Arms detection is one of the fundamental problems in human motion analysis application. The arms are considered as the most challenging body part to be detected since its pose and speed varies in image sequences. Moreover, the arms are usually occluded with other body parts such as the head and torso. In this paper, histogram-based skin colour segmentation is proposed to detect the arms in imag...

This paper presents a comparison of the most frequently used method RGB-IHS for fusion of Landsat 7 ETM+ multi-resolution bands with an approach based on introducing some textural coefficients issued from panchromatic band. The commonly used transformation RGB-IHS with the substitution of Intensity component by Panchro band leads to color alteration and changes of statistics of the input RGB co...

It is proposed that a new image enhancement scheme using wavelet transform, smooth and sharp approximation of a piecewise non linear filter technique after converting the RGB (Red, Green, and Blue) values of each pixel of the original image to HSV (Hue, Saturation, and Value). Wavelet transform is then applied to the luminance value of V component, it decomposes the input image into the four su...

A color estimation method for a gray-level image is proposed by giving a few color pixels. It is known that a density value in the gray-level image will be calculated by linear combination of an RGB vector of the color image. The problem dealt with in this study can be formulated as an ill-posed problem which searches for an RGB vector from a density value as a solution. By assuming a restricte...

The paper proposes a method for robust face recognition from low quality Kinect acquired images which have a wide range of variations in head pose, illumination, facial expressions, sunglass disguise and occlusions by hand. Multiple Kinect images of a person are considered as an image set and face recognition from these images is formulated as an RGB-D image set classification problem. The Kine...

Depth can complement RGB with useful cues about object volumes and scene layout. However, RGB-D image datasets are still too small for directly training deep convolutional neural networks (CNNs), in contrast to the massive monomodal RGB datasets. Previous works in RGB-D recognition typically combine two separate networks for RGB and depth data, pretrained with a large RGB dataset and then fine ...

In recent years, many applications using a pair of RGB and near-infrared (NIR) images have been proposed in computer vision and image processing communities. Thanks to recent progress of image sensor technology, it is also becoming possible to manufacture an image sensor with a novel spectral filter array, which has RGB plus NIR pixels for one-shot acquisition of the RGB and the NIR images. In ...

Recent project of National Aeronautics and Space Administration (NASA) to Mars promised to show 3D images of Mars surface. Spirit and Opportunity, identical Mars rovers of NASA, are equipped with a high-resolution stereo camera pair, called PanCam. Most cameras used by people are sensitive to three color bands, namely red (R), green (G) and blue (B). The PanCam is equipped with more color bands...

White balance algorithms try to remove color casts in images caused by non-white scene illuminants, transforming the images to appear as if they were taken under a canonical light source. We propose a new white balance algorithm for scenes with multiple lights, which requires that the colors of all scene illuminants and their relative contributions to each image pixel are determined. Prior work...

We build a dataset including four kinds of multispectral images with labeled key point correspondence. The dataset includes 7 RGB/NIR image pairs, 4 RGB/Depth image pairs, 3 Flash/no-flash image pairs and 4 different exposure image pairs. In each pair, we uniformly select corner points and label their correspondences. The resolution of the RGB/Depth image pairs is 640 × 480 and all the other im...