Image Classification

classic Classic list List threaded Threaded
6 messages Options
Reply | Threaded
Open this post in threaded view
|

Image Classification

toddhay
Greetings Everyone- Does anyone have an image classification extension to Opticks that includes both unsupervised and supervised techniques? I would be quite interested in using it on a current project. Thanks. Todd
Reply | Threaded
Open this post in threaded view
|

Re: Image Classification

tclarke
Administrator

Not quite..kstreith is working on some hyperspectral classification plug-ins (I believe he’s working on an ISODATA algorithm first). I’m not sure when he expects to have this done, he could tell you more. (he’s on vacation today so he may not respond for a few days) There’s also a basic k-means based algorithms written by dadkins. I’m not sure if he’s published the code but he may be able to make that available for you. Finally, if you are affiliated with the US government, there’s additional hyperspectral capability which we can provide for you, including some classification algorithms.

 

 

From: toddhay [mailto:[hidden email]]
Sent: Wednesday, December 22, 2010 7:18 PM
To: [hidden email]
Subject: [Opticks-devs] Image Classification

 

Greetings Everyone- Does anyone have an image classification extension to Opticks that includes both unsupervised and supervised techniques? I would be quite interested in using it on a current project. Thanks. Todd


View this message in context: Image Classification
Sent from the opticks-devs mailing list archive at Nabble.com.


This message and any enclosures are intended only for the addressee.  Please  
notify the sender by email if you are not the intended recipient.  If you are  
not the intended recipient, you may not use, copy, disclose, or distribute this  
message or its contents or enclosures to any other person and any such actions  
may be unlawful.  Ball reserves the right to monitor and review all messages  
and enclosures sent to or from this email address.

------------------------------------------------------------------------------
Learn how Oracle Real Application Clusters (RAC) One Node allows customers
to consolidate database storage, standardize their database environment, and,
should the need arise, upgrade to a full multi-node Oracle RAC database
without downtime or disruption
http://p.sf.net/sfu/oracle-sfdevnl
_______________________________________________
Opticks-devs mailing list
[hidden email]
https://lists.sourceforge.net/lists/listinfo/opticks-devs
Reply | Threaded
Open this post in threaded view
|

Re: Image Classification

Kip Streithorst
Administrator

I was planning on implementing an ISODATA unsupervised classifier, but I haven’t started work on that.

 

Does anyone have thoughts on preferred classifiers?

 

Thanks,

Kip

 

From: Clarke, Trevor [mailto:[hidden email]]
Sent: Thursday, December 23, 2010 8:41 AM
To: [hidden email]
Subject: Re: [Opticks-devs] Image Classification

 

Not quite..kstreith is working on some hyperspectral classification plug-ins (I believe he’s working on an ISODATA algorithm first). I’m not sure when he expects to have this done, he could tell you more. (he’s on vacation today so he may not respond for a few days) There’s also a basic k-means based algorithms written by dadkins. I’m not sure if he’s published the code but he may be able to make that available for you. Finally, if you are affiliated with the US government, there’s additional hyperspectral capability which we can provide for you, including some classification algorithms.

 

 

From: toddhay [mailto:[hidden email]]
Sent: Wednesday, December 22, 2010 7:18 PM
To: [hidden email]
Subject: [Opticks-devs] Image Classification

 

Greetings Everyone- Does anyone have an image classification extension to Opticks that includes both unsupervised and supervised techniques? I would be quite interested in using it on a current project. Thanks. Todd


View this message in context: Image Classification
Sent from the opticks-devs mailing list archive at Nabble.com.

 
 
This message and any enclosures are intended only for the addressee.  Please  
notify the sender by email if you are not the intended recipient.  If you are  
not the intended recipient, you may not use, copy, disclose, or distribute this  
message or its contents or enclosures to any other person and any such actions  
may be unlawful.  Ball reserves the right to monitor and review all messages  
and enclosures sent to or from this email address.

This message and any enclosures are intended only for the addressee.  Please  
notify the sender by email if you are not the intended recipient.  If you are  
not the intended recipient, you may not use, copy, disclose, or distribute this  
message or its contents or enclosures to any other person and any such actions  
may be unlawful.  Ball reserves the right to monitor and review all messages  
and enclosures sent to or from this email address.

