The context in which an object is found can facilitate its recognition. Yet, it is not known how effective this contextual information is relative to the object's intrinsic visual features, such as color and shape. To address this, we performed four experiments using rendered scenes with novel objects. In each experiment, participants first performed a visual search task, searching for a unique...

Feature discrimination is a critical component in large scale satellite image browsing and retrieval, as well as in other areas of remote sensing. As many satellite images are multi-spectral, the spectral information should be exploited for efficient browsing and retrieval. In this aspect, color is a suitable candidate to represent the spectral contents. This paper presents an efficient algorit...

In a picture of a bright scene, camera sensor readings may be saturated to a maximal value. This results in loss of variation and color distortion of bright regions in the image. We present an algorithm that exploits data from uncorrupted channels to recover image details and color information. The correction is based on the Color Lines model for image representation in RGB color space. Given a...

This paper introduces a calibration-based auto white balance method for digital still camera. The main idea is to detect white-points in an image accurately. White-Point Color Temperature Curve (WPCTC) is constructed from sensor calibration and is utilized to estimate white-point locations in a scene. Minimum Color Temperature Distance (MCTD) with a luminance threshold is defined to further loc...

A new method is presented for the recognition and the localization of three-dimensional objects using color information. In the first processing step a chromatic block matching method is applied to find corresponding pixels in a color stereo image. Second, the computed disparity maps are segmented to distinguish between the image background and the objects that should be recognized. Assuming th...

We investigate the problem of source separation in images in the Bayesian framework using the color channel dependencies. As a case in point we consider the source separation of color images which have dependence between its components. A Markov Random Field (MRF) is used for modeling of the inter and intra-source local correlations. We resort to Gibbs sampling algorithm for obtaining the MAP e...

In general, computational methods to estimate the color of the light source are based on single, low-level image cues such as pixel values and edges. Only a few methods are proposed exploiting multiple cues for color constancy by incorporating pixel values, edge information and higher-order image statistics. However, expanding color constancy beyond these low-level image statistics (pixels, edg...

We introduce Scene Structural Matrix (SSM), a novel image content descriptor and its application to invariant image retrieval. The SSM captures the overall structural characteristics of the scene by indexing the geometric features of the image. We employ a binary image tree (bintree) to partition the image and from which we derive multiscale geometric structural descriptors of the image. We hav...