37aa2b94daa6ac145df8d19d57410f0c  pmc_29301337.pdf
33afedf6394120d1045826cf68a5c69da1a3a702  pmc_29301337.pdf
0fba6b86132a0b59cd6a089794979f00eb34757d0245978abf66759183487124  pmc_29301337.pdf

Title:          Organ Segmentation in Poultry Viscera Using RGB-D
Subject:         We present a pattern recognition framework for semantic segmentation of visual structures, that is, multi-class labelling at pixel level, and apply it to the task of segmenting organs in the eviscerated viscera from slaughtered poultry in RGB-D images. This is a step towards replacing the current strenuous manual inspection at poultry processing plants. Features are extracted from feature maps such as activation maps from a convolutional neural network (CNN). A random forest classifier assigns class probabilities, which are further refined by utilizing context in a conditional random field. The presented method is compatible with both 2D and 3D features, which allows us to explore the value of adding 3D and CNN-derived features. The dataset consists of 604 RGB-D images showing 151 unique sets of eviscerated viscera from four different perspectives. A mean Jaccard index of 78.11% is achieved across the four classes of organs by using features derived from 2D, 3D and a CNN, compared to 74.28% using only basic 2D image features. 
Keywords:       semantic segmentation; RGB-D; random forest; conditional random field; 2D; 3D; CNN
Author:         Mark Philip Philipsen, Jacob Velling Dueholm, Anders Jørgensen, Sergio Escalera and Thomas Baltzer Moeslund
Creator:        LaTeX with hyperref package
Producer:       pdfTeX-1.40.18
CreationDate:   Wed Jan  3 06:16:52 2018 CET
ModDate:        Wed Jan  3 06:16:52 2018 CET
Tagged:         no
UserProperties: no
Suspects:       no
Form:           none
JavaScript:     no
Pages:          15
Encrypted:      no
Page size:      595.276 x 841.89 pts (A4)
Page rot:       0
File size:      2612311 bytes
Optimized:      no
PDF version:    1.5

name                                 type              encoding         emb sub uni object ID
------------------------------------ ----------------- ---------------- --- --- --- ---------
RUBRFX+URWPalladioL-Ital             Type 1            Custom           yes yes no      81  0
NHCJRO+URWPalladioL-Bold             Type 1            Custom           yes yes no      82  0
OXBKYU+TeXGyreAdventor-Bold          Type 1            Custom           yes yes no      83  0
QIFUYL+URWPalladioL-Roma             Type 1            Custom           yes yes no      84  0
RVSEMT+TimesNewRomanPS-BoldItalicMT  Type 1C           WinAnsi          yes yes no      89  0
NZHQYI+CMSY10                        Type 1            Builtin          yes yes no     161  0
GIGFZE+CMR10                         Type 1            Builtin          yes yes no     310  0
QQXUPP+PazoMath                      Type 1            Builtin          yes yes no     325  0
BitstreamVeraSans-Roman              Type 3            Custom           yes no  no     332  0
BitstreamVeraSans-Roman              Type 3            Custom           yes no  no     361  0
IRJODZ+CMSY5                         Type 1            Builtin          yes yes no     443  0
WEIJUK+CMSY9                         Type 1            Builtin          yes yes no     452  0

java.lang.ClassCastException: edu.harvard.hul.ois.jhove.module.pdf.PdfSimpleObject cannot be cast to edu.harvard.hul.ois.jhove.module.pdf.PdfDictionary
	at edu.harvard.hul.ois.jhove.module.PdfModule.readDocCatalogDict(PdfModule.java:1284)
	at edu.harvard.hul.ois.jhove.module.PdfModule.parse(PdfModule.java:525)
	at edu.harvard.hul.ois.jhove.JhoveBase.processFile(JhoveBase.java:825)
	at edu.harvard.hul.ois.jhove.JhoveBase.process(JhoveBase.java:614)
	at edu.harvard.hul.ois.jhove.JhoveBase.dispatch(JhoveBase.java:465)
	at Jhove.main(Jhove.java:296)
Jhove (Rel. 1.6, 2011-01-04)
 Date: 2019-02-14 17:31:40 CET
 RepresentationInformation: pmc_29301337.pdf
  ReportingModule: BYTESTREAM, Rel. 1.3 (2007-04-10)
  LastModified: 2018-03-05 03:52:02 CET
  Size: 2612311
  Format: bytestream
  Status: Well-Formed and valid
  SignatureMatches:
   PDF-hul
  MIMEtype: application/octet-stream
  Checksum: 7d86ed41
   Type: CRC32
  Checksum: 37aa2b94daa6ac145df8d19d57410f0c
   Type: MD5
  Checksum: 33afedf6394120d1045826cf68a5c69da1a3a702
   Type: SHA-1