scispace - formally typeset
Search or ask a question
Topic

Standard test image

About: Standard test image is a research topic. Over the lifetime, 5217 publications have been published within this topic receiving 98486 citations.


Papers
More filters
Proceedings ArticleDOI
13 Jun 2010
TL;DR: This work develops a novel data-driven iterative algorithm that combines the best of both generative and discriminative approaches and introduces the notion of a “pull-back” operation that enables it to predict the parameters of the test image using training samples that are not in its neighborhood (not ∊-close) in parameter space.
Abstract: Image alignment in the presence of non-rigid distortions is a challenging task. Typically, this involves estimating the parameters of a dense deformation field that warps a distorted image back to its undistorted template. Generative approaches based on parameter optimization such as Lucas-Kanade can get trapped within local minima. On the other hand, discriminative approaches like Nearest-Neighbor require a large number of training samples that grows exponentially with the desired accuracy. In this work, we develop a novel data-driven iterative algorithm that combines the best of both generative and discriminative approaches. For this, we introduce the notion of a “pull-back” operation that enables us to predict the parameters of the test image using training samples that are not in its neighborhood (not ∊-close) in parameter space. We prove that our algorithm converges to the global optimum using a significantly lower number of training samples that grows only logarithmically with the desired accuracy. We analyze the behavior of our algorithm extensively using synthetic data and demonstrate successful results on experiments with complex deformations due to water and clothing.

41 citations

Journal ArticleDOI
TL;DR: In this study, mean-squared error over the image is used to evaluate methods for regularizing the ill-posed inverse image reconstruction problem in NIR tomography and it was observed that the bias error dominates at high regularization parameter values while variance dominates as the algorithm is allowed to approach the optimal solution.
Abstract: Near-infrared (NIR) diffuse tomography is an emerging method for imaging the interior of tissues to quantify concentrations of hemoglobin and exogenous chromophores noninvasively in vivo. It often exploits an optical diffusion model-based image reconstruction algorithm to estimate spatial property values from measurements of the light flux at the surface of the tissue. In this study, mean-squared error (MSE) over the image is used to evaluate methods for regularizing the ill-posed inverse image reconstruction problem in NIR tomography. Estimates of image bias and image standard deviation were calculated based upon 100 repeated reconstructions of a test image with randomly distributed noise added to the light flux measurements. It was observed that the bias error dominates at high regularization parameter values while variance dominates as the algorithm is allowed to approach the optimal solution. This optimum does not necessarily correspond to the minimum projection error solution, but typically requires further iteration with a decreasing regularization parameter to reach the lowest image error. Increasing measurement noise causes a need to constrain the minimum regularization parameter to higher values in order to achieve a minimum in the overall image MSE.

41 citations

Patent
Todd D. Newman1
17 Oct 2002
TL;DR: An image processing method for processing image data comprises the steps of obtaining scanpath data corresponding to original image data, determining regions of interest for the original image dataset based on the obtained scanpath, and mapping tone values of the original dataset corresponding to each region of interest in order to obtain tone-mapped image data as discussed by the authors.
Abstract: An image processing method for processing image data comprises the steps of obtaining scanpath data corresponding to original image data, determining regions of interest for the original image data based on the obtained scanpath data, and mapping tone values of the original image data corresponding to each region of interest in order to obtain tone-mapped image data.

41 citations

Patent
01 Jun 2010
TL;DR: In this article, a robust human authentication system, device, and instructions, embeddable in a physical and tangible computer readable medium, for determining if at least one test image obtained using an imaging device matches at least another training image in an enrollment database, are disclosed.
Abstract: A new robust human authentication system, device, and instructions, embeddable in a physical and tangible computer readable medium, for determining if at least one test image obtained using an imaging device matches at least one training image in an enrollment database, are disclosed. This invention applies the concepts of appearance (PCA or PCA+LDA) and holistic anthropometrics that include head, face, neck, and shoulder linear and non-linear geometric measurements. The appearance (“eigen”) coefficients and holistic anthropometric measurements selected may be used as feature vectors. A boosting algorithm ranks features as “weak learners” and combines their outputs for “strong” recognition.

41 citations

Patent
02 Nov 1995
TL;DR: In this article, a computer-aided method of detecting regions of interest in a digital image optimizes and adapts a computer aided scheme for detecting regions in images, which is based on global image characteristics.
Abstract: A computerized method of detecting regions of interest in a digital image optimizes and adapts a computer aided scheme for detecting regions of interest in images. The optimization is based on global image characteristics. For each image in a database of images having known regions of interest, global image features are measured and an image characteristic index is established based on these global image features. All the images in the database are divided into a number of image groups based on the image characteristic index of each image in the database and the CAD scheme is optimized for each image group. Once the CAD scheme is optimized, to process a digital image, an image characteristics based classification criteria is established for that image, and then global image features of the digitized image are determined. The digitized image is then assigned an image characteristics rating based on the determined global image features, and the image is assigned to an image group based on the image rating. Then regions of interest depicted in the image are determined using a detection scheme adapted for the assigned image group.

41 citations


Network Information
Related Topics (5)
Feature extraction
111.8K papers, 2.1M citations
91% related
Image segmentation
79.6K papers, 1.8M citations
91% related
Image processing
229.9K papers, 3.5M citations
90% related
Convolutional neural network
74.7K papers, 2M citations
90% related
Support vector machine
73.6K papers, 1.7M citations
90% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
20231
20228
2021130
2020232
2019321
2018293