Edge detection in multispectral images
CVGIP: Graphical Models and Image Processing
Color image processing by using binary quaternion-moment-preserving thresholding technique
IEEE Transactions on Image Processing
Show-through cancellation in scans of duplex printed documents
IEEE Transactions on Image Processing
Enhancing the Quality of Color Documents with Back-to-Front Interference
ICIAR '09 Proceedings of the 6th International Conference on Image Analysis and Recognition
Multichannel blind separation and deconvolution of images for document analysis
IEEE Transactions on Image Processing
Color space transformations for analysis and enhancement of ancient degraded manuscripts
Pattern Recognition and Image Analysis
Using non-negative matrix factorization for removing show-through
LVA/ICA'10 Proceedings of the 9th international conference on Latent variable analysis and signal separation
Hi-index | 0.00 |
This paper describes a new approach to restoringscanned color document images where the backside imageshows through the paper sheet. A new framework ispresented for correcting show-through components usingdigital image processing techniques. First, the foregroundcomponents on the front side are separated from thebackground and backside components through locallyadaptive binarization for each color component and edgemagnitude thresholding. Background colors are estimatedlocally through color thresholding to generate a restoredimage, and then corrected adaptively through multi-scaleanalysis along with comparison of edge distributions betweenthe original and the restored image. The proposedmethod does not require specific input devices or thebackside to be input; it is able to correct unneeded imagecomponents through analysis of the front side imagealone. Experimental results are given to verify effectivenessof the proposed method.