Automatic grain segmentation in cross-polarized photomicrographs of sedimentary rocks using psychophysics inspired models View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2021-05-20

AUTHORS

Rajdeep Das, B. Uma Shankar, Tapan Chakraborty, Kuntal Ghosh

ABSTRACT

The present work analyses the effect of three spatial filters, modelling the psychophysics data on brightness perception, when applied to a difficult computer vision problem. This pertains to the automatic grain-matrix segmentation of cross-polar images of sedimentary rock thin sections, gathered through petrographic microscopy. These three filters are assumed to be modelling three modes of vision, viz. vision-at-a-glance (VG, through Magnocellular or M channel in primate visual pathway), vision-in-strong-contrast mode (VSC, through Parvocellular or P channel of visual pathway), and vision-with-scrutiny (VS, through Magno-Parvochannels combined referred as the PM filter). The aforementioned biologically inspired filters related to brightness–contrast modelling are applied on the cross-polar microscopic images. Then binary segmentation is performed on the original, as well as the filtered, images using a k-means clustering algorithm which effectively segment the input images according to the homogeneity present. The binary segmented output when compared with our manually built grain-matrix segmented ground truth using suitable indices, forecasts noticeable difference in terms of the applied filter on them and the grain size distribution in that image, manifested sometimes by the resolution scale of capturing the image. Mostly for images with higher resolution of microscope lens while capturing, or for images displaying larger grain size, the PM filtered image has shown better grain-matrix segmentation, though the effect of filtering is not very pronounced for such images. On the other hand, for lower resolution of microscope lens for capturing the image or for smaller grain size featured images, the P filtered image has consistently shown more accurate grain-matrix aggregation result as also distinct improvement over those not filtered. The novelty of the approach lies in the application of a psychophysics model that attempts to mimic the manual segmentation performed by the trained eye of the expert in various visual modes. The proposed method achieves a reasonably higher accuracy in grain segmentation when compared with relevant existing methods especially while dealing with more difficult images containing many small-sized grains. More... »

