2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro 2009
DOI: 10.1109/isbi.2009.5193306
|View full text |Cite
|
Sign up to set email alerts
|

Learning disease severity for capsule endoscopy images

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
2
0
1

Year Published

2011
2011
2020
2020

Publication Types

Select...
4
2
1

Relationship

0
7

Authors

Journals

citations
Cited by 8 publications
(3 citation statements)
references
References 12 publications
0
2
0
1
Order By: Relevance
“…A comparison is drawn using these feature descriptors by training using ans SVM and an ANN classifier. [322], proposes computing a 10-bin normalized hue and saturation histograms and training a SVM classifier for retrieving the class of the tissue in the ROI. [323] proposes representing the localized features in HD endoscopy images in semantic space to generate a CBIR system for clinicians to review online selected regions.…”
Section: -[229] 10) Intra and Inter-operative Re-localization (Iao An...mentioning
confidence: 99%
“…A comparison is drawn using these feature descriptors by training using ans SVM and an ANN classifier. [322], proposes computing a 10-bin normalized hue and saturation histograms and training a SVM classifier for retrieving the class of the tissue in the ROI. [323] proposes representing the localized features in HD endoscopy images in semantic space to generate a CBIR system for clinicians to review online selected regions.…”
Section: -[229] 10) Intra and Inter-operative Re-localization (Iao An...mentioning
confidence: 99%
“…However, due to its long-running time of more than 10 hours, automatic potential ulcer lesions detection and classification becomes essential factor of WCE performance. Machine learning approaches have shown meaningful performance in lesion detection from color images: intestine, polyp [3], ulcer [5] [6] and hookworm [2]. Recently, deep learning methods show much improved results in these applications.…”
Section: Introductionmentioning
confidence: 99%
“…Οι συγγραφείς των εργασιών (Bejakovic et al;2009;Kumar et al, 2009Kumar et al, , 2012Girgis et al, 2010;Jebarami & Daisy, 2013) ασχολήθηκαν με την αναγνώριση φλεγμονών και διαβρώσεων από NC, κάνοντας χρήση χαρακτηριστικών υφής, χρώματος και ακμών. Πιο συγκεκριμένα, χρησιμοποιήθηκαν περιγραφείς MPEG-7 για την εξαγωγή πληροφοριών χρώματος (περιγραφέας κυρίαρχου χρώματος, dominant color descriptor) και ακμών (περιγραφέας ιστογράμματος ακμών -edge histogram descriptor), ενώ για τις πληροφορίες υφής εκμεταλλεύτηκαν τον MPEG-7 περιγραφέα ομογενούς υφής (homogenous texture descriptor), σε συνδυασμό με χαρακτηριστικά από ΤΔΠ, χαρακτηριστικά Haralick και στατιστικές χρωματικού ιστογράμματος.…”
Section: ανίχνευση έλκους και διαβρώσεων από Ncunclassified