanos Regalado
Francisco José Castellanos Regalado
Antonio Javier Gallego SánchezAntonio Javier Gallego Sánchez
Antonio Javier Gallego Sánchez

25 June 2023
Verified
Book Chapter
Closed access
PDF file
ARAdrian Rosello
Adrian Rosello
FRFrancisco José Castellanos Regalado
Francisco José Castellanos Regalado
JMJuan P. Martinez-Esteso
Juan P. Martinez-Esteso
Antonio Javier Gallego SánchezAntonio Javier Gallego Sánchez
Antonio Javier Gallego Sánchez
JCJorge Calvo-Zaragoza
Jorge Calvo-Zaragoza

11 September 2024
Verified
Book Chapter
Closed access
PDF file
FRFrancisco José Castellanos Regalado
Francisco José Castellanos Regalado
JMJuan P. Martinez-Esteso
Juan P. Martinez-Esteso
AGAlejandro Galán-Cuenca
Alejandro Galán-Cuenca
Antonio Javier Gallego SánchezAntonio Javier Gallego Sánchez
Antonio Javier Gallego Sánchez

9 May 2026
Verified
Book Chapter
Closed access
FRFrancisco José Castellanos Regalado
Francisco José Castellanos Regalado
JMJuan P. Martinez-Esteso
Juan P. Martinez-Esteso
AGAlejandro Galan-Cuenca
Alejandro Galan-Cuenca
Antonio Javier Gallego SánchezAntonio Javier Gallego Sánchez
Antonio Javier Gallego Sánchez