Veneer21

Citation Author(s):
Tuomas
Jalonen
Tampere University
Firas
Laakom
Tampere University
Moncef
Gabbouj
Tampere University
Tuomas
Puoskari
Raute Corporation
Submitted by:
Tuomas Jalonen
Last updated:
Wed, 06/02/2021 - 04:27
DOI:
10.21227/vq7x-q108
Links:
License:
0
0 ratings - Please login to submit your rating.

Abstract 

This dataset consists of 2579 image pairs (5158 images in total) of wood veneers before and after drying. The high-resolution .png images (generally over 4000x4000) have a white background. The data has been collected from a real plywood factory. Raute Corporation is acknowledged for making this dataset public. The manufacturing process is well visualized here: https://www.youtube.com/watch?v=tjkIYCEVXko.

Our Veneer21 dataset can be used for visual product tracking as we demonstrate in our paper (cf. citation below). Other possible use cases include knot detection, knot segmentatio and other wood fault detection applications.

Please cite this as: 

T. Jalonen, F. Laakom, M. Gabbouj and T. Puoskari, "Visual Product Tracking System Using Siamese Neural Networks," in IEEE Access, vol. 9, pp. 76796-76805, 2021, doi: 10.1109/ACCESS.2021.3082934.

Instructions: 

There are two folders: "Dry" and "Wet". The "Wet" folder contains wet veneer images and the "Dry" folder dry veneer images. The files are numbered so that e.g. Wet_10 is an image of the same veneer as Dry_10, but the veneer has been dried in between.