Authors :
Tobi Makinde
Volume/Issue :
Volume 9 - 2024, Issue 6 - June
Google Scholar :
https://rb.gy/hod98n
Scribd :
https://rb.gy/oln0dl
DOI :
https://doi.org/10.38124/ijisrt/IJISRT24JUN1069
Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.
Abstract :
This research paper aims to investigate the idea
of object detection in PyTorch employing the most widely
known object detection and localization algorithm that
employs image segmentation techniques and deep learning
approach, which is Mask Region-based Convolutional
Neural Network. Mask R-CNN is widely used in many
fields, such as industrial and medical applications, due to its
ability to accurately identify objects and generate
segmentation masks for each instance. The Mask R-CNN
algorithm combines the region proposal generation and
object classification stages of Faster R-CNN with an
additional branch for pixel-level segmentation.
Keywords :
Convolutional Neural Network, Object Detection, Pre-trained Model, PyTorch, Object Detection, Image Preprocessing, Pandas, NumPy, Pretrained Model, Mask Region-Based Convolutional Neural Network.
References :
- Widiyanto, S., Nugroho, D. P., Daryanto, A., Yunus, M., & Wardani, D. T.. (2021, January 1). Monitoring the Growth of Tomatoes in Real Time with Deep Learning-based Image Segmentation. https://scite.ai/reports/10.14569/ijacsa.2021.0121247.
- Kim, J., Kwon, S., Fu, J., & Park, J. (2022, October 14). Hair Follicle Classification and Hair Loss Severity Estimation Using Mask R-CNN. https://scite.ai/reports/10.3390/jimaging8100283.
- Islam, M. N., & Paul, M.. (2021, October 15). Video Rain-Streaks Removal by Combining Data-Driven and Feature-Based Models. https://scite.ai/reports/10.3390/s21206856
- G. Huang, Z. Liu, L. V. D. Maaten, and K. Q. Weinberger, ‘‘Densely connected convolutional networks,’’ in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2017, pp. 2261–2269.
- Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015). Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1-9). June 2015.
- Thomas, E. A., Gerster, S., Jean, H., & Oates, T.. (2020, October 26). Computer vision supported pedestrian tracking: A demonstration on trail bridges in rural Rwanda. https://scite.ai/reports/10.1371/journal.pone.0241379
- Su, Peifeng, J. (2022, January 25). New particle formation event detection with Mask R-CNN. https://scite.ai/reports/10.5194/acp-22-1293-2022
This research paper aims to investigate the idea
of object detection in PyTorch employing the most widely
known object detection and localization algorithm that
employs image segmentation techniques and deep learning
approach, which is Mask Region-based Convolutional
Neural Network. Mask R-CNN is widely used in many
fields, such as industrial and medical applications, due to its
ability to accurately identify objects and generate
segmentation masks for each instance. The Mask R-CNN
algorithm combines the region proposal generation and
object classification stages of Faster R-CNN with an
additional branch for pixel-level segmentation.
Keywords :
Convolutional Neural Network, Object Detection, Pre-trained Model, PyTorch, Object Detection, Image Preprocessing, Pandas, NumPy, Pretrained Model, Mask Region-Based Convolutional Neural Network.