------------------------------------------------------------------------------
Learn how Oracle Real Application Clusters (RAC) One Node allows customers
to consolidate database storage, standardize their database environment, and,
should the need arise, upgrade to a full multi-node Oracle RAC database
without downtime or disruption
http://p.sf.net/sfu/oracle-sfdevnl
_______________________________________________
Opticks-devs mailing list
[hidden email]
https://lists.sourceforge.net/lists/listinfo/opticks-devs
Reply | Threaded
Open this post in threaded view
|

Re: Image Classification

dadkins
Administrator

The K-Means code I wrote has been submitted. Track its progress and comment/vote at: https://issues.ballforge.net/jira/browse/EXTRAS-104

 

From: Streithorst, Kip [mailto:[hidden email]]
Sent: Monday, December 27, 2010 8:38 AM
To: Clarke, Trevor; [hidden email]
Subject: Re: [Opticks-devs] Image Classification

 

I was planning on implementing an ISODATA unsupervised classifier, but I haven’t started work on that.

 

Does anyone have thoughts on preferred classifiers?

 

Thanks,

Kip

 

From: Clarke, Trevor [mailto:[hidden email]]
Sent: Thursday, December 23, 2010 8:41 AM
To: [hidden email]
Subject: Re: [Opticks-devs] Image Classification

 

Not quite..kstreith is working on some hyperspectral classification plug-ins (I believe he’s working on an ISODATA algorithm first). I’m not sure when he expects to have this done, he could tell you more. (he’s on vacation today so he may not respond for a few days) There’s also a basic k-means based algorithms written by dadkins. I’m not sure if he’s published the code but he may be able to make that available for you. Finally, if you are affiliated with the US government, there’s additional hyperspectral capability which we can provide for you, including some classification algorithms.

 

 

From: toddhay [mailto:[hidden email]]
Sent: Wednesday, December 22, 2010 7:18 PM
To: [hidden email]
Subject: [Opticks-devs] Image Classification

 

Greetings Everyone- Does anyone have an image classification extension to Opticks that includes both unsupervised and supervised techniques? I would be quite interested in using it on a current project. Thanks. Todd


View this message in context: Image Classification
Sent from the opticks-devs mailing list archive at Nabble.com.

 
 
This message and any enclosures are intended only for the addressee.  Please  
notify the sender by email if you are not the intended recipient.  If you are  
not the intended recipient, you may not use, copy, disclose, or distribute this  
message or its contents or enclosures to any other person and any such actions  
may be unlawful.  Ball reserves the right to monitor and review all messages  
and enclosures sent to or from this email address.
 
 
This message and any enclosures are intended only for the addressee.  Please  
notify the sender by email if you are not the intended recipient.  If you are  
not the intended recipient, you may not use, copy, disclose, or distribute this  
message or its contents or enclosures to any other person and any such actions  
may be unlawful.  Ball reserves the right to monitor and review all messages  
and enclosures sent to or from this email address.

This message and any enclosures are intended only for the addressee.  Please  
notify the sender by email if you are not the intended recipient.  If you are  
not the intended recipient, you may not use, copy, disclose, or distribute this  
message or its contents or enclosures to any other person and any such actions  
may be unlawful.  Ball reserves the right to monitor and review all messages  
and enclosures sent to or from this email address.

------------------------------------------------------------------------------
Learn how Oracle Real Application Clusters (RAC) One Node allows customers
to consolidate database storage, standardize their database environment, and,
should the need arise, upgrade to a full multi-node Oracle RAC database
without downtime or disruption
http://p.sf.net/sfu/oracle-sfdevnl
_______________________________________________
Opticks-devs mailing list
[hidden email]
https://lists.sourceforge.net/lists/listinfo/opticks-devs
Reply | Threaded
Open this post in threaded view
|

Re: Image Classification

Todd Hay
I would be interested in seeing the following classifiers:
 
K-Means
ISOData/ISOCluster
Maximum Likelihood
 
Thanks.
 
