-
Chapter and Conference Paper
Point MixSwap: Attentional Point Cloud Mixing via Swap** Matched Structural Divisions
Data augmentation is developed for increasing the amount and diversity of training data to enhance model learning. Compared to 2D images, point clouds, with the 3D geometric nature as well as the high collecti...
-
Article
Image super-resolution by estimating the enhancement weight of self example and external missing patches
Image super-resolution (SR) is the process of generating a high-resolution (HR) image using one or more low-resolution (LR) inputs. Many SR methods have been proposed, but generating the small-scale structure ...
-
Article
Alpha matting using robust color sampling and fully connected conditional random fields
Alpha matting refers to the problem of softly extracting the foreground from a given image. Previous matting approaches often focused on using naïve color sampling methods to estimate foreground and background...
-
Chapter and Conference Paper
Investigating Size Personalization for More Accurate Eye Tracking Glasses
Personalized eyewear frame could improve the accuracy of eye tracking. To obtain the personalized frame size (temple length), we propose a new measuring instrument that consists of (i) the hardware, a 3D print...
-
Chapter and Conference Paper
Practical Error Analysis of Cross-Ratio-Based Planar Localization
Recently, more and more computer vision researchers are paying attention to error analysis so as to fulfill various accuracy requirements arising from different applications. As a geometric invariant under pro...
-
Chapter and Conference Paper
Automatic Chromosome Classification Using Medial Axis Approximation and Band Profile Similarity
Automated chromosome classification is an essential task in cytogenetics and has been an important pattern recognition problem. Numerous attempts were made in the past to characterize chromosome to perform cli...
-
Chapter and Conference Paper
Direct Energy Minimization for Super-Resolution on Nonlinear Manifolds
We address the problem of single image super-resolution by exploring the manifold properties. Given a set of low resolution image patches and their corresponding high resolution patches, we assume they respect...
-
Chapter and Conference Paper
Drawing Graphs with Nonuniform Nodes Using Potential Fields
A potential field approach, coupled with force-directed methods, is proposed in this paper for drawing graphs with nonuniform nodes in 2-D and 3-D. In our framework, nonuniform nodes are uniformly or nonuniformly...
-
Chapter and Conference Paper
Potential-based modeling of 2D regions using non-uniform source distributions
One of existing approaches to path planning problems uses a potential function to represent the topological structure of the free space. 1 Newtonian potential was used in [1] to represent object and obstacles ...
-
Chapter
Performance Evaluation of Phase-Only Technique for High-Resolution Holographic Imaging
Phase-only image reconstruction is a widely used technique in holography. It utilizes only the phase information of the complex amplitude of the resultant wave-field for image formation. In many cases, the pha...
-
Chapter
Computation Simplification for High-Speed Acoustical Image Reconstruction
In many conventional coherent acoustical image formation algorithms using weight, delay, and summation operators, the computation complexity is mainly governed by the associated exponential and trigonometric o...
