Offline Writer Identification Using Convolutional Neural Network Activation Features

Abstract

Convolutional neural networks (CNNs) have recently become the state-of-the-art tool for large-scale image classification. In this work we propose the use of activation features from CNNs as local descriptors for writer identification. A global descriptor is then formed by means of GMM supervector encoding, which is further improved by normalization with the KL-Kernel. We evaluate our method on two publicly available datasets: the ICDAR 2013 benchmark database and the CVL dataset. While we perform comparably to the state of the art on CVL, our proposed method yields about 0.21 absolute improvement in terms of mAP on the challenging bilingual ICDAR dataset.

fixed tab 1b

References in corpus (1)

• Convolutional Neural Networks Applied to House Numbers Digit Classification

Cited by in corpus (10)

• FragNet: Writer Identification using Deep Fragment Networks
• Deep Generalized Max Pooling
• Text-independent writer identification using convolutional neural network
• Semi-supervised Feature Learning For Improving Writer Identification
• An Empirical Study on Writer Identification & Verification from Intra-variable Individual Handwriting
• Writer Identification and Writer Retrieval Based on NetVLAD with Re-ranking
• Writer Retrieval and Writer Identification in Greek Papyri
• Intra-Variable Handwriting Inspection Reinforced with Idiosyncrasy Analysis
• Unsupervised Feature Learning for Writer Identification and Writer Retrieval
• Contrastive Masked Autoencoders for Character-Level Open-Set Writer Identification