Query Based Object Retrieval Using Neural Codes View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2017-08-23

AUTHORS

Surajit Saikia , Eduardo Fidalgo , Enrique Alegre , Laura Fernández-Robles

ABSTRACT

The task of retrieving a specific object from an image, which is similar to a query object is one of the critical applications in the computer vision domain. The existing methods fail to return similar objects when the region of interest is not specified correctly in a query image. Furthermore, when the feature vector is large, the retrieval from big collections is usually computationally expensive. In this paper, we propose an object retrieval method, which is based on the neural codes (activations) generated by the last inner-product layer of the Faster R-CNN network demonstrating that it can be used not only for object detection but for retrieval too. To evaluate the method, we have used a subset of ImageNet comprising of images related to indoor scenes, and to speed-up the retrieval, we first process all the images from the dataset and we save information (i.e. neural codes, objects present in the image, confidence scores and bounding box coordinates) corresponding to each detected object. Then, given a query image, the system detects the object present and retrieves its neural codes, which are then used to compute the cosine similarity against saved neural codes. We retrieved objects with high cosine similarity scores, and then we compared it with the results obtained using confidence scores. We showed that our approach takes only 0.534 s to retrieve all the 1454 objects in our test set. More... »

PAGES

513-523

Book

TITLE

International Joint Conference SOCO’17-CISIS’17-ICEUTE’17 León, Spain, September 6–8, 2017, Proceeding

