PhD defence
From Pixels to Patterns: AI-Driven Image Analysis in Multiple Domains
- S. Javanmardi
- Date
- Wednesday 18 September 2024
- Time
- Location
-
Academy Building
Rapenburg 73
2311 GJ Leiden
Supervisor(s)
- Prof.dr. Ir. F. J. Verbeek
- Prof.dr. M. Bonsangue
Summary
This thesis explores the application of deep learning techniques in image analysis across various domains, focusing on feature extraction, classification, segmentation, and integration. It demonstrates how these technologies can significantly advance agricultural biotechnology, biomedicine, and digital media. The first part of the research develops deep Convolutional Neural Networks (CNNs) to improve the accuracy and efficiency of corn seed classification, automating processes traditionally reliant on simpler vision techniques and manual post-processing. The second part applies these networks to classify the ripeness stages of mulberries, enhancing sorting accuracy and potentially increasing economic value by eliminating the need for specialist assessments. The third theme investigates the use of CNNs for segmenting microscope images, particularly zebrafish larvae in high-throughput settings, supporting rapid screening and detailed biological analyses. The final section integrates image processing with Natural Language Processing (NLP) to create accurate, context-aware captions for images, beneficial across various fields including surveillance and healthcare. Overall, the thesis sets new benchmarks in the respective domains, illustrating the transformative potential of deep learning in enhancing image analysis, with broad implications for future research and practical applications in multiple industries.
PhD dissertations
Approximately one week after the defence, PhD dissertations by Leiden PhD students are available digitally through the Leiden Repository, that offers free access to these PhD dissertations. Please note that in some cases a dissertation may be under embargo temporarily and access to its full-text version will only be granted later.
Press enquiries (journalists only)
+31 (0)71 527 1521
nieuws@leidenuniv.nl
General information
Beadle's Office
pedel@bb.leidenuniv.nl
+31 71 527 7211