Dataset

Firemaker image collection for benchmarking forensic writer identification using image-based pattern recognition

Schomaker, L. (Creator), Vuurpijl, L. (Creator), University of Groningen, 1-Jan-2000

Dataset

Description

This distribution contains 1000 images of scanned handwritten text, scanned at resolution 300dpi grey scale, containing pages of handwritten text by 250 writers, four pages per writer, from four writing conditions, one condition per page. The conditions are:
p1: copied, natural style, p2: copied, UPPER case, p3: copied and forged, i.e.,"try to write in adifferent style than your natural style", and p4,
self generated, i.e., text produced to describe a given cartoon.
Date made available1-Jan-2000
PublisherUniversity of Groningen
Access to the dataset Open
Contact researchdata@rug.nl

    Keywords on Datasets

  • writer identification, image data set, handwriting, benchmarking, Monk Project
Related Publications
  1. Automatic writer identification using connected-component contours and edge-based features of uppercase western script

    Schomaker, L. & Bulacu, M., Jun-2004, In : Ieee transactions on pattern analysis and machine intelligence. 26, 6, p. 787-798 12 p.

    Research output: Contribution to journalArticleAcademicpeer-review

View all (1) »

ID: 67052155