PAGES

167-183

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s11334-021-00400-y

DOI

http://dx.doi.org/10.1007/s11334-021-00400-y

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1138211480


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Machine Intelligence Unit, Indian Statistical Institute, 700108, Kolkata, India", 
          "id": "http://www.grid.ac/institutes/grid.39953.35", 
          "name": [
            "Machine Intelligence Unit, Indian Statistical Institute, 700108, Kolkata, India"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Das", 
        "givenName": "Rajdeep", 
        "id": "sg:person.012506707415.02", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012506707415.02"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Machine Intelligence Unit, Indian Statistical Institute, 700108, Kolkata, India", 
          "id": "http://www.grid.ac/institutes/grid.39953.35", 
          "name": [
            "Machine Intelligence Unit, Indian Statistical Institute, 700108, Kolkata, India"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Shankar", 
        "givenName": "B. Uma", 
        "id": "sg:person.010133347417.23", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010133347417.23"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Geological Studies Unit, Indian Statistical Institute, 700108, Kolkata, India", 
          "id": "http://www.grid.ac/institutes/grid.39953.35", 
          "name": [
            "Geological Studies Unit, Indian Statistical Institute, 700108, Kolkata, India"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Chakraborty", 
        "givenName": "Tapan", 
        "id": "sg:person.014657272430.91", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014657272430.91"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Machine Intelligence Unit, Indian Statistical Institute, 700108, Kolkata, India", 
          "id": "http://www.grid.ac/institutes/grid.39953.35", 
          "name": [
            "Machine Intelligence Unit, Indian Statistical Institute, 700108, Kolkata, India"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Ghosh", 
        "givenName": "Kuntal", 
        "id": "sg:person.0635133453.14", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0635133453.14"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/978-981-15-2188-1_18", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1126104760", 
          "https://doi.org/10.1007/978-981-15-2188-1_18"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2021-05-20", 
    "datePublishedReg": "2021-05-20", 
    "description": "The present work analyses the effect of three spatial filters, modelling the psychophysics data on brightness perception, when applied to a difficult computer vision problem. This pertains to the automatic grain-matrix segmentation of cross-polar images of sedimentary rock thin sections, gathered through petrographic microscopy. These three filters are assumed to be modelling three modes of vision, viz. vision-at-a-glance (VG, through Magnocellular or M channel in primate visual pathway), vision-in-strong-contrast mode (VSC, through Parvocellular or P channel of visual pathway), and vision-with-scrutiny (VS, through Magno-Parvochannels combined referred as the PM filter). The aforementioned biologically inspired filters related to brightness\u2013contrast modelling are applied on the cross-polar microscopic images. Then binary segmentation is performed on the original, as well as the filtered, images using a k-means clustering algorithm which effectively segment the input images according to the homogeneity present. The binary segmented output when compared with our manually built grain-matrix segmented ground truth using suitable indices, forecasts noticeable difference in terms of the applied filter on them and the grain size distribution in that image, manifested sometimes by the resolution scale of capturing the image. Mostly for images with higher resolution of microscope lens while capturing, or for images displaying larger grain size, the PM filtered image has shown better grain-matrix segmentation, though the effect of filtering is not very pronounced for such images. On the other hand, for lower resolution of microscope lens for capturing the image or for smaller grain size featured images, the P filtered image has consistently shown more accurate grain-matrix aggregation result as also distinct improvement over those not filtered. The novelty of the approach lies in the application of a psychophysics model that attempts to mimic the manual segmentation performed by the trained eye of the expert in various visual modes. The proposed method achieves a reasonably higher accuracy in grain segmentation when compared with relevant existing methods especially while dealing with more difficult images containing many small-sized grains.", 
    "genre": "article", 
    "id": "sg:pub.10.1007/s11334-021-00400-y", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1044675", 
        "issn": [
          "1614-5046", 
          "1614-5054"
        ], 
        "name": "Innovations in Systems and Software Engineering", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "2", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "17"
      }
    ], 
    "keywords": [
      "difficult computer vision problem", 
      "computer vision problems", 
      "grain segmentation", 
      "segmented ground truth", 
      "input image", 
      "difficult images", 
      "vision problems", 
      "binary segmentation", 
      "ground truth", 
      "manual segmentation", 
      "segmentation", 
      "such images", 
      "aggregation results", 
      "psychophysics data", 
      "high accuracy", 
      "low resolution", 
      "images", 
      "vision", 
      "microscopic images", 
      "rock thin sections", 
      "visual mode", 
      "algorithm", 
      "modes of vision", 
      "spatial filter", 
      "resolution scale", 
      "capturing", 
      "filter", 
      "filtering", 
      "accuracy", 
      "experts", 
      "effect of filtering", 
      "high resolution", 
      "novelty", 
      "model", 
      "applications", 
      "method", 
      "Biologically", 
      "modelling", 
      "truth", 
      "output", 
      "work", 
      "suitable index", 
      "data", 
      "glance", 
      "resolution", 
      "brightness perception", 
      "distinct improvement", 
      "improvement", 
      "terms", 
      "hand", 
      "mode", 
      "means", 
      "psychophysics", 
      "size", 
      "results", 
      "perception", 
      "viz", 
      "noticeable differences", 
      "lens", 
      "microscope lens", 
      "scale", 
      "present work", 
      "distribution", 
      "eyes", 
      "scrutiny", 
      "index", 
      "sections", 
      "homogeneity", 
      "photomicrographs", 
      "differences", 
      "petrographic microscopy", 
      "effect", 
      "thin sections", 
      "PM", 
      "grain size distribution", 
      "size distribution", 
      "grains", 
      "rocks", 
      "problem", 
      "approach", 
      "microscopy", 
      "grain size", 
      "larger grain size", 
      "small grain size", 
      "small-sized grains", 
      "sedimentary rocks", 
      "automatic grain-matrix segmentation", 
      "grain-matrix segmentation", 
      "cross-polar images", 
      "sedimentary rock thin sections", 
      "strong-contrast mode", 
      "aforementioned biologically", 
      "brightness\u2013contrast modelling", 
      "cross-polar microscopic images", 
      "grain-matrix segmented ground truth", 
      "forecasts noticeable difference", 
      "better grain-matrix segmentation", 
      "accurate grain-matrix aggregation result", 
      "grain-matrix aggregation result", 
      "psychophysics model", 
      "Automatic grain segmentation", 
      "cross-polarized photomicrographs"
    ], 
    "name": "Automatic grain segmentation in cross-polarized photomicrographs of sedimentary rocks using psychophysics inspired models", 
    "pagination": "167-183", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1138211480"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s11334-021-00400-y"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s11334-021-00400-y", 
      "https://app.dimensions.ai/details/publication/pub.1138211480"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2022-01-01T19:01", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220101/entities/gbq_results/article/article_881.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1007/s11334-021-00400-y"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/s11334-021-00400-y'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s11334-021-00400-y'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s11334-021-00400-y'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s11334-021-00400-y'


 

This table displays all metadata directly associated to this object as RDF triples.

