A proposition of a robust system for historical document images indexation

08/28/2013 ∙ by Nizar Zaghden, et al. ∙ 0 ∙ share

Characterizing noisy or ancient documents is a challenging problem up to now. Many techniques have been done in order to effectuate feature extraction and image indexation for such documents. Global approaches are in general less robust and exact than local approaches. That's why, we propose in this paper, a hybrid system based on global approach(fractal dimension), and a local one based on SIFT descriptor. The Scale Invariant Feature Transform seems to do well with our application since it's rotation invariant and relatively robust to changing illumination.In the first step the calculation of fractal dimension is applied to images in order to eliminate images which have distant features than image request characteristics. Next, the SIFT is applied to show which images match well the request. However the average matching time using the hybrid approach is better than "fractal dimension" and "SIFT descriptor" if they are used alone.

READ FULL TEXT

FWLBP: A Scale Invariant Descriptor for Texture Classification

In this paper we propose a novel texture recognition feature called Frac...
01/10/2018 ∙ by Swalpa Kumar Roy, et al. ∙ 0 ∙ share

read it
Radial Line Fourier Descriptor for Segmentation-free Handwritten Word Spotting

Automatic recognition of historical handwritten manuscripts is a dauntin...
09/06/2017 ∙ by Anders Hast, et al. ∙ 0 ∙ share

read it
Exploiting SIFT Descriptor for Rotation Invariant Convolutional Neural Network

This paper presents a novel approach to exploit the distinctive invarian...
03/30/2019 ∙ by Abhay Kumar, et al. ∙ 0 ∙ share

read it
Performance Evaluation of SIFT Descriptor against Common Image Deformations on Iban Plaited Mat Motifs

Borneo indigenous communities are blessed with rich craft heritage. One ...
10/03/2018 ∙ by Silvia Joseph, et al. ∙ 2 ∙ share

read it
HDD-Net: Hybrid Detector Descriptor with Mutual Interactive Learning

Local feature extraction remains an active research area due to the adva...
05/12/2020 ∙ by Axel Barroso Laguna, et al. ∙ 3 ∙ share

read it
Image Matching Using SIFT, SURF, BRIEF and ORB: Performance Comparison for Distorted Images

Fast and robust image matching is a very important task with various app...
10/07/2017 ∙ by Ebrahim Karami, et al. ∙ 0 ∙ share

read it
Application of Threshold Techniques for Readability Improvement of Jawi Historical Manuscript Images

Historical documents such as old books and manuscripts have a high aesth...
03/29/2011 ∙ by Hafizan Mat Som, et al. ∙ 0 ∙ share

read it

A proposition of a robust system for historical document images indexation

Authors

FWLBP: A Scale Invariant Descriptor for Texture Classification

Radial Line Fourier Descriptor for Segmentation-free Handwritten Word Spotting

Exploiting SIFT Descriptor for Rotation Invariant Convolutional Neural Network

Performance Evaluation of SIFT Descriptor against Common Image Deformations on Iban Plaited Mat Motifs

HDD-Net: Hybrid Detector Descriptor with Mutual Interactive Learning

Image Matching Using SIFT, SURF, BRIEF and ORB: Performance Comparison for Distorted Images

Application of Threshold Techniques for Readability Improvement of Jawi Historical Manuscript Images

This week in AI