General system for digital processing and analysis of images and computer vision for welfare
Keywords:
digital image processing, image analysis, computational vision, welfareAbstract
Introduction: The image and signal processing and analysis laboratory of the Computing Research Center of the Universidad Central Marta Abreu de Las Villas, develops algorithms and programs for the digital processing and analysis of images and computational vision. A representative sample of work from the laboratory in recent years illustrates the validity of the proposed generalizing system.
Objective: To propose a generalizing scheme to form various applications, based on the processing and analysis of image sets and to illustrate the validity of the proposed generalizing system with works for welfare.
Methods: The scheme consists of several interconnected functional blocks that, from sets of images of different modalities, achieve the improvement or analysis of their quality, the extraction and selection of features for classification, the detection of objects and structures of interest, or its monitoring. In the blocks, the possible algorithms and outputs must be selected in different iterations and with the necessary feedback to achieve the desired results.
Results: The scheme validity is illustrated for reducing noise in mammography images, generating isodose maps from irradiated radiochromic films, recognizing robust patterns to electrode displacement in myoelectric monitoring, automatically and rapidly locating structures in fundus images, automatically measuring hip radiographs to diagnose developmental dysplasia and estimating respiration signals from videos. The image processing and computer vision techniques from the generalizing scheme outperformed the reference ones in all cases.
Conclusions: The algorithms and programs for digital image processing and computer vision of the generalizing scheme solve problems related to people's well-being, although they are not limited to that objective.
Downloads
Published
How to Cite
Issue
Section
License
The journal Anales de la Academia de Ciencias de Cuba protects copyright, and operates with a Creative Commons License 4.0 (Creative Commons Attribution-NonCommercial License 4.0). By publishing in it, authors allow themselves to copy, reproduce, distribute, publicly communicate their work and generate derivative works, as long as the original author is cited and acknowledged. They do not allow, however, the use of the original work for commercial or lucrative purposes.
The authors authorize the publication of their writings, retaining the authorship rights, and assigning and transferring to the magazine all the rights protected by the intellectual property laws that govern in Cuba, which imply editing to disseminate the work.
Authors may establish additional agreements for the non-exclusive distribution of the version of the work published in the journal (for example, placing it in an institutional repository or publishing it in a book), with recognition of having been first published in this journal.
To learn more, see https://creativecommons.org