187 TRIPLES      22 PREDICATES      128 URIs      119 LITERALS      6 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s11334-021-00400-y schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N354a136c0c40402a8edb8c691a5036f0
4 schema:citation sg:pub.10.1007/978-981-15-2188-1_18
5 schema:datePublished 2021-05-20
6 schema:datePublishedReg 2021-05-20
7 schema:description The present work analyses the effect of three spatial filters, modelling the psychophysics data on brightness perception, when applied to a difficult computer vision problem. This pertains to the automatic grain-matrix segmentation of cross-polar images of sedimentary rock thin sections, gathered through petrographic microscopy. These three filters are assumed to be modelling three modes of vision, viz. vision-at-a-glance (VG, through Magnocellular or M channel in primate visual pathway), vision-in-strong-contrast mode (VSC, through Parvocellular or P channel of visual pathway), and vision-with-scrutiny (VS, through Magno-Parvochannels combined referred as the PM filter). The aforementioned biologically inspired filters related to brightness–contrast modelling are applied on the cross-polar microscopic images. Then binary segmentation is performed on the original, as well as the filtered, images using a k-means clustering algorithm which effectively segment the input images according to the homogeneity present. The binary segmented output when compared with our manually built grain-matrix segmented ground truth using suitable indices, forecasts noticeable difference in terms of the applied filter on them and the grain size distribution in that image, manifested sometimes by the resolution scale of capturing the image. Mostly for images with higher resolution of microscope lens while capturing, or for images displaying larger grain size, the PM filtered image has shown better grain-matrix segmentation, though the effect of filtering is not very pronounced for such images. On the other hand, for lower resolution of microscope lens for capturing the image or for smaller grain size featured images, the P filtered image has consistently shown more accurate grain-matrix aggregation result as also distinct improvement over those not filtered. The novelty of the approach lies in the application of a psychophysics model that attempts to mimic the manual segmentation performed by the trained eye of the expert in various visual modes. The proposed method achieves a reasonably higher accuracy in grain segmentation when compared with relevant existing methods especially while dealing with more difficult images containing many small-sized grains.
8 schema:genre article
9 schema:inLanguage en
10 schema:isAccessibleForFree false
11 schema:isPartOf N13d18801210148b1ba6c2e51e698c5fd
12 Nc26604320a0f47b0984ad78e200ea28a
13 sg:journal.1044675
14 schema:keywords Automatic grain segmentation
15 Biologically
16 PM
17 accuracy
18 accurate grain-matrix aggregation result
19 aforementioned biologically
20 aggregation results
21 algorithm
22 applications
23 approach
24 automatic grain-matrix segmentation
25 better grain-matrix segmentation
26 binary segmentation
27 brightness perception
28 brightness–contrast modelling
29 capturing
30 computer vision problems
31 cross-polar images
32 cross-polar microscopic images
33 cross-polarized photomicrographs
34 data
35 differences
36 difficult computer vision problem
37 difficult images
38 distinct improvement
39 distribution
40 effect
41 effect of filtering
42 experts
43 eyes
44 filter
45 filtering
46 forecasts noticeable difference
47 glance
48 grain segmentation
49 grain size
50 grain size distribution
51 grain-matrix aggregation result
52 grain-matrix segmentation
53 grain-matrix segmented ground truth
54 grains
55 ground truth
56 hand
57 high accuracy
58 high resolution
59 homogeneity
60 images
61 improvement
62 index
63 input image
64 larger grain size
65 lens
66 low resolution
67 manual segmentation
68 means
69 method
70 microscope lens
71 microscopic images
72 microscopy
73 mode
74 model
75 modelling
76 modes of vision
77 noticeable differences
78 novelty
79 output
80 perception
81 petrographic microscopy
82 photomicrographs
83 present work
84 problem
85 psychophysics
86 psychophysics data
87 psychophysics model