Todd

On Tue, Dec 28, 2010 at 8:12 AM, Adkins, Dustan <[hidden email]> wrote:

The K-Means code I wrote has been submitted. Track its progress and comment/vote at: https://issues.ballforge.net/jira/browse/EXTRAS-104

 

From: Streithorst, Kip [mailto:[hidden email]]
Sent: Monday, December 27, 2010 8:38 AM
To: Clarke, Trevor; [hidden email]


Subject: Re: [Opticks-devs] Image Classification

 

I was planning on implementing an ISODATA unsupervised classifier, but I haven’t started work on that.

 

Does anyone have thoughts on preferred classifiers?

 

Thanks,

Kip

 

From: Clarke, Trevor [mailto:[hidden email]]

Sent: Thursday, December 23, 2010 8:41 AM
Subject: Re: [Opticks-devs] Image Classification

 

Not quite..kstreith is working on some hyperspectral classification plug-ins (I believe he’s working on an ISODATA algorithm first). I’m not sure when he expects to have this done, he could tell you more. (he’s on vacation today so he may not respond for a few days) There’s also a basic k-means based algorithms written by dadkins. I’m not sure if he’s published the code but he may be able to make that available for you. Finally, if you are affiliated with the US government, there’s additional hyperspectral capability which we can provide for you, including some classification algorithms.

 

 

From: toddhay [mailto:[hidden email]]

Sent: Wednesday, December 22, 2010 7:18 PM
Subject: [Opticks-devs] Image Classification

 

Greetings Everyone- Does anyone have an image classification extension to Opticks that includes both unsupervised and supervised techniques? I would be quite interested in using it on a current project. Thanks. Todd


View this message in context: Image Classification
Sent from the opticks-devs mailing list archive at Nabble.com.

 
 
This message and any enclosures are intended only for the addressee.  Please  
notify the sender by email if you are not the intended recipient.  If you are  
not the intended recipient, you may not use, copy, disclose, or distribute this  
message or its contents or enclosures to any other person and any such actions  
may be unlawful.  Ball reserves the right to monitor and review all messages  
and enclosures sent to or from this email address.
 
 
This message and any enclosures are intended only for the addressee.  Please  
notify the sender by email if you are not the intended recipient.  If you are  
not the intended recipient, you may not use, copy, disclose, or distribute this  
message or its contents or enclosures to any other person and any such actions  
may be unlawful.  Ball reserves the right to monitor and review all messages  
and enclosures sent to or from this email address.
This message and any enclosures are intended only for the addressee.  Please  
notify the sender by email if you are not the intended recipient.  If you are  
not the intended recipient, you may not use, copy, disclose, or distribute this  
message or its contents or enclosures to any other person and any such actions  
may be unlawful.  Ball reserves the right to monitor and review all messages  
and enclosures sent to or from this email address.

------------------------------------------------------------------------------
Learn how Oracle Real Application Clusters (RAC) One Node allows customers
to consolidate database storage, standardize their database environment, and,
should the need arise, upgrade to a full multi-node Oracle RAC database
without downtime or disruption
http://p.sf.net/sfu/oracle-sfdevnl
_______________________________________________
Opticks-devs mailing list
[hidden email]
https://lists.sourceforge.net/lists/listinfo/opticks-devs



------------------------------------------------------------------------------
Learn how Oracle Real Application Clusters (RAC) One Node allows customers
to consolidate database storage, standardize their database environment, and,
should the need arise, upgrade to a full multi-node Oracle RAC database
without downtime or disruption
http://p.sf.net/sfu/oracle-sfdevnl
_______________________________________________
Opticks-devs mailing list
[hidden email]
https://lists.sourceforge.net/lists/listinfo/opticks-devs
Reply | Threaded
Open this post in threaded view
|

Re: Image Classification

Kip Streithorst
Administrator

It’s good to get confirmation that I was thinking in the right direction.  I’m knee deep in upgrading Opticks to Visual Studio 2010 at the moment, but I’ll look into these after that.

 

My plan was to prototype them first using the Python Scripting Extension before writing full fledged C++ Opticks plug-ins for the algorithms.

 

Thanks,

Kip

 

From: Todd Hay [mailto:[hidden email]]
Sent: Thursday, December 30, 2010 5:24 PM
To: Adkins, Dustan
Cc: Streithorst, Kip; Clarke, Trevor; [hidden email]
Subject: Re: [Opticks-devs] Image Classification

 

I would be interested in seeing the following classifiers:

 

K-Means

ISOData/ISOCluster

Maximum Likelihood

 

Thanks.

