Algoritmo para la Generación de Imágenes Sintéticas de Microscopía Celular formadas por Eritrocitos y Evaluación de Algoritmos de Segmentación

Moreno-Montes-de-Oca, A.; Chinea-Valdés, Lyanett; Lorenzo-Ginori, Juan V.

doi:10.1007/978-3-642-21198-0_262

Cited by 1 publication

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study was realized using two sets of ten images each: one set is composed by synthetic images generated using an erythrocyte simulation algorithm [6] and the other is composed of ten images drawn from an atlas of hematology [5]. The digital images that appear in the latter were obtained from human blood smears and all of them are represented in the RGB color space.…”

Section: Characteristics Of the Images Employed In This Studymentioning

confidence: 99%

Effects of Interpolation on Segmentation in Cell Imaging

Coca-Rodríguez¹,

Lorenzo-Ginori²

2014

CyS

View full text Add to dashboard Cite

In digital image processing and computer vision applications for microscopy imaging, calculating image features is a frequent task. Features related to intensity, color and morphology are used to classify cells and other objects. The precision of segmentation influences the calculated feature values and can affect the results of classification. Therefore, achieving a high precision in segmentation is very important. In this work, the effects of interpolation on the precision of image segmentation were studied using instances of cell microscopy images and different interpolation and segmentation methods. The goal was to determine quantitatively to what extent improvements in segmentation precision can be obtained through previous interpolation of the images. This effect can be particularly important for small objects, whose images might be deteriorated due to limitations in the camera's resolution. The results show that an improvement in the precision of segmentation can be obtained by previously interpolating the images.

show abstract

Section: Characteristics Of the Images Employed In This Studymentioning

confidence: 99%