Fusion of Word Spotting and Spatial Information for Figure Caption Retrieval in Historical Document Images

2009 ◽  
Author(s):  
Khurram Khurshid ◽  
Claudie Faure ◽  
Nicole Vincent
Keyword(s):  
Spatial Information ◽  
Document Images ◽  
Historical Document ◽  
Word Spotting ◽  
Figure Caption

A voting-based technique for word spotting in handwritten document images

2021 ◽  
Author(s):  
Shamik Majumder ◽  
Subhrangshu Ghosh ◽  
Samir Malakar ◽  
Ram Sarkar ◽  
Mita Nasipuri
Keyword(s):  
Document Images ◽  
Word Spotting ◽  
Handwritten Document

scholarly journals The use of Gabor features for semi-automatically generated polyon-based ground truth of historical document images

2017 ◽  
Vol 32 (suppl_1) ◽  
pp. i134-i149 ◽  
Author(s):  
Hao Wei ◽  
Mathias Seuret ◽  
Marcus Liwicki ◽  
Rolf Ingold
Keyword(s):  
Ground Truth ◽  
Document Images ◽  
Historical Document ◽  
Gabor Features

A New Method for Detecting Altered Text in Document Images

2021 ◽  
pp. 2160010
Author(s):  
Lokesh Nandanwar ◽  
Palaiahnakote Shivakumara ◽  
Umapada Pal ◽  
Tong Lu ◽  
Daniel Lopresti ◽  
...  
Keyword(s):  
Spatial Information ◽  
Feature Vector ◽  
New Method ◽  
Document Images ◽  
Positive And Negative Coefficients ◽  
Digital Format ◽  
Fused Image ◽  
Fusion Operation ◽  
The Relationship ◽  
Text Images

As more and more office documents are captured, stored, and shared in digital format, and as image editing software are becoming increasingly more powerful, there is a growing concern about document authenticity. To prevent illicit activities, this paper presents a new method for detecting altered text in document images. The proposed method explores the relationship between positive and negative coefficients of DCT to extract the effect of distortions caused by tampering by fusing reconstructed images of respective positive and negative coefficients, which results in Positive-Negative DCT coefficients Fusion (PNDF). To take advantage of spatial information, we propose to fuse R, G, and B color channels of input images, which results in RGBF (RGB Fusion). Next, the same fusion operation is used for fusing PNDF and RGBF, which results in a fused image for the original input one. We compute a histogram to extract features from the fused image, which results in a feature vector. The feature vector is then fed to a deep neural network for classifying altered text images. The proposed method is tested on our own dataset and the standard datasets from the ICPR 2018 Fraud Contest, Altered Handwriting (AH), and faked IMEI number images. The results show that the proposed method is effective and the proposed method outperforms the existing methods irrespective of image type.

Text line extraction for historical document images

2014 ◽  
Vol 35 ◽  
pp. 23-33 ◽  
Author(s):  
Raid Saabni ◽  
Abedelkadir Asi ◽  
Jihad El-Sana
Keyword(s):  
Text Line ◽  
Document Images ◽  
Historical Document ◽  
Line Extraction ◽  
Text Line Extraction
Sign in / Sign up

Export Citation Format

Share Document