A process is designed to fuse multiple images of the same scene to produce an image that contains less noise and more information. First, the speckle noise is removed. Second, histogram equalization is applied to expose details and maximize the information content of the image. Third, images are registered to prepare for fusion. In the fourth step, we apply our new pointwise spatial frequency m...

This paper empirically compares two algorithms for classifying remotely sensed images: The minimum-distance classifier and peer group pixels based spatial classifier. The minimum-distance classifier is a per-pixel classifier. The spatial classifier incorporates contextual information by using the average of the pixels from a peer group of each pixel and classifying this pixel into one of severa...

A small baseline stereo matching method based on maximum like estimation is proposed. Firstly, the mixed window strategy is used to determine the matching window for each point in the reference image. Secondly, the normalized cross correlation function is employed to compute matching cost for possible matching points in the disparity range, then the “winner-take all” strategy is utilized to com...

A robust skin detector is the primary need of many fields of computer vision, including face detection, gesture recognition, and pornography filtering. Less than 10 years ago, the first paper on automatic pornography filtering was published. Since then, different researchers claim different color spaces to be the best choice for skin detection in pornography filtering. Unfortunately, no com...

A new grayscale image authentication method with a pixel-level self-recovering capability for tampered region repairing is proposed. By dividing the grayscale range into bins, a 3-bit bin code is generated as the authentication signal for each pixel in the input cover image. The authentication signals then are embedded randomly into the image pixels for the double purposes of tampering localiza...

Because hyperspectral imagery is generally low resolution, it is possible for one pixel in the image to contain several materials. The process of determining the abundance of representative materials in a single pixel is called spectral unmixing. We discuss the L1 unmixing model and fast computational approaches based on Bregman iteration. We then use the unmixing information and Total Variatio...

ABSTRACT We have developed an image-sensor-based optical receiver for free-space optical communications. In our scheme, each pixel has a function of an optical receiver as well as an image sensor. The functional mode can be selected pixel by pixel. The position of a communication target is detected from the image captured in the image sensor mode. Then, functional mode of the pixel receiving op...