ISBN

978-3-319-67179-6
978-3-319-67180-2

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-319-67180-2_50

DOI

http://dx.doi.org/10.1007/978-3-319-67180-2_50

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1091287479


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"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0806", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information Systems", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Researcher at INCIBE (Spanish National Cybersecurity Institute), Le\u00f3n, Spain", 
          "id": "http://www.grid.ac/institutes/None", 
          "name": [
            "Department of Electrical, Systems and Automation, University of Le\u00f3n, Le\u00f3n, Spain", 
            "Researcher at INCIBE (Spanish National Cybersecurity Institute), Le\u00f3n, Spain"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Saikia", 
        "givenName": "Surajit", 
        "id": "sg:person.013366561121.26", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013366561121.26"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Researcher at INCIBE (Spanish National Cybersecurity Institute), Le\u00f3n, Spain", 
          "id": "http://www.grid.ac/institutes/None", 
          "name": [
            "Department of Electrical, Systems and Automation, University of Le\u00f3n, Le\u00f3n, Spain", 
            "Researcher at INCIBE (Spanish National Cybersecurity Institute), Le\u00f3n, Spain"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Fidalgo", 
        "givenName": "Eduardo", 
        "id": "sg:person.012664070017.21", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012664070017.21"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Researcher at INCIBE (Spanish National Cybersecurity Institute), Le\u00f3n, Spain", 
          "id": "http://www.grid.ac/institutes/None", 
          "name": [
            "Department of Electrical, Systems and Automation, University of Le\u00f3n, Le\u00f3n, Spain", 
            "Researcher at INCIBE (Spanish National Cybersecurity Institute), Le\u00f3n, Spain"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Alegre", 
        "givenName": "Enrique", 
        "id": "sg:person.016266057305.75", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016266057305.75"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Mechanical, Informatics and Aerospace Engineering, University of Le\u00f3n, Le\u00f3n, Spain", 
          "id": "http://www.grid.ac/institutes/grid.4807.b", 
          "name": [
            "Researcher at INCIBE (Spanish National Cybersecurity Institute), Le\u00f3n, Spain", 
            "Department of Mechanical, Informatics and Aerospace Engineering, University of Le\u00f3n, Le\u00f3n, Spain"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Fern\u00e1ndez-Robles", 
        "givenName": "Laura", 
        "id": "sg:person.010415303037.45", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010415303037.45"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2017-08-23", 
    "datePublishedReg": "2017-08-23", 
    "description": "The task of retrieving a specific object from an image, which is similar to a query object is one of the critical applications in the computer vision domain. The existing methods fail to return similar objects when the region of interest is not specified correctly in a query image. Furthermore, when the feature vector is large, the retrieval from big collections is usually computationally expensive. In this paper, we propose an object retrieval method, which is based on the neural codes (activations) generated by the last inner-product layer of the Faster R-CNN network demonstrating that it can be used not only for object detection but for retrieval too. To evaluate the method, we have used a subset of ImageNet comprising of images related to indoor scenes, and to speed-up the retrieval, we first process all the images from the dataset and we save information (i.e. neural codes, objects present in the image, confidence scores and bounding box coordinates) corresponding to each detected object. Then, given a query image, the system detects the object present and retrieves its neural codes, which are then used to compute the cosine similarity against saved neural codes. We retrieved objects with high cosine similarity scores, and then we compared it with the results obtained using confidence scores. We showed that our approach takes only 0.534\u00a0s to retrieve all the 1454 objects in our test set.", 
    "editor": [
      {
        "familyName": "P\u00e9rez Garc\u00eda", 
        "givenName": "Hilde", 
        "type": "Person"
      }, 
      {
        "familyName": "Alfonso-Cend\u00f3n", 
        "givenName": "Javier", 
        "type": "Person"
      }, 
      {
        "familyName": "S\u00e1nchez Gonz\u00e1lez", 
        "givenName": "Lidia", 
        "type": "Person"
      }, 
      {
        "familyName": "Quinti\u00e1n", 
        "givenName": "H\u00e9ctor", 
        "type": "Person"
      }, 
      {
        "familyName": "Corchado", 
        "givenName": "Emilio", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-319-67180-2_50", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-319-67179-6", 
        "978-3-319-67180-2"
      ], 
      "name": "International Joint Conference SOCO\u201917-CISIS\u201917-ICEUTE\u201917 Le\u00f3n, Spain, September 6\u20138, 2017, Proceeding", 
      "type": "Book"
    }, 
    "keywords": [
      "query image", 
      "computer vision domain", 
      "object retrieval method", 
      "task of retrieving", 
      "cosine similarity score", 
      "query object", 
      "vision domain", 
      "CNN network", 
      "indoor scenes", 
      "Faster R", 
      "object detection", 
      "object retrieval", 
      "critical applications", 
      "feature vectors", 
      "cosine similarity", 
      "retrieval method", 
      "similar objects", 
      "big collection", 
      "neural code", 
      "similarity scores", 
      "specific objects", 
      "object present", 
      "region of interest", 
      "retrieval", 
      "confidence scores", 
      "objects", 
      "test set", 
      "images", 
      "code", 
      "queries", 
      "retrieving", 
      "scene", 
      "datasets", 
      "network", 
      "task", 
      "method", 
      "information", 
      "set", 
      "applications", 
      "system", 
      "detection", 
      "domain", 
      "collection", 
      "speed", 
      "vector", 
      "subset", 
      "similarity", 
      "interest", 
      "comprising", 
      "results", 
      "layer", 
      "present", 
      "scores", 
      "region", 
      "approach", 
      "paper", 
      "last inner-product layer", 
      "inner-product layer", 
      "ImageNet comprising", 
      "high cosine similarity scores"
    ], 
    "name": "Query Based Object Retrieval Using Neural Codes", 
    "pagination": "513-523", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1091287479"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-67180-2_50"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-67180-2_50", 
      "https://app.dimensions.ai/details/publication/pub.1091287479"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2021-11-01T19:01", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20211101/entities/gbq_results/chapter/chapter_57.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-319-67180-2_50"
  }
]
 

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.10.1007/978-3-319-67180-2_50'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-67180-2_50'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-67180-2_50'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-67180-2_50'


 

