Scholarly record
AUTOMATION OF THE TOTAL CLINICAL BLOOD TEST BASED ON THE USE OF A HYBRID ALGORITHM
Abstract
Segmentation of badly structured images is a complex task for different models of artificial intelligence systems. The given work presents algorithmic solutions for intercellular relations measurement in peripheral blood. There has been proposed hybrid algorithm, allowing to distinguish three classes of formed elements: ?erythrocyte?, ?leukocyte? and ?not erythrocyte and not leukocyte?. The algorithm provides for two-level processing of the image. Analysis of geometric attributes of image segments and their colour characteristics is the basis of the algorithm. Different images, being got by use of morphologic operators ?erosion? and ?dilatation? to the initial image, are analysis in this article. The process of segmentation is carried out on black-and-white image by gradient method. At each stage of the algorithm decision is made on the basis of aggregation of two values obtained as a result of analysis of segment colour and geometric attributes. Final decision is made on the basis of decision comparing, accepted at the first and second stages of processing. The algorithm may be used in automated systems of hematologic analysis.
Publication Impact Profile
- Citations
- Scopus - Citation Indexes: 1
- Captures
- Mendeley - Readers: 3
Publication details
References0
Structured references will appear here after the reference import pass. The count is preserved now so the scholarly record is not incomplete.
View or Download full articleAccess options
SWS access login
Login as SWS Scientific CommitteeLogin as SWS Scientific PartnerLogin as SWS AuthorAuthors and approved SWS contributors will read and export their own linked papers after identity matching by SWS profile, email and SGEM GlobalID.
For librarian assistance: [email protected]
Purchase Instant Access
- Article can be downloaded after successful payment.
- Article may be used according to SWS library access terms.
- Article cannot be redistributed.