88 resolution
89 resolution scale
90 results
91 rock thin sections
92 rocks
93 scale
94 scrutiny
95 sections
96 sedimentary rock thin sections
97 sedimentary rocks
98 segmentation
99 segmented ground truth
100 size
101 size distribution
102 small grain size
103 small-sized grains
104 spatial filter
105 strong-contrast mode
106 such images
107 suitable index
108 terms
109 thin sections
110 truth
111 vision
112 vision problems
113 visual mode
114 viz
115 work
116 schema:name Automatic grain segmentation in cross-polarized photomicrographs of sedimentary rocks using psychophysics inspired models
117 schema:pagination 167-183
118 schema:productId N7799ab3ebb314510a939ead057d52679
119 Ne871851ecfe042b2b6d3b478b38bb55d
120 schema:sameAs https://app.dimensions.ai/details/publication/pub.1138211480
121 https://doi.org/10.1007/s11334-021-00400-y
122 schema:sdDatePublished 2022-01-01T19:01
123 schema:sdLicense https://scigraph.springernature.com/explorer/license/
124 schema:sdPublisher N61a795ce584044c28cc62cfca83b6580
125 schema:url https://doi.org/10.1007/s11334-021-00400-y
126 sgo:license sg:explorer/license/
127 sgo:sdDataset articles
128 rdf:type schema:ScholarlyArticle
129 N13d18801210148b1ba6c2e51e698c5fd schema:volumeNumber 17
130 rdf:type schema:PublicationVolume
131 N354a136c0c40402a8edb8c691a5036f0 rdf:first sg:person.012506707415.02
132 rdf:rest Na14c49043f8145e7abdb5bcc8728e3cf
133 N61a795ce584044c28cc62cfca83b6580 schema:name Springer Nature - SN SciGraph project
134 rdf:type schema:Organization
135 N7799ab3ebb314510a939ead057d52679 schema:name dimensions_id
136 schema:value pub.1138211480
137 rdf:type schema:PropertyValue
138 N8a9a13df5b5f486a89a3bf7372af7841 rdf:first sg:person.014657272430.91
139 rdf:rest Nec42a3d5a5cf4aabaa5379ffe12e0d31
140 Na14c49043f8145e7abdb5bcc8728e3cf rdf:first sg:person.010133347417.23
141 rdf:rest N8a9a13df5b5f486a89a3bf7372af7841
142 Nc26604320a0f47b0984ad78e200ea28a schema:issueNumber 2
143 rdf:type schema:PublicationIssue
144 Ne871851ecfe042b2b6d3b478b38bb55d schema:name doi
145 schema:value 10.1007/s11334-021-00400-y
146 rdf:type schema:PropertyValue
147 Nec42a3d5a5cf4aabaa5379ffe12e0d31 rdf:first sg:person.0635133453.14
148 rdf:rest rdf:nil
149 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
150 schema:name Information and Computing Sciences
151 rdf:type schema:DefinedTerm
152 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
153 schema:name Artificial Intelligence and Image Processing
154 rdf:type schema:DefinedTerm
155 sg:journal.1044675 schema:issn 1614-5046
156 1614-5054
157 schema:name Innovations in Systems and Software Engineering
158 schema:publisher Springer Nature
159 rdf:type schema:Periodical
160 sg:person.010133347417.23 schema:affiliation grid-institutes:grid.39953.35
161 schema:familyName Shankar
162 schema:givenName B. Uma
163 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010133347417.23
164 rdf:type schema:Person
165 sg:person.012506707415.02 schema:affiliation grid-institutes:grid.39953.35
166 schema:familyName Das
167 schema:givenName Rajdeep
168 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012506707415.02
169 rdf:type schema:Person
170 sg:person.014657272430.91 schema:affiliation grid-institutes:grid.39953.35
171 schema:familyName Chakraborty
172 schema:givenName Tapan
173 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014657272430.91
174 rdf:type schema:Person
175 sg:person.0635133453.14 schema:affiliation grid-institutes:grid.39953.35
176 schema:familyName Ghosh
177 schema:givenName Kuntal
178 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0635133453.14
179 rdf:type schema:Person
180 sg:pub.10.1007/978-981-15-2188-1_18 schema:sameAs https://app.dimensions.ai/details/publication/pub.1126104760
181 https://doi.org/10.1007/978-981-15-2188-1_18
182 rdf:type schema:CreativeWork
183 grid-institutes:grid.39953.35 schema:alternateName Geological Studies Unit, Indian Statistical Institute, 700108, Kolkata, India
184 Machine Intelligence Unit, Indian Statistical Institute, 700108, Kolkata, India
185 schema:name Geological Studies Unit, Indian Statistical Institute, 700108, Kolkata, India
186 Machine Intelligence Unit, Indian Statistical Institute, 700108, Kolkata, India
187 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...