Theses and Dissertations
ORCID
https://orcid.org/0009-0000-4220-7905
Issuing Body
Mississippi State University
Advisor
Samiappan, Sathishkumar
Committee Member
Gudla, Charan
Committee Member
Zhang, Jialin (JZ)
Committee Member
Chen, Jingdao
Date of Degree
12-13-2024
Original embargo terms
Visible MSU only 1 year
Document Type
Graduate Thesis - Campus Access Only
Major
Computer Science (Research)
Degree Name
Master of Science (M.S.)
College
James Worth Bagley College of Engineering
Department
Department of Computer Science and Engineering
Abstract
This thesis explores the use of Deep learning for detection and classification of small foreign materials (FMs) in poultry meat using color and hyperspectral imagery (HSI). The study employs You only look once (YOLO) object detection models on color images for precise localization, and one-dimensional convolutional neural network (1D CNN), two-dimensional convolutional neural network (2D CNN) was used on HSI (600 – 1700 nm) for classification. Twelve different FMs commonly known as polymers including PVC, PET, LDPE and HDPE, were examined using 52 color and 52 hyperspectral images. Four YOLO models (v5x, v7x, v8x, v10x) were implemented, trained, tested and the performance was evaluated using F1 score, precision – recall curve and mean Average Precision (mAP@0.50). This study determined that YOLOv7x, v10x were most reliable for detection, while 1D CNN showed best balance between accuracy and generalization in classification.
Recommended Citation
Maram, Rohini, "Deep learning - based automated detection and classification of foreign materials in poultry using color and hyperspectral imaging" (2024). Theses and Dissertations. 6433.
https://scholarsjunction.msstate.edu/td/6433