You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@mahout.apache.org by "Suneel Marthi (JIRA)" <ji...@apache.org> on 2016/12/26 23:26:58 UTC
[jira] [Commented] (MAHOUT-1898) Mahout for parsing/analysing
scanned medical images
[ https://issues.apache.org/jira/browse/MAHOUT-1898?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15779184#comment-15779184 ]
Suneel Marthi commented on MAHOUT-1898:
---------------------------------------
Firstly, this is a question that should have been posed on user@mahout.apache.org and not meant to be a Jira.
So if I understand ur question right, u r looking to parse scanned images and persist them in a DB. Mahout is a Machine Learning library, not a Data transformation/processing pipeline.
There are libraries out there that can read scanned images and convert them into pixels. This is not a ML issue, feel free to pose this question again user@mahout.apache.org.
> Mahout for parsing/analysing scanned medical images
> ---------------------------------------------------
>
> Key: MAHOUT-1898
> URL: https://issues.apache.org/jira/browse/MAHOUT-1898
> Project: Mahout
> Issue Type: Question
> Components: Classification, Clustering, Collaborative Filtering
> Reporter: Santhosh Kumar V S
> Fix For: 0.13.0
>
>
> We have a set of scaned images of medical records -this is unstructured data - Our requirement is to parse these documents and store in a structured format possibly in a
> Relation DB or Schemaless DB like MongoDB
> How Mahout will help in this usecase ?
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)