Online citations, reference lists, and bibliographies.

Offline Writer Identification Using Convolutional Neural Network Activation Features

Vincent Christlein, David Bernecker, A. Maier, E. Angelopoulou
Published 2015 · Computer Science

Cite This
Download PDF
Analyze on Scholarcy
Share
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 \(\mathrm {mAP}\) on the challenging bilingual ICDAR dataset.
This paper references
10.1016/j.patcog.2013.11.029
Writer identification using oriented Basic Image Features and the Delta encoding
A. J. Newell (2014)
10.1109/ICPR.2000.906196
Biometric personal identification based on handwriting
Yong Zhu (2000)
10.1007/978-3-319-10584-0_26
Multi-scale Orderless Pooling of Deep Convolutional Activation Features
Yunchao Gong (2014)
10.1109/TPAMI.2007.1009
Text-Independent Writer Identification and Verification Using Textural and Allographic Features
M. Bulacu (2007)
10.1109/ICDAR.2013.282
ICDAR 2013 Competition on Writer Identification
G. Louloudis (2013)
10.1109/ICPR.2014.353
Delta-n Hinge: Rotation-Invariant Features for Writer Identification
Sheng He (2014)
10.1007/978-3-319-10578-9_43
Boosting VLAD with Supervised Dictionary Learning and High-Order Statistics
Xiaojiang Peng (2014)
10.1109/ICDAR.2013.64
Feature Extraction with Convolutional Neural Networks for Handwritten Word Recognition
Théodore Bluche (2013)
10.1007/s11263-013-0636-x
Image Classification with the Fisher Vector: Theory and Practice
J. Sánchez (2013)
Convolutional neural networks applied to house numbers digit classification
Pierre Sermanet (2012)
10.1145/1772690.1772862
Web-scale k-means clustering
D. Sculley (2010)
Torch7: A Matlab-like Environment for Machine Learning
Ronan Collobert (2011)
10.1109/ICIP.2010.5653825
Extended Hierarchical Gaussianization for scene classification
Minqiang Xu (2010)
10.1145/3065386
ImageNet classification with deep convolutional neural networks
A. Krizhevsky (2017)
Aggregating Local Image Descriptors into Compact Codes
JégouHervé (2012)
10.1061/(ASCE)GT.1943-5606.0001284
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky (2012)
10.1007/978-3-319-10593-2_34
Deep Features for Text Spotting
Max Jaderberg (2014)
10.1109/ICDAR.2013.117
CVL-DataBase: An Off-Line Database for Writer Retrieval, Writer Identification and Word Spotting
F. Kleber (2013)
10.1109/CVPR.2014.417
Triangulation Embedding and Democratic Aggregation for Image Search
H. Jégou (2014)
10.1016/j.patcog.2011.07.005
Writer identification using directional ink-trace width measurements
Axel Brink (2012)
10.1109/TIFS.2014.2301274
Offline Text-Independent Writer Identification Based on Scale Invariant Feature Transform
Xiangqian Wu (2014)
10.1109/DAS.2014.76
Evaluation of Texture Features for Offline Arabic Writer Identification
Chawki Djeddi (2014)
10.1109/ICPR.2010.463
Scribe Identification in Medieval English Manuscripts
Tara Gilliam (2010)
10.1109/TPAMI.2004.18
Automatic writer identification using connected-component contours and edge-based features of uppercase Western script
Lambert Schomaker (2004)
Deep Learning of Representations for Unsupervised and Transfer Learning
Yoshua Bengio (2012)
10.1109/ICFHR.2014.103
Combining Local Features for Offline Writer Identification
R. Jain (2014)
10.1109/ICDAR.2013.115
Writer Identification Using an Alphabet of Contour Gradient Descriptors
R. Jain (2013)
Maximum Likelihood from Incomplete Data via the EM Algorithm
A. D. E. Altri (1977)
10.1006/dspr.1999.0361
Speaker Verification Using Adapted Gaussian Mixture Models
D. Reynolds (2000)
10.1109/ICDAR.2013.114
Writer Identification and Writer Retrieval Using the Fisher Vector on Visual Vocabularies
S. Fiel (2013)
10.1016/j.patcog.2010.05.019
Text independent writer recognition using redundant writing patterns with contour-based orientation and curvature features
I. Siddiqi (2010)
10.1109/WACV.2014.6835995
Writer identification and verification using GMM supervectors
Vincent Christlein (2014)



