Abstract
An eye disease screening system is an important tool for health practitioners in performing mass screening tests at a low cost. Thus, the system is usually built for a mobile platform where the form factor is small and easily dispatched to rural areas. The system is also expected to perform automated decision-making with the help of the state-of-the-art intelligent artificial intelligence system. Hence, MobileNet V3 is an optimized convolutional neural network, which has been designed specifically for mobile applications. It consists of a stack of expansion modules that have been embedded with squeeze and excitation units. However, the network does not have dedicated multi-scale feature extraction functions to cater to objects of interest of various sizes. Therefore, a set of parallel atrous convolution with multiple dilation rates has been integrated into the original network to further improve classification accuracy. The results show that a set of atrous convolution with a maximum dilation rate of 4 produces the best accuracy of 0.719.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zulkifley, M.A., Abdani, S.R., Zulkifley, N.H.: Pterygium-Net: a deep learning approach to pterygium detection and localization. Multimedia Tools Appl. 78, 34563–34584 (2019). https://doi.org/10.1007/s11042-019-08130-x
Mohamed, N.A., Zulkifley, M.A., Hussain, A.: On analyzing various density functions of local binary patterns for optic disc segmentation. In: 2015 IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE), pp. 37–41. IEEE (2015)
Playout, C., Duval, R., Cheriet, F.: A novel weakly supervised multitask architecture for retinal lesions segmentation on fundus images. IEEE Trans. Med. Imaging 38(10), 2434–2444 (2019). https://doi.org/10.1109/TMI.2019.2906319
Zhang, J., et al.: Knowledge-based automatic performance evaluation for medical training debriefing. In: 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 2180–2185 (2014). https://doi.org/10.1109/SMC.2014.6974247
Dizdaroglu, B., Corbacioglu, B.: Deep diagnosis of non-proliferative diabetic retinopathy in a mobile system. In: 2019 Medical Technologies Congress (TIPTE-KNO), pp. 1–4 (2019). https://doi.org/10.1109/TIPTEKNO.2019.8894946
Nkosi, M.T., Mekuria, F., Gejibo, S.H.: Challenges in mobile bio-sensor based mhealth development. In: 2011 IEEE 13th International Conference on e-Health Networking, Applications and Services, pp. 21–27 (2011). https://doi.org/10.1109/HEALTH.2011.6026750
Howard, A., et al.: Searching for MobileNetV3. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 1314–1324 (2019)
Zulkifley, M., Rawlinson, D., Moran, B.: Robust observation detection for single object tracking: deterministic and probabilistic patch-based approaches. Sensors 12(11), 15638–15670 (2012)
Zulkifley, M.A.: Robust single object tracker based on kernelled patch of a fixed RGB camera. Optik 127(3), 1100–1110 (2016). https://doi.org/10.1016/j.ijleo.2015.10.130. http://www.sciencedirect.com/science/article/pii/ S0030402615014989
Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. CoRR abs/1704.04861 (2017). http://arxiv.org/abs/1704.04861
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.: MobileNetV2: inverted residuals and linear bottlenecks. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)
Iandola, F.N., Moskewicz, M.W., Ashraf, K., Han, S., Dally, W.J., Keutzer, K.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size. CoRR abs/1602.07360 (2016). http://arxiv.org/abs/1602.07360
Zhang, X., Zhou, X., Lin, M., Sun, J.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6848–6856 (2018)
Ma, N., Zhang, X., Zheng, H.T., Sun, J.: ShuffleNet V2: practical guidelines for efficient CNN architecture design. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11218, pp. 116–131. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01264-9_8
Zulkifley, M.A., Abdani, S.R., Zulkifley, N.H.: Covid-19 screening using a lightweight convolutional neural network with generative adversarial network data augmentation. Symmetry 12(9), 1530 (2020)
Zulkifley, M.A., Abdani, S.R., Zulkifley, N.H.: Automated bone age assessment with image registration using hand X-ray images. Appl. Sci. 10(20), 7233 (2020)
Holm, S., Russell, G., Nourrit, V., McLoughlin, N.: DR HAGIS-a fundus image database for the automaticextraction of retinal surface vessels from diabetic patients. J. Med. Imaging (Bellingham) 4(1), 014503 (2017)
Nayak, J., Bhat, P.S., Acharya, R., Lim, C.M., Kagathi, M.: Automated identification of diabetic retinopa thy stages using digital fundus images. J. Med. Syst. 32(2), 107–115 (2008)
Baidu Research Open-Access Dataset: Baidu Research Open-Access Dataset, Baidu. http://ai.baidu.com/broad/introduction
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the 3rd International Conference on Learning Representations (2014)
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on Imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026–1034 (2015)
Acknowledgments
The authors would like to acknowledge funding from Ministry of Education Malaysia (Fundamental Research Grant Scheme: FRGS/1/2019/ICT02/UKM/02/1) and Universiti Kebangsaan Malaysia (Geran Universiti Penyelidikan: GUP-2019-008).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Abdani, S.R., Zulkifley, M.A., Kamari, N.A.M., Moubark, A.M. (2022). Optimal Selection of Parallel Atrous Convolutions for MobileNet V3. In: Mahyuddin, N.M., Mat Noor, N.R., Mat Sakim, H.A. (eds) Proceedings of the 11th International Conference on Robotics, Vision, Signal Processing and Power Applications. Lecture Notes in Electrical Engineering, vol 829. Springer, Singapore. https://doi.org/10.1007/978-981-16-8129-5_150
Download citation
DOI: https://doi.org/10.1007/978-981-16-8129-5_150
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-8128-8
Online ISBN: 978-981-16-8129-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)