Statements (29)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
computer vision technique
|
| gptkbp:alsoKnownAs |
gptkb:BoVW
|
| gptkbp:alternativeTo |
CNN-based features
|
| gptkbp:application |
gptkb:machine_learning
computer vision |
| gptkbp:clusteringAlgorithm |
gptkb:k-means
|
| gptkbp:feature |
gptkb:SIFT
gptkb:ORB gptkb:SURF |
| gptkbp:featureExtractionMethod |
yes
|
| gptkbp:featureVectorLength |
number of clusters in vocabulary
|
| https://www.w3.org/2000/01/rdf-schema#label |
Bag of Visual Words
|
| gptkbp:inspiredBy |
gptkb:Bag_of_Words_model
|
| gptkbp:limitation |
ignores spatial information
|
| gptkbp:processor |
cluster features to form visual vocabulary
extract local features from images represent images as histograms of visual words |
| gptkbp:proposedBy |
2000s
|
| gptkbp:relatedTo |
gptkb:Spatial_Pyramid_Matching
deep learning Bag of Words |
| gptkbp:representationType |
gptkb:Vector
|
| gptkbp:usedFor |
scene recognition
image annotation |
| gptkbp:usedIn |
image classification
object recognition image retrieval |
| gptkbp:bfsParent |
gptkb:Computer_Vision
|
| gptkbp:bfsLayer |
6
|