Image quality assessment and outliers filtering in an image-based animal supervision system

Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussaKirjan luku tai artikkeliTieteellinenvertaisarvioitu

Kuvaus

This paper presents a probabilistic framework for the image quality assessment (QA), and filtering of outliers, in an image-based animal supervision system (asup). The proposed framework recognizes asup's imperfect frames in two stages. The first stage deals with the similarity analysis of the same-class distributions. The objective of this stage is to maximize the separability measures by defining a set of similarity indicators (SI) under the condition that the number of permissible values for them is restricted to be relatively low. The second stage, namely faulty frame recognition (FFR), deals with asup's QA training and real-time quality assessment (RTQS). In RTQS, decisions are made based on a real-time quality assessment mechanism such that the majority of the defected frames are removed from the consecutive sub routines that calculate the movements. The underlying approach consists of a set of SI indexes employed in a simple Bayesian inference model. The results confirm that a significant amount of defected frames can be efficiently classified by this approach. The performance of the proposed technique is demonstrated by the classification on a cross-validation set of mixed high and low quality frames. The classification shows a true positive rate of 88.6% while the false negative rate is only about 2.5%. © 2018, IGI Global. All rights reserved.
Alkuperäiskielienglanti
OtsikkoVeterinary Science: Breakthroughs in Research and Practice
KustantajaIGI Global
Julkaisupäivä2018
Sivut34-50
ISBN (painettu)9781522556404
ISBN (elektroninen)9781522556411
DOI - pysyväislinkit
TilaJulkaistu - 2018
OKM-julkaisutyyppiA3 Kirjan tai muun kokoomateoksen osa

Tieteenalat

  • 413 Eläinlääketiede
  • 113 Tietojenkäsittely- ja informaatiotieteet

Lainaa tätä

@inbook{2e58c0b95caa45a3832fb64259ddae0c,
title = "Image quality assessment and outliers filtering in an image-based animal supervision system",
abstract = "This paper presents a probabilistic framework for the image quality assessment (QA), and filtering of outliers, in an image-based animal supervision system (asup). The proposed framework recognizes asup's imperfect frames in two stages. The first stage deals with the similarity analysis of the same-class distributions. The objective of this stage is to maximize the separability measures by defining a set of similarity indicators (SI) under the condition that the number of permissible values for them is restricted to be relatively low. The second stage, namely faulty frame recognition (FFR), deals with asup's QA training and real-time quality assessment (RTQS). In RTQS, decisions are made based on a real-time quality assessment mechanism such that the majority of the defected frames are removed from the consecutive sub routines that calculate the movements. The underlying approach consists of a set of SI indexes employed in a simple Bayesian inference model. The results confirm that a significant amount of defected frames can be efficiently classified by this approach. The performance of the proposed technique is demonstrated by the classification on a cross-validation set of mixed high and low quality frames. The classification shows a true positive rate of 88.6{\%} while the false negative rate is only about 2.5{\%}. {\circledC} 2018, IGI Global. All rights reserved.",
keywords = "413 Veterinary science, 113 Computer and information sciences",
author = "E. Khoramshahi and J. Hietaoja and A. Valros and J. Yun and M. Pastell",
year = "2018",
doi = "10.4018/978-1-5225-5640-4.ch003",
language = "English",
isbn = "9781522556404",
pages = "34--50",
booktitle = "Veterinary Science: Breakthroughs in Research and Practice",
publisher = "IGI Global",
address = "United States",

}

Image quality assessment and outliers filtering in an image-based animal supervision system. / Khoramshahi, E.; Hietaoja, J.; Valros, A.; Yun, J.; Pastell, M.

Veterinary Science: Breakthroughs in Research and Practice. IGI Global, 2018. s. 34-50.

Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussaKirjan luku tai artikkeliTieteellinenvertaisarvioitu

TY - CHAP

T1 - Image quality assessment and outliers filtering in an image-based animal supervision system

AU - Khoramshahi, E.

AU - Hietaoja, J.

AU - Valros, A.

AU - Yun, J.

AU - Pastell, M.

PY - 2018

Y1 - 2018

N2 - This paper presents a probabilistic framework for the image quality assessment (QA), and filtering of outliers, in an image-based animal supervision system (asup). The proposed framework recognizes asup's imperfect frames in two stages. The first stage deals with the similarity analysis of the same-class distributions. The objective of this stage is to maximize the separability measures by defining a set of similarity indicators (SI) under the condition that the number of permissible values for them is restricted to be relatively low. The second stage, namely faulty frame recognition (FFR), deals with asup's QA training and real-time quality assessment (RTQS). In RTQS, decisions are made based on a real-time quality assessment mechanism such that the majority of the defected frames are removed from the consecutive sub routines that calculate the movements. The underlying approach consists of a set of SI indexes employed in a simple Bayesian inference model. The results confirm that a significant amount of defected frames can be efficiently classified by this approach. The performance of the proposed technique is demonstrated by the classification on a cross-validation set of mixed high and low quality frames. The classification shows a true positive rate of 88.6% while the false negative rate is only about 2.5%. © 2018, IGI Global. All rights reserved.

AB - This paper presents a probabilistic framework for the image quality assessment (QA), and filtering of outliers, in an image-based animal supervision system (asup). The proposed framework recognizes asup's imperfect frames in two stages. The first stage deals with the similarity analysis of the same-class distributions. The objective of this stage is to maximize the separability measures by defining a set of similarity indicators (SI) under the condition that the number of permissible values for them is restricted to be relatively low. The second stage, namely faulty frame recognition (FFR), deals with asup's QA training and real-time quality assessment (RTQS). In RTQS, decisions are made based on a real-time quality assessment mechanism such that the majority of the defected frames are removed from the consecutive sub routines that calculate the movements. The underlying approach consists of a set of SI indexes employed in a simple Bayesian inference model. The results confirm that a significant amount of defected frames can be efficiently classified by this approach. The performance of the proposed technique is demonstrated by the classification on a cross-validation set of mixed high and low quality frames. The classification shows a true positive rate of 88.6% while the false negative rate is only about 2.5%. © 2018, IGI Global. All rights reserved.

KW - 413 Veterinary science

KW - 113 Computer and information sciences

U2 - 10.4018/978-1-5225-5640-4.ch003

DO - 10.4018/978-1-5225-5640-4.ch003

M3 - Chapter

SN - 9781522556404

SP - 34

EP - 50

BT - Veterinary Science: Breakthroughs in Research and Practice

PB - IGI Global

ER -