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

170 TRIPLES      23 PREDICATES      86 URIs      78 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-67180-2_50 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 anzsrc-for:0806
4 schema:author N6f732348ae9f4cb9b87792ab0b04323b
5 schema:datePublished 2017-08-23
6 schema:datePublishedReg 2017-08-23
7 schema:description The task of retrieving a specific object from an image, which is similar to a query object is one of the critical applications in the computer vision domain. The existing methods fail to return similar objects when the region of interest is not specified correctly in a query image. Furthermore, when the feature vector is large, the retrieval from big collections is usually computationally expensive. In this paper, we propose an object retrieval method, which is based on the neural codes (activations) generated by the last inner-product layer of the Faster R-CNN network demonstrating that it can be used not only for object detection but for retrieval too. To evaluate the method, we have used a subset of ImageNet comprising of images related to indoor scenes, and to speed-up the retrieval, we first process all the images from the dataset and we save information (i.e. neural codes, objects present in the image, confidence scores and bounding box coordinates) corresponding to each detected object. Then, given a query image, the system detects the object present and retrieves its neural codes, which are then used to compute the cosine similarity against saved neural codes. We retrieved objects with high cosine similarity scores, and then we compared it with the results obtained using confidence scores. We showed that our approach takes only 0.534 s to retrieve all the 1454 objects in our test set.
8 schema:editor N17768865d95c4146b67151186a2cb59d
9 schema:genre chapter
10 schema:inLanguage en
11 schema:isAccessibleForFree false
12 schema:isPartOf N3d0a1598b8fb442e81960c8a9cf632af
13 schema:keywords CNN network
14 Faster R
15 ImageNet comprising
16 applications
17 approach
18 big collection
19 code
20 collection
21 comprising
22 computer vision domain
23 confidence scores
24 cosine similarity
25 cosine similarity score
26 critical applications
27 datasets
28 detection
29 domain
30 feature vectors
31 high cosine similarity scores
32 images
33 indoor scenes
34 information
35 inner-product layer
36 interest
37 last inner-product layer
38 layer
39 method
40 network
41 neural code
42 object detection
43 object present
44 object retrieval
45 object retrieval method
46 objects
47 paper
48 present
49 queries
50 query image
51 query object
52 region
53 region of interest
54 results
55 retrieval
56 retrieval method
57 retrieving
58 scene
59 scores
60 set
61 similar objects
62 similarity
63 similarity scores
64 specific objects
65 speed
66 subset
67 system
68 task
69 task of retrieving
70 test set
71 vector
72 vision domain
73 schema:name Query Based Object Retrieval Using Neural Codes
74 schema:pagination 513-523
75 schema:productId N99a059e704d04c22b676485959a36e7b
76 N9bcafba77e364804bff5c1dfb3fe8ae9
77 schema:publisher N831425e903dd46ffab3bfe4c4f7582c2
78 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091287479
79 https://doi.org/10.1007/978-3-319-67180-2_50
80 schema:sdDatePublished 2021-11-01T19:01
81 schema:sdLicense https://scigraph.springernature.com/explorer/license/
82 schema:sdPublisher N7d8bc732775b46b2a22755ae66ce244b
83 schema:url https://doi.org/10.1007/978-3-319-67180-2_50
84 sgo:license sg:explorer/license/
85 sgo:sdDataset chapters
86 rdf:type schema:Chapter
87 N0b9d80319eca4fbabadfcda584f34696 rdf:first Nc33d8d34fb4e4aeda889ee7784119724
88 rdf:rest N37c0b95aea9b464db86c1ee560c12655
89 N17768865d95c4146b67151186a2cb59d rdf:first N5621b38a05af469e964f88c0efcc8077
90 rdf:rest N0b9d80319eca4fbabadfcda584f34696
91 N17cfc1626ede4f489d7d994735b7a5af schema:familyName Quintián
92 schema:givenName Héctor
93 rdf:type schema:Person
94 N20a831568bed4cbab5ea42ea6a67f48e rdf:first sg:person.010415303037.45
95 rdf:rest rdf:nil
