READ ME

This text describes the data presented in the paper: <insert paper title> 

========================
Introductory information
========================
Files included in the data deposit (include a short description of what data are contained): 

1)Pinch: Contains pictures (5184x3456 pixels) of 19 objects including 72 different views of them taken in 5 degrees intervals.
2)Tripod: Contains pictures (5184x3456 pixels) of 11 objects including 72 different views of them taken in 5 degrees intervals.
3)Palmar_Wrist_Neutral: Contains pictures (5184x3456 pixels) of 30 objects including 72 different views of them taken in 5 degrees intervals.
4)Palmar_Wrist_Pronated: Contains pictures (5184x3456 pixels) of 11 objects including 72 different views of them taken in 5 degrees intervals.


Explain the relationship between multiple data sets, if required:

The images are taken in the same condition as Amsterdam Library of Images (ALOI): http://aloi.science.uva.nl/.
As access to the same objects that were used to create the ALOI database was not possible, Newcastle database is built to enable us to perform real-time analysis.
The distance between the camera and the object was 60 cm and the webcam was 15 cm higher than object. With this setting we could achieve images of objects that were
comparable in size with those available in the ALOI database.

Key words used to describe the data:

Graspable objects database, Household objects database, Newcastle grasp library


========================== 
Methodological information
==========================
A brief method description – what the data is, how and why it was collected or created, and how it was processed:

Newcastle grasp library consists of pictures of 71 household objects, 72 different views for each object taken at 5 degree intervals. The images are taken in the 
same condition as Amsterdam Library of Images (ALOI). As access to the same objects that were used to create the ALOI database was not possible, Newcastle database 
is built to enable us to perform real-time analysis.
We synchronised a Crayfish 55 turntable (Seabass, UK) with a Canon Kiss X4 DSLR camera (resolution 18 Megapixel, 5184x3456 pixels)
to take 72 pictures from each object (at 5 intervals) against a black background. 
To ensure object size is taken into account we positioned the camera at a fixed distance from objects when collecting the images. The distance between the camera and 
the object was 60 cm and the webcam was 15 cm higher than object. With this setting we could achieve images of objects that were
comparable in size with those available in the ALOI database.
The provided data includes the original images.


Instruments, hardware and software used: 

- Canon Kiss X4 DSLR camera (resolution 18 Megapixel, 5184x3456 pixels)
- Crayfish 55 turntable (Seabass, UK)


Date(s) of data collection: 

December 2015


Geographic coverage of data:



Data validation (how was the data checked, proofed and cleaned):



Overview of secondary data, if used:



=========================
Data-specific information
=========================
Definitions of names, labels, acronyms or specialist terminology uses for variables, records and their values: 

The labels we used for grasp classification in the paper "Deep learning-based artificial vision for grasp classification in myoelectric hands" are the folder names:
Pinch, Tripod, Palmar_Wrist_Neutral, Palmar_Wrist_Pronated.
For object detection, file names can be used as the labels.


Explanation of weighting and grossing variables: 



Outline any missing data:



=======
Contact
=======
Please contact rdm@ncl.ac.uk for further information