This paper is referenced by
10.1016/j.asoc.2020.106277
Local gradient full-scale transform patterns based off-line text-independent writer identification
Abderrazak Chahi (2020)
10.1109/ACCESS.2019.2927286
Length Independent Writer Identification Based on the Fusion of Deep and Hand-Crafted Descriptors
Alaa Sulaiman (2019)
10.1109/ICDAR.2019.00124
Online Writer Identification using GMM Based Feature Representation and Writer-Specific Weights
V. Venugopal (2019)
10.1109/DAS.2018.9
Encoding CNN Activations for Writer Recognition
Vincent Christlein (2018)
10.1109/TIFS.2018.2823276
Online Writer Identification With Sparse Coding-Based Descriptors
V. Venugopal (2018)
10.1109/TIFS.2020.2981236
FragNet: Writer Identification Using Deep Fragment Networks
Sheng He (2020)
10.1109/ICDAR.2017.37
Legibility and Aesthetic Analysis of Handwriting
Chandranath Adak (2017)
10.1109/ACCESS.2018.2890810
Automatic Visual Features for Writer Identification: A Deep Learning Approach
A. Rehman (2019)
10.1016/j.ins.2019.01.024
Semi-supervised feature learning for improving writer identification
S. Chen (2019)
10.1109/ICDAR.2019.00159
Deep Learning Based Approach for Historical Manuscript Dating
Anmol Hamid (2019)
10.1016/j.patrec.2018.07.022
Text-independent writer identification using convolutional neural network
H. T. Nguyen (2019)
10.1109/TIFS.2020.2991833
Intra-Variable Handwriting Inspection Reinforced With Idiosyncrasy Analysis
Chandranath Adak (2020)
10.12792/ICISIP2017.020
Writer Identification for Offline Japanese Handwritten Character using Convolutional Neural Network
Ryosuke Nasuno (2017)
10.1109/ICFHR.2016.0109
Text-Independent Writer Identification via CNN Features and Joint Bayesian
Y. Tang (2016)
10.1109/ICDAR.2017.165
Unsupervised Feature Learning for Writer Identification and Writer Retrieval
Vincent Christlein (2017)
10.1109/ICFHR-2018.2018.00083
Offline Text-Independent Writer Identification Based on Writer-Independent Model using Conditional AutoEncoder
Mariko Hosoe (2018)
10.1109/ICGS3.2019.8688032
A Comparative Study of Machine Learning Approaches for Handwriter Identification
Amal Durou (2019)
10.1142/S0218001417560080
Off-line Text-Independent Writer Recognition: A Survey
Yujie Xiong (2017)
10.1007/978-3-662-54345-0_6
Tutorial: Deep Learning Advancing the State-of-the-Art in Medical Image Analysis
Vincent Christlein (2017)
10.1109/ACCESS.2019.2899908
An Empirical Study on Writer Identification and Verification From Intra-Variable Individual Handwriting
Chandranath Adak (2019)
10.1007/978-3-030-57058-3
Document Analysis Systems: 14th IAPR International Workshop, DAS 2020, Wuhan, China, July 26–29, 2020, Proceedings
X. Bai (2020)
10.1109/TIFS.2020.2991880
Encoding Pathlet and SIFT Features With Bagged VLAD for Historical Writer Identification
Songxuan Lai (2020)
10.1016/j.engappai.2019.103459
Cross multi-scale locally encoded gradient patterns for off-line text-independent writer identification
Abderrazak Chahi (2020)
10.1007/978-3-030-57058-3_40
Re-ranking for Writer Identification and Writer Retrieval
S. Jordan (2020)
10.1016/j.compeleceng.2020.106707
Segmentation-free writer identification based on convolutional neural network
Parveen Kumar (2020)
10.1007/s11042-018-6577-1
Writer identification using machine learning approaches: a comprehensive review
A. Rehman (2018)
Unsupervised feature learning for writer identification
Eduard Pallàs Arranz (2018)
Multi-Frame Super-Resolution Reconstruction with Applications to Medical Imaging
Thomas Kohler (2018)
10.1109/icdar.2019.00177
Deep Generalized Max Pooling
Vincent Christlein (2019)
Semantic Scholar Logo Some data provided by SemanticScholar