Dayvid Castro
Papers
2
Total Citations
22
H-Index
2
About
Dayvid Castro is a researcher at the intersection of computer vision, deep learning, and medical robotics. His work focuses on making neural networks more efficient and practical for real-world, resource-constrained applications. A key contribution is the development of **OctShuffleMLT**, a compact octave-based convolutional neural network designed for end-to-end multilingual text detection and recognition. This architecture addresses the challenge of deploying deep networks on hardware with limited capabilities, such as robots, achieving strong performance with reduced computational overhead. In the medical domain, Castro has pioneered the use of **optimized CNNs for robotic surgery skill evaluation**. His work aims to replace subjective, bias-prone checklist assessments with objective, automated analysis of surgical performance, directly improving training outcomes. Both of his most-cited papers, published in 2019, have each garnered **11 citations**, reflecting early impact in their respective fields. By bridging efficient model design with critical applications in robotics and healthcare, Dayvid Castro is contributing to the next generation of intelligent, deployable vision systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2