This article will describe the details about integrating already generated metadata with Clowder.
Background
At the time of writing this document, there are about 171,000 images that were processed for extracting various features like faces, eyes, facial profile, close ups, printed text, presence of Stryker hole, presence of border, mean and standard deviation of grayscale values, subject details, photographer details, and category details. These are being done on Comet by using stripped down version of Clowder Extractors or in certain cases, by creating new standalone programs. Integrating this information with Clowder is important to use its features like RESTful API, authentication and authorization, available visualizations, etc.
PyClowder2
Write a short note about PyClowder2 - the latest version of Python library for writing Clowder extractors
Data Tables
The following set of data tables contain extracted metadata. Description of those tables are provided to understand the contents of the table
FacesInfo
Field Description | Database Column Name |
---|---|
LOC Index | id |
Image height | imght |
Image width | imgwid |
[ ]
Index ()
()
()
dumbX is just the letter F , it's only there to help browse raw data,
number of faces found (num_faces)
bounding box location of faces (face_segs)
this is a text string that has the ith-face,x,y,width,height of face segment
each face segment is separated by ';'
dumbX is just the letter P , it's only there to help browse raw data,
number of profiles found (num_profiles)
bounding box location of profiles (prof_segs)
dumbX is just the letter Y , it's only there to help browse raw data,
bounding box location of eyes (eye_segs)
dumbX is just the letter C , it's only there to help browse raw data,
number of face full closeups (num_fullcls) 'FULL' and 'MID' are relative to image size
number of face mid closeups (num_midcls)
number of profile full closeups (num_fullprof) 'FULL' and 'MID' are relative to image size
number of profile mid closeups (num_midprof)