Classification system for blister pack of pills
View/
Date
2014-10Share
Metadata
Show full item recordCollections
Cita
Abstract
En este trabajo, se presenta el desarrollo de un sistema que
permite clasificar un conjunto de Blister Packs utilizados para
el almacenamiento de Pastillas de Medicamentos. Aunque las
pastillas pueden ser identificadas directamente por su color, se
utilizó una técnica de extracción de características, tal como lo
es la Segmentación basada en Análisis Fractal de Texturas;
dado que se requería un conjunto de parámetros para alimentar
un clasificador utilizando aprendizaje supervisado a partir de
K-nearest neighbours.
Abstract
Abstract— In this paper we present a classification system for
blister pack of pills. For the development of the system was taken
into account three types of Blister Packs, where we performed a
classification process considering a Segmentation-based Fractal
Texture Analysis system, likewise, was used Otsu multi-level
algorithm, as nonparametric technique for thresholds detection.
The features extracted from the Fractal Texture-based
Segmentation Analysis system, are used as a database of
entrainment to a classification system based on k-nearest
PDF Documents
xmlui.custom.comments.form-panel-heading
The following license files are associated with this item:
Except where otherwise noted, this item's license is described as Atribución-NoComercial-CompartirIgual 2.5 Colombia
Indexado por:
