Abstract
Deep learning has gained a lot of prominence in the past few years, with it even taking precedence over other learning techniques quite significantly. The use of computer vision is a very good example of its widespread application. As the amount of data generated becomes more, the complexity of the analysis also increases. This is the ideal application of the Deep Learning Method and it is known to outperform other traditional Machine Learning algorithms by quite some margins as the latter has issues in dealing with high-volume data. The specialty of deep learning is that it is applicable for texts as well as image data alike. Two important algorithms of deep learning that have multiple utilities are Convolutional Neural Network and Deep Belief Network. By using a Convolutional Neural Network, one can extract information from images by detection and recognition. It can be used in the medical science field by locating out tumors accurately and identifying its type and using robots for navigation by locating the hurdles. The main aim of this review paper is to provide a brief about the deep learning methods used. It includes a description of their structure, functioning, and limitation and also includes their utility in computer vision like for object identification, human face, and activity recognition etcetera. In the end, a brief description of the future usage of it and how the newer challenges can be dealt with is shared here.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Amritkar, C., Jabade, V.: Image caption generation using deep learning technique. Fourth Int. Conf. Comput. Commun. Control Autom. (ICCUBEA) 2018, 1–4 (2018)
Dargan, S., Kumar, M., Ayyagari, M.R., Kumar, G.: A survey of deep learning and its applications: a new paradigm to machine learning. Arch. Comput. Methods Eng. 27(4), 1071–1092 (2019). https://doi.org/10.1007/s11831-019-09344-w
Hassaballah, M., Awad, A.I.: Deep Learning in Computer Vision: Principles and Applications. CRC Press, Boca Raton (2020). https://doi.org/10.1201/9781351003827
Kaushal, M., Khehra, B., Sharma, A.: Soft computing based object detection and tracking approaches: state-of-the-art survey. Appl. Soft. Comput. 70, 423–464 (2018)
Kautz, T., Groh, B., Hannink, J., Jensen, U., Strubberg, H., Eskofer, B.: Activity recognition in beach volleyball using a DEEp Convolutional Neural NETwork: leveraging the potential of DEEp Learning in sports. Data Min. Knowl. Disc. 31(6), 1678–1705 (2018)
Patel, P., Thakkar, A.: The upsurge of deep learning for computer vision applications. Int. J. Electr. Comput. Eng. (IJECE) 10(1), 538–548 (2020)
Reda, I., et al.: A new CNN-based system for early diagnosis of prostate cancer. In: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)
Shetty, S.K., Siddiqa, A.: Deep learning algorithms and applications in computer vision. Int. J. Comput. Sci. Eng. 7(7), 195–201 (2019)
Vicky, M., Aziz, G., Hindersah, H., Prihatmanto, A.: Implementation of vehicle detection algorithm for self-driving car on toll road cipularang using Python language. In: 2017 4th International Conference on Electric Vehicular Technology (ICEVT)
Voulodimos, A., Doulamis, N., Doulamis, A., Protopapadakis, E.: Deep learning for computer vision: a brief review. Comput. Intell. Neurosci. 2018, 1–13 (2018). https://doi.org/10.1155/2018/7068349
Wu, Q., Shen, C., Wang, P., Dick, A., Hengel, A.: Image captioning and visual question answering based on attributes and external knowledge. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1367–1381 (2018)
Xu, B., et al.: Orchestral fully convolutional networks forsmall lesion segmentation in brain MRI. In: Proceeding of IEEE International Symposium on Biomedical Imaging, pp. 889–892 (2018)
Zhao, C., Chen, K., Wei, Z., Chen, Y., Miao, D., Wang, W.: Multilevel triplet deep learning model for person re-identification. Pattern Recogn. Lett. 117, 161–168 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Singh, C. (2021). Applications and Challenges of Deep Learning in Computer Vision. In: Siuly, S., Wang, H., Chen, L., Guo, Y., Xing, C. (eds) Health Information Science. HIS 2021. Lecture Notes in Computer Science(), vol 13079. Springer, Cham. https://doi.org/10.1007/978-3-030-90885-0_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-90885-0_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-90884-3
Online ISBN: 978-3-030-90885-0
eBook Packages: Computer ScienceComputer Science (R0)