Bicubic interpolation

About: Bicubic interpolation is a research topic. Over the lifetime, 3348 publications have been published within this topic receiving 73126 citations.

Single Depth Image Super-Resolution Using Convolutional Neural Networks

Abstract: In this paper, we propose single depth image super-resolution using convolutional neural networks (CNN). We adopt CN-N to acquire a high-quality edge map from the input low-resolution (LR) depth image. We use the high-quality edge map as the weight of the regularization term in a total variation (TV) model for super-resolution. First, we interpolate the LR depth image using bicubic interpolation and extract its low-quality edge map. Then, we get the high-quality edge map from the low-quality one using CNN. Since the CNN output often contains broken edges and holes, we refine it using the low-quality edge map. Guided by the high-quality edge map, we upsample the input LR depth image in the TV model. The edge-based guidance in TV effectively removes noise in depth while minimizing jagged artifacts and preserving sharp edges. Various experiments on the Middle-bury stereo dataset and Laser Scan dataset demonstrate the superiority of the proposed method over state-of-the-arts in both qualitative and quantitative measurements.

Correlation of modeling techniques and power factor for switched-reluctance machines drives

Abstract: The paper summarises the authors' reported and ongoing research on both modelling and on sensorless control and power-factor improvement of switched-reluctance-machine (SRM) drives. The paper presents four models of SRMs: the piecewise-interpolation model using a two-dimensional (2-D) bicubic spline, an analytical model based on the 2-D least-squares technique, a cross hybrid model based on the 2-D bicubic and 2-D bilinear splines, and the coupling model taking account of mutual coupling. These four models are validated by simulations and experiments. An estimation scheme of the initial rotor position at standstill and a sensorless control scheme at low and high speeds are also developed. In addition, the authors have studied the effect of the control and output parameters on power factor in SRM drives. Consequently, a new control strategy and two real-time schemes for improving the power factor have been developed.

Image Interpolation Using PBLP Method on the Eigenspace

Abstract: In this paper the authors propose a method to use interpolation to eliminate characters in only one image with telops or other text through an image interpolation method that uses the eigenspace method. Background scenes and other images have a fractal character, and often the self-correlation in the image can be assumed to be high. The authors focus on this point and represent rules for describing the image based on an eigenspace consisting of only one image that has defects. The eigenspace generated in this manner reflects the features of the image, and by using this eigenspace, image interpolation can be achieved. Although this interpolation method does not restore the original image, the authors confirmed through experimental results that it can provide interpolation without a feeling of oddness for images which have a high level of self-correlation. © 2006 Wiley Periodicals, Inc. Syst Comp Jpn, 38(1): 87– 96, 2007; Published online in Wiley InterScience (). DOI 10.1002sscj.10319.

Brain MRI Super Resolution Using 3D Deep Densely Connected Neural Networks

Abstract: Magnetic resonance image (MRI) in high spatial resolution provides detailed anatomical information and is often necessary for accurate quantitative analysis. However, high spatial resolution typically comes at the expense of longer scan time, less spatial coverage, and lower signal to noise ratio (SNR). Single Image Super-Resolution (SISR), a technique aimed to restore high-resolution (HR) details from one single low-resolution (LR) input image, has been improved dramatically by recent breakthroughs in deep learning. In this paper, we introduce a new neural network architecture, 3D Densely Connected Super-Resolution Networks (DCSRN) to restore HR features of structural brain MR images. Through experiments on a dataset with 1,113 subjects, we demonstrate that our network outperforms bicubic interpolation as well as other deep learning methods in restoring 4x resolution-reduced images.

Block-level parallel processing for scaling evenly divisible images

Abstract: Image scaling is a frequent operation in medical image processing. This paper presents how two-dimensional (2-D) image scaling can be accelerated with a new coarse-grained parallel processing method. The method is based on evenly divisible image sizes which is, in practice, the case with most medical images. In the proposed method, the image is divided into slices and all the slices are scaled in parallel. The complexity of the method is examined with two parallel architectures while considering memory consumption and data throughput. Several scaling functions can be handled with these generic architectures including linear, cubic B-spline, cubic, Lagrange, Gaussian, and sinc interpolations. Parallelism can be adjusted independent of the complexity of the computational units. The most promising architecture is implemented as a simulation model and the hardware resources as well as the performance are evaluated. All the significant resources are shown to be linearly proportional to the parallelization factor. With contemporary programmable logic, real-time scaling is achievable with large resolution 2-D images and a good quality interpolation. The proposed block-level scaling is also shown to increase software scaling performance over four times.