 

Todd

On Tue, Dec 28, 2010 at 8:12 AM, Adkins, Dustan <[hidden email]> wrote:

The K-Means code I wrote has been submitted. Track its progress and comment/vote at: https://issues.ballforge.net/jira/browse/EXTRAS-104

 

From: Streithorst, Kip [mailto:[hidden email]]
Sent: Monday, December 27, 2010 8:38 AM
To: Clarke, Trevor; [hidden email]


Subject: Re: [Opticks-devs] Image Classification

 

I was planning on implementing an ISODATA unsupervised classifier, but I haven’t started work on that.

 

Does anyone have thoughts on preferred classifiers?

 

Thanks,

Kip

 

From: Clarke, Trevor [mailto:[hidden email]]

Sent: Thursday, December 23, 2010 8:41 AM

Subject: Re: [Opticks-devs] Image Classification

 

Not quite..kstreith is working on some hyperspectral classification plug-ins (I believe he’s working on an ISODATA algorithm first). I’m not sure when he expects to have this done, he could tell you more. (he’s on vacation today so he may not respond for a few days) There’s also a basic k-means based algorithms written by dadkins. I’m not sure if he’s published the code but he may be able to make that available for you. Finally, if you are affiliated with the US government, there’s additional hyperspectral capability which we can provide for you, including some classification algorithms.

 

 

From: toddhay [mailto:[hidden email]]

Sent: Wednesday, December 22, 2010 7:18 PM

Subject: [Opticks-devs] Image Classification

 

Greetings Everyone- Does anyone have an image classification extension to Opticks that includes both unsupervised and supervised techniques? I would be quite interested in using it on a current project. Thanks. Todd


View this message in context: Image Classification
Sent from the opticks-devs mailing list archive at Nabble.com.

 
 
This message and any enclosures are intended only for the addressee.  Please  
notify the sender by email if you are not the intended recipient.  If you are  
not the intended recipient, you may not use, copy, disclose, or distribute this  
message or its contents or enclosures to any other person and any such actions  
may be unlawful.  Ball reserves the right to monitor and review all messages  
and enclosures sent to or from this email address.
 
 
This message and any enclosures are intended only for the addressee.  Please  
notify the sender by email if you are not the intended recipient.  If you are  
not the intended recipient, you may not use, copy, disclose, or distribute this  
message or its contents or enclosures to any other person and any such actions  
may be unlawful.  Ball reserves the right to monitor and review all messages  
and enclosures sent to or from this email address.
This message and any enclosures are intended only for the addressee.  Please  
notify the sender by email if you are not the intended recipient.  If you are  
not the intended recipient, you may not use, copy, disclose, or distribute this  
message or its contents or enclosures to any other person and any such actions  
may be unlawful.  Ball reserves the right to monitor and review all messages  
and enclosures sent to or from this email address.


------------------------------------------------------------------------------
Learn how Oracle Real Application Clusters (RAC) One Node allows customers
to consolidate database storage, standardize their database environment, and,
should the need arise, upgrade to a full multi-node Oracle RAC database
without downtime or disruption
http://p.sf.net/sfu/oracle-sfdevnl
_______________________________________________
Opticks-devs mailing list
[hidden email]
https://lists.sourceforge.net/lists/listinfo/opticks-devs

 


This message and any enclosures are intended only for the addressee.  Please  
notify the sender by email if you are not the intended recipient.  If you are  
not the intended recipient, you may not use, copy, disclose, or distribute this  
message or its contents or enclosures to any other person and any such actions  
may be unlawful.  Ball reserves the right to monitor and review all messages  
and enclosures sent to or from this email address.

------------------------------------------------------------------------------
Learn how Oracle Real Application Clusters (RAC) One Node allows customers
to consolidate database storage, standardize their database environment, and,
should the need arise, upgrade to a full multi-node Oracle RAC database
without downtime or disruption
http://p.sf.net/sfu/oracle-sfdevnl
_______________________________________________
Opticks-devs mailing list
[hidden email]
https://lists.sourceforge.net/lists/listinfo/opticks-devs