UCID: an uncompressed color image database

By Gerald Schaefer, M. Stich. IS&T/SPIE Electronic Imaging, 2003

1,248 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/015525f864ccaf28efbdaed46029598441121a9e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

A New Payload Partition Strategy in Color Image Steganography (2020, methodology): “In this subsection, we ﬁrst use the testing image data-base consisted of 1034 color 768 × 576 TIF images from McGill [41], 1338 color 512 × 384 TIF images from UCID [42].”
A generalized Benford's law for JPEG coefficients and its applications in image forensics (2007, methodology): “UCID (Uncompressed Image Database) [10], a publicly available uncompressed image database which consists of 1,338 uncompressed images (version 2) in tiff format is used in our experiments.”
Image De-Raining Transformer (2022, methodology): “DDN-Data [66] includes 1000 clean images from UCID data-set [100], BSD dataset [101] and Google image search being used to synthesize 14000 rain images.”
On The Detection of Synthetic Images Generated by Diffusion Models (2022, methodology): “Real data instead come from COCO [31], ImageNet [32] and UCID [33].”
Removing Rain from Single Images via a Deep Detail Network (2017, methodology): “We collect 1,000 clean images from the UCID dataset [29], the BSD dataset [2] and Google image search to synthesize rainy images.”
Image De-Raining Using a Conditional Generative Adversarial Network (2017, methodology): “The training set consists of a total of 700 images, where 500 images are randomly chosen from the first 800 images in the UCID dataset [61] and 200 images are randomly chosen from the BSD-500’s training set [62].”
Semi-Supervised Transfer Learning for Image Rain Removal (2018, methodology): “or supervised training data, we use one million 64 64 rainy/clean image patch pairs, which is in similar way with the baseline CNN method [3]. The clean images are collected from the the UCID dataset [34], the BSD dataset [35] and Google image search. For unsupervised training data, we collect the r”
Neural network-based arithmetic coding of intra prediction modes in HEVC (2017, methodology): “The training data are obtained from a subset of natural images coming from UCID [9], including 885 images with resolution 512 × 384.”
Clearing the Skies: A Deep Network Architecture for Single-Image Rain Removal (2016, methodology): “We randomly collected a total of 350 clean outdoor images from the UCID dataset [29], the BSD dataset [30] and Google image search which we used to synthesize rainy images.”
Exposing Digital Forgeries From JPEG Ghosts (2009, background): “At the originally saved quality of 65, the central region has a lower difference than the remaining image. Colour Image Database (UCID) [ 20 ].”
MSR-net: Low-light Image Enhancement Using Deep Convolutional Network (2017, methodology): “We collect more than 20,000 images from the UCID dataset [26], the BSD dataset [2] and Google image search.”
Edge Adaptive Image Steganography Based on LSB Matching Revisited (2010, methodology): “Three image datasets have been used for algorithm evaluation, UCID [22] including 1338 uncompressed color images with a size of 384 512 or 512 384, NJIT dataset including 3680 uncompressed color images with a size of either 512 768 or 768 512, which were taken with different kinds of camera, and our”
Removing Rain from a Single Image via Discriminative Sparse Coding (2015, methodology): “The rain images for testing are synthesized by adding rainy effect on 200+ outdoor images randomly selected from the UCID dataset [22]; see Fig.”
MFC Datasets: Large-Scale Benchmark Datasets for Media Forensic Challenge Evaluation (2019, background): “Many general benchmark media datasets are available in literature: UCID (2003) [14] and ImageCLEF (2004-2013) [15] for image retrieval; Caltech-256 (2007) [16], 80 million tiny images (2008) [17], Mammal Image (2008) [18], PASCAL (2008-2015) [19], ImageNet (2009) [20], SUN (2010) [21], Kitti (2013)…”
A convolutional neural network-based approach to rate control in HEVC intra coding (2017, methodology): “The images come from the UCID dataset [11] and the RAISE dataset [12].”
Median Filtering Forensics Based on Convolutional Neural Networks (2015, methodology): “These images are from five widely used image databases: the BOSSbase 1.01 [20], the UCID database [21], the BOSS RAW database [22], the Dresden Image Database [23] and the NRCS Photo Gallery database [24].”