Hidenori Takeshima

Facial Deblur Inference Using Subspace Analysis for Recognition of Blurred Faces

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.

Facial deblur inference to improve recognition of blurred faces

This paper proposes a novel method for deblurring facial images to recognize faces degraded by blur. The main problem is how to infer a point spread function (PSF) representing the process of blur. Inferring a PSF from a single facial image is an ill-posed problem. To make this problem more tractable, our method uses learned prior information derived from a training set of blurred facial images of several individuals. We construct a feature space such that blurred faces degraded by the same PSF are similar to one another and form a cluster. During training, we compute a statistical model of each PSF cluster in this feature space. For PSF inference we compare a query image of unknown blur with each model and select the closest one. Using the PSF corresponding to that model, the query image is deblurred, ready for recognition. Experiments on a standard face database artificially degraded by focus or motion blur show that our method substantially improves the recognition performance compared with state-of-the-art methods. We also demonstrate improved performance on real blurred images.

Image registration using subpixel-shifted images for super-resolution

A novel image registration algorithm for super-resolution is proposed. The quality of reconstructed images becomes poor when the arrangement of the registered positions is irregular. However, there are no known ways to acquire the positions arranged regularly without using active cameras. By using a conventional algorithm, the positions registered with subpixel accuracy are often distributed near integer values in the low-resolution grid when the aperture problem occurs, for example, in the case of processing straight edges. Since this phenomenon causes an irregular arrangement, the high- resolution images are reconstructed inefficiently. The proposed method estimates corresponding positions on the shifted image whose image grid is shifted by a desired subpixel displacement. By using the proposed method, the distribution of the corresponding positions is shifted artificially so that the quality of the reconstructed image is improved. The effectiveness of the proposed method is demonstrated in experiments.

Estimation of Spatiotemporal Sensitivity Using Band-limited Signals with No Additional Acquisitions for k−t Parallel Imaging

Purpose: Dynamic MR techniques, such as cardiac cine imaging, benefit from shorter acquisition times. The goal of the present study was to develop a method that achieves short acquisition times, while maintaining a cost-effective reconstruction, for dynamic MRI. k – t sensitivity encoding (SENSE) was identified as the base method to be enhanced meeting these two requirements. Methods: The proposed method achieves a reduction in acquisition time by estimating the spatiotemporal (x – f) sensitivity without requiring the acquisition of the alias-free signals, typical of the k – t SENSE technique. The cost-effective reconstruction, in turn, is achieved by a computationally efficient estimation of the x – f sensitivity from the band-limited signals of the aliased inputs. Such band-limited signals are suitable for sensitivity estimation because the strongly aliased signals have been removed. Results: For the same reduction factor 4, the net reduction factor 4 for the proposed method was significantly higher than the factor 2.29 achieved by k – t SENSE. The processing time is reduced from 4.1 s for k – t SENSE to 1.7 s for the proposed method. The image quality obtained using the proposed method proved to be superior (mean squared error [MSE] ± standard deviation [SD] = 6.85 ± 2.73) compared to the k – t SENSE case (MSE ± SD = 12.73 ± 3.60) for the vertical long-axis (VLA) view, as well as other views. Conclusion: 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.

Morphology-matching-based R-wave detection for noise-robust ECG gating

Background Accurate ECG R-wave detection is crucial for cardiac gating in MRI. However, in high-field MRI systems, it is hard to detect R-waves in ECG signals accurately, because the amplitude of the ECG signal may be smaller than that of the noise induced by the MRI system. To overcome this issue, existing studies have focused on (a) acquiring additional ECG signals or on (b) improving the R-wave detector to be robust against noise. In the first approach, ECG gating with a 12-lead ECG has been reported to have high accuracy [1]. However, due to ECG monitor limitations, this study utilizes a common dual-lead ECG. We propose a new morphology-matching-based R-wave detector for noise-robust ECG gating. The morphology is analyzed in filtered ECG signals, and the R-wave is detected by matching the input ECG signals to R-wave templates. The templates are updated when the MRI system is not scanning, and they contribute to robustness against patient variation and noise [1].

Super-resolution using a local matching designed for suppressing errors of reconstructed edges

A novel registration algorithm for multi-frame super-resolution (SR) is proposed. SR requires known LR pixels shifted by non-integer amounts of pixels. Such LR pixels can be acquired from non-target frames using registration. A method suitable for implementing registration in consumer products is the block-matching algorithm (BMA). However, when the BMA is used, in the case of processing a straight edge, it is shown that the arrangement tends to be irregular. It is also shown that the quality of reconstructed images becomes poor when the arrangement of the registered pixels is irregular. The proposed method is based on the BMA but is designed for improving the arrangement of the registered pixels. The experimental results show that (1) the pixels are registered near each position to be reconstructed, and (2) the quality of reconstructed images is improved. To make the proposed method practical for consumer products, the search is performed using a fast block-matching algorithm.

Object Contour Detection Using Spatio-temporal Self-sim

A novel contour detector that refines a rough boundary between an object and a background to a precise boundary in moving pictures robustly is proposed. To estimate boundaries of objects, the proposed method uses self-similar block matching (SSBM) in spatio-temporal 3-D space. SSBM, which searches a larger similar block for each block placed near a boundary, estimates contours correctly. In this paper, it is shown analytically that the robustness of spatio-temporal SSBM is superior to that of conventional 2-D SSBM. Since SSBM does not assume contour smoothness, the proposed algorithm can detect sharp corners more accurately than the methods using smooth constraints such as Snake. Experimental results show that the proposed method is effective for estimating precise regions of objects even if pictures are noisy