169 datasets found

The dataset used in the paper is a collection of ballast images with corresponding Fouling Index (FI) values.

The proposed minimal solvers exploit the scale constraint: two instances of rigidly-transformed coplanar repeats occupy identical areas in the scene plane and in the rectified...

The dataset used in the paper for feature correspondence between two images, using the epipolar line and cheirality constraint.

The proposed measurement-adaptive sparse image sampling and recovery framework.

The dataset used in the paper is a suite of 16 real benchmarks for deep learning and image processing applications.

We investigate the problem of training neural networks from incomplete images without replacing missing values.

Anomaly detection in images using multivariate Gaussian and whitening transformation

A benchmark for edge-preserving image smoothing for the purpose of quantitative performance evaluation and further advancing the state-of-the-art.

The dataset includes image processing operators and their properties.

The dataset includes image processing operators such as Sobel and Hough.

The PASCAL VOC2012 dataset is a benchmark for object detection, containing 1464 images with corresponding labeled object instances for 20 classes.

The SBD dataset is a benchmark for semantic edge detection, containing 11,355 images with corresponding labeled semantic edge maps for 20 Pascal VOC classes.

The dataset used in the paper is a binary matrix, and the authors used it to test their algorithm for Boolean Matrix Factorization (BMF) and Fp-Matrix Factorization (Fp-MF).

The dataset used to test the proposed variable pixel imaging method.

The proposed parallel variable pixel arrays system for generating images gives an improved visual quality for the images studied.

The Hough transform is an image processing technique for finding mathematically predefined objects such as lines and circles in an image. The Hough transform is also applied in...

The dataset used in the paper for reflection symmetry detection in real images.

The dataset used in this paper is a group-sparse signal denoising problem with overlapping groups.

The dataset is a photogrammetric digital surface model of the city of Zurich in Switzerland, processed using the photogrammetric surface reconstruction software SURE.

A novel, generic method for automatic ground truth generation of camera-captured document images.