Open AccessBook
An introduction to digital image processing
About:
The article was published on 1986-01-01 and is currently open access. It has received 1745 citations till now. The article focuses on the topics: Digital image processing & Image processing.read more
Citations
More filters
Proceedings ArticleDOI
Improved document image binarization by using a combination of multiple binarization techniques and adapted edge information
TL;DR: The proposed method is mainly based on the combination of several state- of-the-art binarization methodologies as well as on the efficient incorporation of the edge information of the gray scale source image to produce a high quality result while preserving stroke information.
Patent
Photographic document imaging system
Edward P. Heaney,Zachary Andree,Zachariah Clegg,James Darpinian,Kurt A. Rapelje,William J. Adams,Zachary Dodds +6 more
TL;DR: An apparatus and method for processing captured image and more particularly for processing a captured image comprising a document is described in this article. But this method is not suitable for the processing of images containing a document.
Journal ArticleDOI
MFP-Unet: A novel deep learning based approach for left ventricle segmentation in echocardiography
Shakiba Moradi,Mostafa Ghelich Oghli,Azin Alizadehasl,Isaac Shiri,Niki Oveisi,Mehrdad Oveisi,Majid Maleki,Jan D'hooge +7 more
TL;DR: The proposed network yielded significantly improved results when comparing with results from U-net, dilated U-nets, Unet++, ACNN, SHG, and deeplabv3, and an average Dice Metric, Hausdorff Distance, and Mean Absolute Distance are achieved in the public dataset.
Proceedings ArticleDOI
Spectral characteristics preserving image fusion based on Fourier domain filtering
TL;DR: In this study, a new method for image fusion will be presented that is based on filtering in the Fourier domain that preserves the spectral characteristics of the lower resolution mul-tispectral images.
Finger-vein biometric identication using convolutional neural network
TL;DR: A reduced-complexity four-layer CNN with fused convolutional-subsampling architecture is proposed for finger-vein recognition and modified and applied the stochastic diagonal Levenberg{Marquardt algorithm, which results in a faster convergence time.
Related Papers (5)
Survey over image thresholding techniques and quantitative performance evaluation
Mehmet Sezgin,Bulent Sankur +1 more