• Publications
  • Influence
Color image indexing using BTC
  • G. Qiu
  • Computer Science
    IEEE Trans. Image Process.
  • 20 March 2003
TLDR
It is shown that BTC can not only be used for compressing color images, it can also be conveniently used for content-based image retrieval from image databases.
Deep Feature Consistent Variational Autoencoder
TLDR
This work employs a pre-trained deep convolutional neural network and uses its hidden features to define a feature perceptual loss for VAE training, which ensures the VAE's output to preserve the spatial correlation characteristics of the input, thus leading the output to have a more natural visual appearance and better perceptual quality.
A Novel Method for Detecting Cropped and Recompressed Image Block
TLDR
A novel method for the detection of image tampering operations in JPEG images by exploiting the blocking artifact characteristics matrix (BACM) to train a support vector machine (SVM) classifier for recognizing whether an image is an original JPEG image or it has been cropped from another JPEG image and re-saved as a JPEG image.
Robust Detection of Region-Duplication Forgery in Digital Image
TLDR
An efficient and robust algorithm for detecting and localizing this type of malicious tampering for images that have been subjected to various forms of post region duplication image processing, including blurring, noise contamination, severe lossy compression, and a mixture of these processing operations.
JPEG Error Analysis and Its Applications to Digital Image Forensics
TLDR
The new JPEG error analysis method can reliably detect JPEG image blocks which are as small as 8 × 8 pixels and compressed with quality factors as high as 98.5%, important for analyzing and locating small tampered regions within a composite image.
Image Companding and Inverse Halftoning using Deep Convolutional Neural Networks
TLDR
This work introduces deep learning technology to tackle two traditional low-level image processing problems, companding and inverse halftoning and develops an effective deep learning algorithm based on insights into the properties of visual quality of images and the internal representation properties of a deep convolutional neural network (CNN).
Tone-mapping high dynamic range images by novel histogram adjustment
Random Forest for Image Annotation
TLDR
A novel method for image annotation is presented to use the tags contained in the training images as the supervising information to guide the generation of random trees, thus enabling the retrieved nearest neighbor images not only visually alike but also semantically related.
Crowd density estimation based on rich features and random projection forest
  • Bolei Xu, G. Qiu
  • Computer Science
    IEEE Winter Conference on Applications of…
  • 7 March 2016
TLDR
This paper uses random forest as the regression model whose tree structure is intrinsically fast and scalable and embeds random projection in the tree nodes to simultaneously combat the curse of dimensionality and to introduce randomness in theTree construction (the authors call this Random Projection Forest), thus making the method very efficient and effective.
...
...