Abstract
For polyp detection, we adapt a Faster R-CNN (Ren et al. 2015) architecture shown in Fig. 11.1. Faster R-CNN has two stages: region proposal network (RPN), and a box classifier network. Both stages share a common set of convolutional layers as a feature extractor to reduce the marginal cost for detection. The RPN utilizes feature maps of the last convolutional layer to generate class-agnostic RoI proposals called anchors, each with an objectness confidence value. The anchors have different aspect ratios and scales. The classifier network crops these anchors from the feature maps of the last convolutional layer and feeds the cropped features to the remainder of the network in order to predict location and confidence values of the object class (polyps).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
He, K., Gkioxari, G., Dollár, P., & Girshick, R. (2017). Mask r-cnn.
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 770–778).
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014). Microsoft coco: Common objects in context. In European Conference on Computer Vision (pp. 740–755). Springer.
Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems (pp. 91–99).
Su, J., Vargas, D. V., & Sakurai, K. (2019). One pixel attack for fooling deep neural networks. IEEE Transactions on Evolutionary Computation.
Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. A. (2017). Inception-v4, inception-resnet and the impact of residual connections on learning. In Thirty-First AAAI Conference on Artificial Intelligence.
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 (pp. 1–9).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Qadir, H.A., Balasingham, I., Shin, Y. (2021). Region-Based Convolutional Neural Network for Polyp Detection and Segmentation. In: Bernal, J., Histace, A. (eds) Computer-Aided Analysis of Gastrointestinal Videos. Springer, Cham. https://doi.org/10.1007/978-3-030-64340-9_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-64340-9_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-64339-3
Online ISBN: 978-3-030-64340-9
eBook Packages: Computer ScienceComputer Science (R0)