ICDAR 2026 Competition on Writer Identification and Pen Classification from Hand-Drawn Circles

TL;DR

CircleID is a large-scale ICDAR 2026 competition dataset and benchmark for writer identification and pen classification from hand-drawn circles, highlighting challenges in biometric and physical pen feature recognition.

Contribution

This paper introduces a new dataset, competition tasks, and baseline results for writer and pen classification from minimal hand-drawn traces.

Findings

Best writer identification accuracy: 64.8%

Best pen classification accuracy: 92.7%

Large-scale dataset with 46,155 samples from 66 writers and 8 pens

Abstract

This paper presents CircleID, a large-scale ICDAR 2026 competition on writer identification and pen classification from scanned hand-drawn circles. The primary objective is to investigate how biometric writer characteristics and physical pen features naturally entangle within minimal, static traces. CircleID comprises two distinct tasks: (1) open-set writer identification, requiring models to recognize known writers while explicitly rejecting unknown ones, and (2) cross-writer pen classification, evaluated across both seen and unseen writers. Participants were provided with a new, controlled dataset of 46,155 tightly cropped circle images, digitized at 400 DPI and annotated for writer identity and pen type. The dataset comprises samples from 44 known and 22 unknown writers using eight different pens. Hosted on Kaggle as two separate tracks with public and private leaderboards, the competition provided participants with a ResNet baseline. In total, 389 teams (436 participants) made 3,185 submissions for the pen classification task, and 113 teams (141 participants) made 1,737 submissions for the writer identification track. The best-performing private leaderboard submissions achieved a Top-1 accuracy of 64.801% for writer identification and 92.726% for pen classification. This paper details the dataset, evaluates the winning methodologies, and analyzes the impact of out-of-distribution writers on model generalization and feature disentanglement. In this large-scale competition, CircleID establishes a new baseline for minimal-trace analysis.