96 N37c0b95aea9b464db86c1ee560c12655 rdf:first N8a6545bf5a9a414faf21c4152fe619b9
97 rdf:rest Ne23837f43ec748cfae4b2aa292c1ec9d
98 N3d0a1598b8fb442e81960c8a9cf632af schema:isbn 978-3-319-67179-6
99 978-3-319-67180-2
100 schema:name International Joint Conference SOCO’17-CISIS’17-ICEUTE’17 León, Spain, September 6–8, 2017, Proceeding
101 rdf:type schema:Book
102 N5206fbcb66654b068d106e620177dfd6 rdf:first sg:person.012664070017.21
103 rdf:rest Ned39a7f38a7a41a9aded06ca5a8fde77
104 N5621b38a05af469e964f88c0efcc8077 schema:familyName Pérez García
105 schema:givenName Hilde
106 rdf:type schema:Person
107 N6f732348ae9f4cb9b87792ab0b04323b rdf:first sg:person.013366561121.26
108 rdf:rest N5206fbcb66654b068d106e620177dfd6
109 N7d8bc732775b46b2a22755ae66ce244b schema:name Springer Nature - SN SciGraph project
110 rdf:type schema:Organization
111 N831425e903dd46ffab3bfe4c4f7582c2 schema:name Springer Nature
112 rdf:type schema:Organisation
113 N8a6545bf5a9a414faf21c4152fe619b9 schema:familyName Sánchez González
114 schema:givenName Lidia
115 rdf:type schema:Person
116 N99a059e704d04c22b676485959a36e7b schema:name doi
117 schema:value 10.1007/978-3-319-67180-2_50
118 rdf:type schema:PropertyValue
119 N9bcafba77e364804bff5c1dfb3fe8ae9 schema:name dimensions_id
120 schema:value pub.1091287479
121 rdf:type schema:PropertyValue
122 Na0b25ff30453438f813a625e320f40e5 rdf:first Nd331b8a0179c4248a65eb3b6522df1a5
123 rdf:rest rdf:nil
124 Nc33d8d34fb4e4aeda889ee7784119724 schema:familyName Alfonso-Cendón
125 schema:givenName Javier
126 rdf:type schema:Person
127 Nd331b8a0179c4248a65eb3b6522df1a5 schema:familyName Corchado
128 schema:givenName Emilio
129 rdf:type schema:Person
130 Ne23837f43ec748cfae4b2aa292c1ec9d rdf:first N17cfc1626ede4f489d7d994735b7a5af
131 rdf:rest Na0b25ff30453438f813a625e320f40e5
132 Ned39a7f38a7a41a9aded06ca5a8fde77 rdf:first sg:person.016266057305.75
133 rdf:rest N20a831568bed4cbab5ea42ea6a67f48e
134 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
135 schema:name Information and Computing Sciences
136 rdf:type schema:DefinedTerm
137 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
138 schema:name Artificial Intelligence and Image Processing
139 rdf:type schema:DefinedTerm
140 anzsrc-for:0806 schema:inDefinedTermSet anzsrc-for:
141 schema:name Information Systems
142 rdf:type schema:DefinedTerm
143 sg:person.010415303037.45 schema:affiliation grid-institutes:grid.4807.b
144 schema:familyName Fernández-Robles
145 schema:givenName Laura
146 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010415303037.45
147 rdf:type schema:Person
148 sg:person.012664070017.21 schema:affiliation grid-institutes:None
149 schema:familyName Fidalgo
150 schema:givenName Eduardo
151 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012664070017.21
152 rdf:type schema:Person
153 sg:person.013366561121.26 schema:affiliation grid-institutes:None
154 schema:familyName Saikia
155 schema:givenName Surajit
156 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013366561121.26
157 rdf:type schema:Person
158 sg:person.016266057305.75 schema:affiliation grid-institutes:None
159 schema:familyName Alegre
160 schema:givenName Enrique
161 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016266057305.75
162 rdf:type schema:Person
163 grid-institutes:None schema:alternateName Researcher at INCIBE (Spanish National Cybersecurity Institute), León, Spain
164 schema:name Department of Electrical, Systems and Automation, University of León, León, Spain
165 Researcher at INCIBE (Spanish National Cybersecurity Institute), León, Spain
166 rdf:type schema:Organization
167 grid-institutes:grid.4807.b schema:alternateName Department of Mechanical, Informatics and Aerospace Engineering, University of León, León, Spain
168 schema:name Department of Mechanical, Informatics and Aerospace Engineering, University of León, León, Spain
169 Researcher at INCIBE (Spanish National Cybersecurity Institute), León, Spain
170 rdf:type schema:Organization
 




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


...