Deep learning approaches for ctenophore identification and tracking

Author

• Anagha Bharadwaj, New Jersey Institute of TechnologyFollow

Document Type

Thesis

Date of Award

5-31-2026

Degree Name

Master of Science in Computer Science - (M.S.)

Department

Computer Science

First Advisor

Akshay Rangamani

Second Advisor

Allison Edgar

Third Advisor

Guiling Wang

Abstract

Ctenophores are translucent marine organisms with nearly invisible tentacles and pose significant challenges due to their transparent morphology and ambiguous structural features. This research addresses the classification and tracking of these organisms and evaluates the performance of current computer vision models under sparse-data environments.

A dataset from the NJIT Life History Lab consisting of microscopic laboratory videos and photographs of different growth stages is used to train and assess a number of convolutional neural network designs, including VGG16, ResNet, BioCLIP2, YOLO, and DeepLabCut. Additionally, a web-based interface is developed to evaluate expert-labeled ground truth with the model's performance.

The findings demonstrate that existing computer vision frameworks are in moderate agreement with expert assessments which is inadequate for dependable automated analysis of ctenophores. Improvement in performance and accuracy requires larger datasets along with models specifically designed for translucent marine organisms.

Recommended Citation

Bharadwaj, Anagha, "Deep learning approaches for ctenophore identification and tracking" (2026). Theses. 3547.
https://digitalcommons.njit.edu/theses/3547