Keyword Spotting Scores Fusion based on Fuzzy Integral and Curvelet Descriptor

This paper deals with a new matching scheme for keyword spotting that combines advantages of two set of different descriptors using the Discrete Choquet Fuzzy Integral (DCFI) combiner and the Dynamic Time Warping (DTW) algorithm. In fact, DTW computes for each descriptor the score of matching between two word images. However, the idea of FI technique is that the final matching decision can be significantly increased by giving the combiner a possibility to bias the different DTW output scores based on a priori knowledge about the worthiness degree of each descriptor. Certainly, a complementary information can be derived from two matching system with two different inputs. The experiments conducted on two different document images show that the fusion of statistical and Curvelet descriptors provides a higher spotting precision in comparison with other descriptors.

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

[2]  Sung-Bae Cho,et al.  Combining multiple neural networks by fuzzy integral for robust classification , 1995, IEEE Trans. Syst. Man Cybern..

[3]  E. Candès,et al.  New tight frames of curvelets and optimal representations of objects with piecewise C2 singularities , 2004 .

[4]  C. V. Jawahar,et al.  Word-Level Access to Document Image Datasets , .

[5]  Yong Deng,et al.  Combining conflicting evidence using the DEMATEL method , 2018, Soft Comput..

[6]  Christian Wagner,et al.  Comparison of Fuzzy Integral-Fuzzy Measure Based Ensemble Algorithms with the State-of-the-Art Ensemble Algorithms , 2018, IPMU.

[7]  M. Pechwitz,et al.  IFN/ENIT: database of handwritten arabic words , 2002 .

[8]  Fakhri Karray,et al.  Multisensor data fusion: A review of the state-of-the-art , 2013, Inf. Fusion.

[9]  Timothy C. Havens,et al.  Efficient Multiple Kernel Classification Using Feature and Decision Level Fusion , 2017, IEEE Transactions on Fuzzy Systems.

[10]  M. Sugeno,et al.  An interpretation of fuzzy measures and the Choquet integral as an integral with respect to a fuzzy , 1989 .

[11]  菅野 道夫,et al.  Theory of fuzzy integrals and its applications , 1975 .

[12]  David L. Donoho,et al.  Digital curvelet transform: strategy, implementation, and experiments , 2000, SPIE Defense + Commercial Sensing.

[13]  Djamel Bouchaffra,et al.  Combining Pixel- and Object-Based Approaches for Multispectral Image Classification Using Dempster-Shafer Theory , 2013, 2013 International Conference on Signal-Image Technology & Internet-Based Systems.

[14]  K. Leszczynski,et al.  Sugeno's fuzzy measure and fuzzy clustering , 1985 .

[15]  James M. Keller,et al.  Information fusion in computer vision using the fuzzy integral , 1990, IEEE Trans. Syst. Man Cybern..

[16]  R. Manmatha,et al.  Word image matching using dynamic time warping , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[17]  Qingjiu Tian,et al.  A comparison of multiple classifier combinations using different voting-weights for remote sensing image classification , 2018 .

[18]  Laurent Demanet,et al.  Fast Discrete Curvelet Transforms , 2006, Multiscale Model. Simul..

[19]  Quan Pan,et al.  Combining sources of evidence with reliability and importance for decision making , 2014, Central Eur. J. Oper. Res..

[20]  Youcef Chibani,et al.  Keyword-guided Arabic word spotting in ancient document images using Curvelet descriptors , 2014, 2014 International Conference on Multimedia Computing and Systems (ICMCS).

[21]  G. Klir,et al.  Fuzzy Measure Theory , 1993 .

[22]  H. Salari,et al.  A NEW MULTI-CRITERIA EVALUATION MODEL BASED ON THE COMBINATION OF NON-ADDITIVE FUZZY AHP, CHOQUET INTEGRAL AND SUGENO λ-MEASURE , 2017 .

[23]  R. Polikar,et al.  Ensemble based systems in decision making , 2006, IEEE Circuits and Systems Magazine.

[24]  Lucia Rita Quitadamo,et al.  A Fuzzy Integral Ensemble Method in Visual P300 Brain-Computer Interface , 2015, Comput. Intell. Neurosci..

[25]  Nicole Vincent,et al.  A fusion methodology based on Dempster-Shafer evidence theory for two biometric applications , 2006, 18th International Conference on Pattern Recognition (ICPR'06).