Multiple writer retrieval systems based on language independent dissimilarity learning

Abstract Retrieval based on query images supports interesting applications in handwritten document analysis, such as checking manuscripts originality, and authorship. In this respect, writer retrieval systems aim to automatically find all manuscripts belonging to the same author. Presently, we propose a new combination scheme for multiple writer retrieval systems that employ different features and dissimilarities. The proposed combination is founded on writer-independent, SVM dissimilarity learning. For experimental evaluation, three individual systems are proposed each of which, has its specific features. To develop the first system, we propose the Multiscale Histogram Of Templates (M-HOT). For the second system, we introduce the so-called Multi-Gradient Elongated Quinary Pattern (MG-EQP) as new descriptor for handwriting characterization. The third system uses the well-known Run Length Features. Retrieval tests are performed on CVL, ICDAR-2011, ICDAR-2013 and ICDAR-2017 datasets. Furthermore, to highlight the language-independence aspect, experiments are performed on KHATT dataset that contains Arabic handwritten documents. Results obtained evince the effectiveness of the proposed features as well as the combination scheme, which outperforms both individual systems and the state of the art.

[1]  Mohammad Alshayeb,et al.  KHATT: Arabic Offline Handwritten Text Database , 2012, 2012 International Conference on Frontiers in Handwriting Recognition.

[2]  Alice Caplier,et al.  Enhanced Patterns of Oriented Edge Magnitudes for Face Recognition and Image Matching , 2012, IEEE Transactions on Image Processing.

[3]  Sargur N. Srihari,et al.  Information Retrieval System for Handwritten Documents , 2004, Document Analysis Systems.

[4]  Laurence Likforman-Sulem,et al.  Writer Retrieval - Exploration of a Novel Biometric Scenario Using Perceptual Features Derived from Script Orientation , 2011, 2011 International Conference on Document Analysis and Recognition.

[5]  Liu Jianzhuang,et al.  Automatic thresholding of gray-level pictures using two-dimension Otsu method , 1991, China., 1991 International Conference on Circuits and Systems.

[6]  Hassiba Nemmour,et al.  Evaluation of Gradient Descriptors and Dissimilarity Learning for Writer Retrieval , 2018, 2018 Eighth International Conference on Information Science and Technology (ICIST).

[7]  Robert Sablatnig,et al.  Writer Retrieval and Writer Identification Using Local Features , 2012, 2012 10th IAPR International Workshop on Document Analysis Systems.

[8]  Shu Liao,et al.  Face Recognition by Using Elongated Local Binary Patterns with Average Maximum Distance Gradient Magnitude , 2007, ACCV.

[9]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[10]  Yassine Ruichek,et al.  An effective and conceptually simple feature representation for off-line text-independent writer identification , 2019, Expert Syst. Appl..

[11]  Hassiba Nemmour,et al.  Writer Retrieval Using Histogram Of Templates Features and SVM , 2017 .

[12]  Loris Nanni,et al.  Overview of the combination of biometric matchers , 2017, Inf. Fusion.

[13]  Labiba Souici-Meslati,et al.  Text-independent writer recognition using multi-script handwritten texts , 2013, Pattern Recognit. Lett..

[14]  Robert Sablatnig,et al.  Writer Identification and Retrieval Using a Convolutional Neural Network , 2015, CAIP.

[15]  M. S. Shirdhonkar,et al.  Writer Based Handwritten Document Image Retrieval Using Contourlet Transform , 2011 .

[16]  Yassine Ruichek,et al.  Block wise local binary count for off-Line text-independent writer identification , 2018, Expert Syst. Appl..

[17]  Alessandro Vinciarelli,et al.  Application of information retrieval techniques to single writer documents , 2005, Pattern Recognit. Lett..

[18]  A. Papandreou,et al.  ICDAR 2013 Competition on Writer Identification , 2013, 2013 12th International Conference on Document Analysis and Recognition.

[19]  Subhash C. Bagui,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2005, Technometrics.

[20]  Robert Sablatnig,et al.  Writer Identification and Writer Retrieval Using the Fisher Vector on Visual Vocabularies , 2013, 2013 12th International Conference on Document Analysis and Recognition.

[21]  D. Wilson,et al.  Hausdorff-distance enhanced matching of Scale Invariant Feature Transform descriptors in context of image querying , 2012, 2012 IEEE 16th International Conference on Intelligent Engineering Systems (INES).

[22]  Robert Sablatnig,et al.  CVL-DataBase: An Off-Line Database for Writer Retrieval, Writer Identification and Word Spotting , 2013, 2013 12th International Conference on Document Analysis and Recognition.

[23]  Hassiba Nemmour,et al.  Handwritten signature verification using the quad-tree histogram of templates and a Support Vector-based artificial immune classification , 2017, Image Vis. Comput..

[24]  Hassiba Nemmour,et al.  Fuzzy integrals for combining multiple SVM and histogram features for writer's gender prediction , 2017, IET Biom..

[25]  Matti Pietikäinen,et al.  A comparative study of texture measures with classification based on featured distributions , 1996, Pattern Recognit..

[26]  Hassiba Nemmour,et al.  Robust soft-biometrics prediction from off-line handwriting analysis , 2016, Appl. Soft Comput..

[27]  Imran Siddiqi,et al.  Improving handwriting based gender classification using ensemble classifiers , 2017, Expert Syst. Appl..

[28]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[29]  Alex Alexandridis,et al.  Writer independent offline signature verification based on asymmetric pixel relations and unrelated training-testing datasets , 2019, Expert Syst. Appl..

[30]  Imran Siddiqi,et al.  Arabic Writer Identification System Using the Histogram of Oriented Gradients (HOG) of Handwritten Fragments , 2016, MedPRAI-2016.

[31]  Robert Sabourin,et al.  Multi-feature extraction and selection in writer-independent off-line signature verification , 2013, International Journal on Document Analysis and Recognition (IJDAR).

[32]  Loris Nanni,et al.  Local binary patterns variants as texture descriptors for medical image analysis , 2010, Artif. Intell. Medicine.

[33]  Rafal Doroz,et al.  An ensemble learning approach to lip-based biometric verification, with a dynamic selection of classifiers , 2019, Expert Syst. Appl..

[34]  Mohammad Alshayeb,et al.  KHATT: An open Arabic offline handwritten text database , 2014, Pattern Recognit..

[35]  Julian Fiérrez,et al.  Multiple classifiers in biometrics. Part 2: Trends and challenges , 2018, Inf. Fusion.

[36]  Luc Vandendorpe,et al.  Multiple classifier combination for face-based identity verification , 2004, Pattern Recognit..

[37]  Emam Hossain,et al.  Automated Facial Expression Recognition Using Gradient-Based Ternary Texture Patterns , 2013 .

[38]  Gour C. Karmakar,et al.  Improving Image Classification Using Extended Run Length Features , 1999, VISUAL.

[39]  Luiz Eduardo Soares de Oliveira,et al.  Texture-based descriptors for writer identification and verification , 2013, Expert Syst. Appl..

[40]  Satoshi Goto,et al.  Histogram of template for human detection , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[41]  Basilios Gatos,et al.  ICDAR 2011 Writer Identification Contest , 2011, 2011 International Conference on Document Analysis and Recognition.

[42]  Satnam Singh Dlay,et al.  Multi-gradient features and elongated quinary pattern encoding for image-based facial expression recognition , 2017, Pattern Recognit..