Learn More
Co-saliency is used to discover the common saliency on the multiple images, which is a relatively underexplored area. In this paper, we introduce a new cluster-based algorithm for co-saliency detection. Global correspondence between the multiple images is implicitly learned during the clustering process. Three visual attention cues: contrast, spatial, and(More)
Image compositing technology has become popular for tampering with digital photographies. We describe how such composites can be detected by enforcing the geometric and photometric constraints from shadows. In particular, we explore (i) the imaged shadow relations that are modeled by the planar homology, and (ii) the color characteristics of the shadows(More)
—In this paper, we propose a framework for detecting tampered digital images based on photometric consistency of illumination in shadows. In particular, we formulate color characteristics of shadows measured by the shadow matte value. The shadow boundaries and the penumbra shadow region in an image are first extracted. Then a simple and efficient method is(More)
In this paper, we introduce a novel Flip INvariant Descriptor (FIND). FIND improves the degenerated performance resulted from image flips and reduces both space and time costs. Flip invariance of FIND enables the intractable flip detection to be achieved easily, instead of duplicately implementing the procedure. To alleviate the pressure brought by the(More)
In video post-production applications, camera motion analysis and alignment are important in order to ensure the geometric correctness and temporal consistency. In this paper, we trade some generality in estimating and aligning camera motion for reduced computational complexity and increased image-based nature. The main contribution is to use fundamental(More)
Foreground detection plays a core role in a wide spectrum of applications such as tracking and behavior analysis. It, especially for videos captured by fixed cameras, can be posed as a component decomposition problem, the background of which is typically assumed to lie in a low dimensional subspace. However, in real world cases, dynamic backgrounds like(More)
When one records a video/image sequence through a transparent medium (e.g. glass), the image is often a su-perposition of a transmitted layer (scene behind the medium) and a reflected layer. Recovering the two layers from such images seems to be a highly ill-posed problem since the number of unknowns to recover is twice as many as the given measurements. In(More)
Compression of encrypted data draws much attention in recent years due to the security concerns in a service-oriented environment such as cloud computing. We propose a scalable lossy compression scheme for images having their pixel value encrypted with a standard stream cipher. The encrypted data are simply compressed by transmitting a uniformly subsampled(More)
This paper describes how model-specific constraints and domain specific knowledge can be utilized to develop efficient sampling based algorithms for robust model estimation in the presence of out-liers. As a special case, a robust algorithm for homography estimation is proposed that exploits the invariance of collinearity under homogra-phy to improve(More)