[
https://issues.apache.org/jira/browse/SPARK-8486?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Feynman Liang updated SPARK-8486:
---------------------------------
Description:
Scale invariant feature transform (SIFT) is a method to transform images into
dense vectors describing local features which are invariant to scale and
rotation. (Lowe, IJCV 2004, http://www.cs.ubc.ca/~lowe/papers/ijcv04.pdf)
We can implement SIFT in Spark ML pipelines as a
[[org.apache.spark.ml.Transformer]]. Given an image Array[Array[Numeric]], the
SIFT transformer should output an Array[Numeric] of the SIFT features present
in the image.
Depending on performance, approximating Laplacian of Gaussian by Difference of
Gaussian (aka SURF) as described by Lowe can be even further improved using box
filters (Bay, ECCV 2006, http://www.vision.ee.ethz.ch/~surf/eccv06.pdf).
was:
Scale invariant feature transform (SIFT) is a method to transform images into
dense vectors describing local features which are invariant to scale and
rotation. (Lowe, IJCV 2004, http://www.cs.ubc.ca/~lowe/papers/ijcv04.pdf)
We can implement SIFT in Spark ML pipelines as a
[[org.apache.spark.ml.Transformer]]. Given an image Array[Array[Numeric]], the
SIFT transformer should output an Array[Numeric] of the SIFT features present
in the image.
Depending on performance, approximating Laplacian of Gaussian by Difference of
Gaussian as described by Lowe can be even further improved using box filters
(Bay, ECCV 2006, http://www.vision.ee.ethz.ch/~surf/eccv06.pdf).
> SIFT/SURF Feature Extractor
> ---------------------------
>
> Key: SPARK-8486
> URL: https://issues.apache.org/jira/browse/SPARK-8486
> Project: Spark
> Issue Type: Sub-task
> Components: ML
> Reporter: Feynman Liang
>
> Scale invariant feature transform (SIFT) is a method to transform images into
> dense vectors describing local features which are invariant to scale and
> rotation. (Lowe, IJCV 2004, http://www.cs.ubc.ca/~lowe/papers/ijcv04.pdf)
> We can implement SIFT in Spark ML pipelines as a
> [[org.apache.spark.ml.Transformer]]. Given an image Array[Array[Numeric]],
> the SIFT transformer should output an Array[Numeric] of the SIFT features
> present in the image.
> Depending on performance, approximating Laplacian of Gaussian by Difference
> of Gaussian (aka SURF) as described by Lowe can be even further improved
> using box filters (Bay, ECCV 2006,
> http://www.vision.ee.ethz.ch/~surf/eccv06.pdf).
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
