Logo image
High-precision groundfish length measurement and species identification: a thesis in Computer Science
Thesis   Open access

High-precision groundfish length measurement and species identification: a thesis in Computer Science

Nandini Lokesh Reddy
Master of Science (MS), University of Massachusetts Dartmouth
2024
DOI:
https://doi.org/10.62791/20355

Abstract

The fish processing industry has traditionally relied on manual methods for determining the type and size of fish, a process that is both labor-intensive and time-consuming. Recognizing this significant challenge, this thesis explores the application of advanced computer vision techniques to automate and enhance groundfish length measurement and species identification. For precise length measurement, this thesis employs Segment Anything Model (SAM) and several image processing methods, including skeletonization, convex hull, erosion, and dilation. Additionally, this work implements transformer models for groundfish species identification, achieving a remarkable accuracy of 94%, surpassing previous efforts that utilized the YOLOv8 model on the self-collected dataset. This integrated approach represents a substantial advancement in automating fish processing, significantly improving both efficiency and accuracy. The findings demonstrate the potential of transformer models and advanced computer vision techniques to revolutionize the fish processing industry.
pdf
Lokesh Reddy N. COE MS Thesis 20246.75 MBDownloadView
CC BY-NC-ND V4.0 Open Access

Metrics

12 File views/ downloads
21 Record Views

Details

Logo image