This paper proposes a novel method for recognizing faces degraded by blur using deblurring of facial images. The main issue is how to infer a Point Spread Function (PSF) representing the process of blur on faces. Inferring a PSF from a single facial image is an ill-posed problem. Our method uses learned prior information derived from a training set of blurred faces to make the problem more tractable. We construct a feature space such that blurred faces degraded by the same PSF are similar to one another. We learn statistical models that represent prior knowledge of predefined PSF sets in this feature space. A query image of unknown blur is compared with each model and the closest one is selected for PSF inference. The query image is deblurred using the PSF corresponding to that model and is thus ready for recognition. Experiments on a large face database (FERET) artificially degraded by focus or motion blur show that our method substantially improves the recognition performance compared to existing methods. We also demonstrate improved performance on real blurred images on the FRGC 1.0 face database. Furthermore, we show and explain how combining the proposed facial deblur inference with the local phase quantization (LPQ) method can further enhance the performance.
The purposes of this work are to develop a method for efficiently processing MR-specific artifacts using a convolutional neural network (CNN), and to present its applications for the removal of the artifacts without suppressing actual signals. In MR images that are acquired using parallel imaging and/or EPI, the locations of aliasing artifacts and/or N-half ghost artifacts can be analytically calculated.However, existing methods using CNNs do not take the structures of the artifacts into account, and therefore need a large number of convolution layers for processing the artifacts. Methods: For processing the artifacts, a new layer that is named the aliasing layer (AL) is proposed. Because a CNN stands on the assumption that an image has spatial locality, a convolution layer is formulated as a linear function of neighbor locations.For processing the artifacts, the AL preprocesses MR images by moving the calculated locations to the locations accessible through summations over all channels in a standard convolution layer. To evaluate the application of ALs for the removal of parallel imaging and EPI artifacts, CNNs with ALs were compared with those without ALs. Results: The results showed that image-quality metrics of a six-layer CNN with ALs were better than those of a 12-layer CNN without ALs. The results also showed that CNNs with ALs suppressed the artifacts selectively.
Conclusion:The aliasing layer is proposed for processing MR-specific artifacts efficiently. The experimental results demonstrated that the AL improved CNNs for removing artifacts from parallel imaging and EPI.
K E Y W O R D Saliasing layers, artifact, convolutional neural networks
| INTRODUCTIONConvolutional neural networks (CNNs) 1 have been used widely for modeling various nonlinear functions in MR applications such as image reconstruction, 2 denoising, 3 and disease classification. 4 Using the assumption that an image has spatial locality, CNNs use cross-correlations, which share local connections in an entire image, instead of full connections.Existing studies used CNNs with standard convolution layers for suppressing aliasing artifacts generated by parallel imaging (PI). 5,6 To reduce PI aliasing artifacts on image How to cite this article: Takeshima H. Aliasing layers for processing parallel imaging and EPI ghost artifacts efficiently in convolutional neural networks.
In the present study, k - t SENSE was identified as a suitable base method to be improved achieving both short acquisition times and a cost-effective reconstruction. To enhance these characteristics of base method, a novel implementation is proposed, estimating the x - f sensitivity without the need for an explicit scan of the reference signals. Experimental results showed that the acquisition, computational times and image quality for the proposed method were improved compared to the standard k - t SENSE method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.