Blood Content Prediction using Deep Learning Techniques
N.R. P. Nivetha1, C. P.Moulya2, A.RumanaParveen3, R.Narmatha Shree4, S.Ragupathy5
1Ms. N. R. P. Nivetha*, Assistant Professor, Sri Krishna college of Technology, Coimbatore, India.
2Ms. C. P. Moulya, Department of CSE, Sri Krishna College of Technology, Coimbatore, Tamil Nadu, India.
3Ms. A. Rumana Parveen, Department of CSE, Sri Krishna College of Technology, Coimbatore, Tamil Nadu, India.
4Ms. R. Narmatha Shree, Department of CSE, Sri Krishna College of Technology, Coimbatore, Tamil Nadu, India.
5Mr. S. Ragupathy, Department of CSE, Sri Krishna College of Technology, Coimbatore, Tamil Nadu, India.
Manuscript received on March 15, 2020. | Revised Manuscript received on March 27, 2020. | Manuscript published on April 10, 2020. | PP: 308-313 | Volume-9 Issue-6, April 2020. | Retrieval Number: F3067049620/2020©BEIESP | DOI: 10.35940/ijitee.F3067.049620
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Cells in the human circulatory system and identifying the types and its functionalities cannot be done through naked eye. This asks for greater accurate methods of visualizing it and hence is vital in understanding blood disease causes, symptoms and the solution for them. But this field lacked clearance for the imaging system. Image Recognition was innovated using Deep Learning Technique. Human body cells assume an astounding job in the human resistant framework. To know more about blood-related infections and its effects, pathologists need to think about the attributes of cells. To diagnose a blood related disease, we need to identify and characterize blood samples of patients. In the medical field, automation for detecting and classifying blood cells and its subtypes have gained more importance nowadays. Recognition of an object is a basic piece for the vision of a computer that distinguishes an article in the given picture regardless of foundations, impediment, lighting or the edge of the view. Problems that are too difficult to solve can be handled using architectures that run deep using algorithms that dive deeper into the features extracted from the input and this can be possible using Deep Learning.
Keywords: Blood samples, Deep Learning, Image recognition, medical applications.
Scope of the Article: Smart Learning and Innovative Education Systems