Habitual detection and measurement of human blood cells on hyperspectral imagery for convolutional neural network
by T. Arumuga Maria Devi; PaulRaj Thangaselvi
International Journal of Biomedical Engineering and Technology (IJBET), Vol. 45, No. 1, 2024

Abstract: This paper's proposed strategy has taken a stab at a different dataset of smear pictures, where it has performed acceptably. With the accuracy and the disclosure execution of the proposed system, it will in general be said that the procedure has the potential to ease off the manual platelet recognising verification and counting measure. A complete platelet incorporate is a critical test in clinical end to survey by and large disease. Usually, platelets are counted actually using haemocytometer close by other examination office equipment's and substance blends, which is a dreary and monotonous commission. In this effort, the makers nearby an AI advance for modified ID and together with of three kinds of platelets using 'you simply look once' (YOLO) object acknowledgment and gathering computation. YOLO structure has been set up with a changed arrangement BCCD Dataset of blood smear picture to normally recognise and check red platelets, white platelets, and platelets. Experimental results demonstrate that the proposed model can achieve better classification performance than traditional CNNs and widely used support vector machine (SVM) approaches, especially as training small-sample-size situations.

Online publication date: Thu, 16-May-2024

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Biomedical Engineering and Technology (IJBET):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com