Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Object Detection and Size Determination of Pineapple Fruit at a Juicing Factory
The aim of this thesis is to develop a method for determining pineapple fruit size from images. This was achieved by first detecting pineapples in each image using Mask Region-based Convolutional Neural Network (Mask R-CNN) and then extracting the pixel diameter and length measurements, and the proj...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
Department of Statistical Sciences
2022
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613489048059904 |
|---|---|
| access_status_str | Open Access |
| author | Harris, Jessica |
| author2 | Er, Sebnem |
| author_browse | Er, Sebnem Harris, Jessica |
| author_facet | Er, Sebnem Harris, Jessica |
| author_sort | Harris, Jessica |
| collection | Thesis |
| description | The aim of this thesis is to develop a method for determining pineapple fruit size from images. This was achieved by first detecting pineapples in each image using Mask Region-based Convolutional Neural Network (Mask R-CNN) and then extracting the pixel diameter and length measurements, and the projected areas, from the detected mask outputs. Various Mask R-CNNs were considered for the task of pineapple detection. The best-performing detector made use of MS COCO starting weights, a ResNet50 CNN backbone, and horizontal flipping data augmentation during the training process. This model (Model 4: COCO Fliplr Res50) achieved an average precision of 91.4% on the validation set and an average precision of 90.1% on the test set, and was used to predict masks for an unseen dataset containing images of pre-measured pineapples. The distributions of measurements extracted from the detected masks were compared to those of the manual measurements using two-sample Z-tests and Kolmogorov–Smirnov (KS) tests. There was sufficient similarity between the distributions, and it was therefore established that the reported method is appropriate for pineapple size determination in this context. All the data and code is available in a GitHub repository for reproducible research. |
| format | Thesis |
| id | oai:open.uct.ac.za:11427/35596 |
| institution | University of Cape Town (South Africa) |
| language | eng |
| last_indexed | 2026-06-10T12:36:57.479Z |
| license_str | Not specified — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from UCTD — University of Cape Town Open Access Repository |
| publishDate | 2022 |
| publishDateRange | 2022 |
| publishDateSort | 2022 |
| publisher | Department of Statistical Sciences |
| publisherStr | Department of Statistical Sciences |
| record_format | dspace |
| source_str | UCTD — University of Cape Town Open Access Repository |
| spelling | oai:open.uct.ac.za:11427/35596 Object Detection and Size Determination of Pineapple Fruit at a Juicing Factory Harris, Jessica Er, Sebnem Statistical Sciences The aim of this thesis is to develop a method for determining pineapple fruit size from images. This was achieved by first detecting pineapples in each image using Mask Region-based Convolutional Neural Network (Mask R-CNN) and then extracting the pixel diameter and length measurements, and the projected areas, from the detected mask outputs. Various Mask R-CNNs were considered for the task of pineapple detection. The best-performing detector made use of MS COCO starting weights, a ResNet50 CNN backbone, and horizontal flipping data augmentation during the training process. This model (Model 4: COCO Fliplr Res50) achieved an average precision of 91.4% on the validation set and an average precision of 90.1% on the test set, and was used to predict masks for an unseen dataset containing images of pre-measured pineapples. The distributions of measurements extracted from the detected masks were compared to those of the manual measurements using two-sample Z-tests and Kolmogorov–Smirnov (KS) tests. There was sufficient similarity between the distributions, and it was therefore established that the reported method is appropriate for pineapple size determination in this context. All the data and code is available in a GitHub repository for reproducible research. 2022-01-27T07:58:04Z 2022-01-27T07:58:04Z 2021 2022-01-26T13:36:37Z Master Thesis Masters MSc http://hdl.handle.net/11427/35596 eng application/pdf Department of Statistical Sciences Faculty of Science |
| spellingShingle | Statistical Sciences Harris, Jessica Object Detection and Size Determination of Pineapple Fruit at a Juicing Factory |
| thesis_degree_str | Master's |
| title | Object Detection and Size Determination of Pineapple Fruit at a Juicing Factory |
| title_full | Object Detection and Size Determination of Pineapple Fruit at a Juicing Factory |
| title_fullStr | Object Detection and Size Determination of Pineapple Fruit at a Juicing Factory |
| title_full_unstemmed | Object Detection and Size Determination of Pineapple Fruit at a Juicing Factory |
| title_short | Object Detection and Size Determination of Pineapple Fruit at a Juicing Factory |
| title_sort | object detection and size determination of pineapple fruit at a juicing factory |
| topic | Statistical Sciences |
| url | http://hdl.handle.net/11427/35596 |
| work_keys_str_mv | AT harrisjessica objectdetectionandsizedeterminationofpineapplefruitatajuicingfactory |