Deep Learning Algorithms and Applications in Computer Vision
DOI:
https://doi.org/10.26438/ijcse/v7i7.195201Keywords:
AI, ML, Computer Vision, DBN, CNN, RNNAbstract
Deep Learning is a system powered by huge amounts of data. With the generation of massive amounts of data, the data analysing keeps getting complex. Deep learning solves the problem of Traditional ML algorithms that fail to perform well when the amount of data is enormous. Deep learning can be applied to any type of data such as text, image and so on. Deep learning algorithms generally used and best suited for image data are DBN and CNN. Analysing Computer vision using CNN brings a lot of use cases such as detection, recognition from the images, which can be useful in many fields such as medical images to detect a tumour and recognize its type, or help a robot navigate by identifying obstacles. In this paper we discuss what is Artificial Intellignece(AI), Machine Learning(ML) and Deep Learning and explore some of the Deep learning algorithms. We also understand how CNN can be applied in different applications of Computer vision and study the three major applications of Computer vision which are Image captioning, Medical image analysis and Robots Navigation.
References
[1] T. M. Mitchell, “Machine Learning”, McGraw Hill Education; First edition, New York, USA
[2] S. Rajaraman, S. Candemir, Z. Xue, P. O. Alderson, M. Kohli, J. Abuya, G. R. Thoma, and S. Antani, “A novel stacked generalization of models for improved TB detection in chest radiographs”
[3] B. Xu, Y. Chai, C. M. Galarza, C. Q. Vu, B. Tamrazi, B. Gaonkar, L. Macyszyn, T. D. Coates, N. Lepore, and J. C. Wood, “Orchestral Fully Convolutional Networks forsmall lesion segmentation in Brain MRI”
[4] S. Shabir, S. Y. Arafat, “An image conveys a message: A brief survey on image description generation”
[5]I. Reda, B. O. Ayinde, M. Elmogy, A. Shalaby, M. El-Melegy, M. A. El-Ghar, A. A. El-fetouh, M. Ghazal, A. El-Baz, “A new CNN based system for early diagnosis of Prostate Cancer”
[6] C. C. Park, B. Kim, and G. Kim, “Towards Personalized Image Captioning via Multimodal Memory Networks”
[7] Q. Wu , C. Shen , P. Wang, A. Dick, and A. v. d. Hengel, “Captioning and Visual Question Answering Based on Attributes and External Knowledge”
[8] M. Vicky, G. Aziz, H. Hindersah, “Implementation of Vehicle Detection Algorithm for Self-Driving Car on Toll Road Cipularang using Python Language”
[9] C. Lin, J. Lu, J. Zhou, “Multi-Grained deep feature Learning for Pedestrian detection”
[10] S. Hussain, M. Abualkibash, S. Tout, “A of Traffic Sign Recognition Systems Based on Convolutional Neural Networks”
[11] C. Amritkar, V. Jabade, “Image Caption Generation using Deep Learning Technique”
[12] S. Shabir, S. Y. Arafat, “An image conveys a message: A brief survey on image description generation”
[13] Boya Akhila, Burgubai Jyothi, “Face Identification through Learned Image High Feature Video Frame Works”
[14] N.S. Lele, “Image Classification Using Convolutional Neural Network”.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
