Digital photography has made it possible to quickly and easily take a pair of images of low-light environments: one with flash to capture detail and one without flash to capture ambient illumination. We present a variety of applications that analyze and combine the strengths of such flash/no-flash image pairs. Our applications include denoising and detail transfer (to merge the ambient qualities of the no-flash image with the high-frequency flash detail), white-balancing (to change the color tone of the ambient image), continuous flash (to interactively adjust flash intensity), and red-eye removal (to repair artifacts in the flash image). We demonstrate how these applications can synthesize new images that are of higher quality than either of the originals.

/pdf/digital-photography-with-flash-and-no-flash-image-pairs-1axeg1z7xv.pdf

Digital photography with flash and no-flash image pairs

Super-resolution, the process of obtaining one or more high-resolution images from one or more low-resolution observations, has been a very attractive research topic over the last two decades. It has found practical applications in many real-world problems in different fields, from satellite and aerial imaging to medical image processing, to facial image analysis, text image analysis, sign and number plates reading, and biometrics recognition, to name a few. This has resulted in many research papers, each developing a new super-resolution algorithm for a specific purpose. The current comprehensive survey provides an overview of most of these published works by grouping them in a broad taxonomy. For each of the groups in the taxonomy, the basic concepts of the algorithms are first explained and then the paths through which each of these groups have evolved are given in detail, by mentioning the contributions of different authors to the basic concepts of each group. Furthermore, common issues in super-resolution algorithms, such as imaging models and registration algorithms, optimization of the cost functions employed, dealing with color information, improvement factors, assessment of super-resolution algorithms, and the most commonly employed databases are discussed.

/pdf/super-resolution-a-comprehensive-survey-xjl42yt9nt.pdf

Super-resolution: a comprehensive survey

We present an image-based modeling and editing system that takes a single photo as input. We represent a scene as a layered collection of depth images, where each pixel encodes both color and depth. Starting from an input image, we employ a suite of user-assisted techniques, based on a painting metaphor, to assign depths and extract layers. We introduce two specific editing operations. The first, a “clone brushing tool,” permits the distortion-free copying of parts of a picture, by using a parameterization optimization technique. The second, a “texture-illuminance decoupling filter,” discounts the effect of illumination on uniformly textured areas, by decoupling large- and small-scale features via bilateral filtering. Our system enables editing from different viewpoints, extracting and grouping of image-based objects, and modifying the shape, color, and illumination of these objects.

/pdf/image-based-modeling-and-photo-editing-2ye7pvltxg.pdf

Image-based modeling and photo editing

An image processing apparatus for tracking faces in an image stream iteratively receives an acquired image from the image stream including one or more face regions. The acquired image is sub-sampled at a specified resolution to provide a sub-sampled image. An integral image is then calculated for a least a portion of the sub-sampled image. Fixed size face detection is applied to at least a portion of the integral image to provide a set of candidate face regions. Responsive to the set of candidate face regions produced and any previously detected candidate face regions, the resolution is adjusted for sub-sampling a subsequent acquired image.

Real-time face tracking in a digital image acquisition device

A method analyzes the visual content of media such as videos for collecting together visually-similar appearances in their constituent images (e.g. same scenes, same objects, faces of the same people.) As a result, the most relevant and salient (of clearest and largest presence) visual appearances depicted in the videos are presented to the user, both for the sake of summarizing the video content for the users to “see before they watch” (that is, judge by the depicted video content in a filmstrip-like summary whether they want to mouse-click on the video and actually spend time watching it), as well as for allowing to users to further refine their video search result set according to the most relevant and salient video content returned (e.g. largest screen-time faces).

Apparatus and software system for and method of performing a visual-relevance-rank subsequent search

A red-eye reduction system is described that includes a masking module. The masking module converts an image into a mask having first state areas representing red color pixels of the image and second state areas representing other color pixels of the image. The image includes an eye with a red pupil. A pupil locating module is coupled to the masking module to locate a substantially first state area in the mask that resembles a pupil. A color replacing module is then coupled to the pupil locating module to change the red color pixels in the area into monochrome (grey) or other predefined colors. The color replacing module also adjusts the boundary of the area by changing the colors of pixels in close proximity to the area if the color of these pixels is determined to be sufficiently close to red such that natural appearance of the eye is maintained when reducing the red pupil. A method of reducing red-eye effect in a digital image is also described.

Apparatus and a method for reducing red-eye in a digital image

A method and system for capturing analog video data and previewing still video images of the captured analog video data without converting the analog video data into digital image data. The system takes analog video data and converts the data into raw digitized video data. The raw digitized video data is stored in a memory until the data is selected for previewing. Once selected, the raw digitized video data is reconverted into analog video data that presents a still image of the desired data. The system is also able to discard unnecessary portions of the raw digitized video data and store only necessary portions of the raw digitized video data. Preferably, the video capture, preview, and storage technique is used in video printing. When used in video printing, the raw digitized video data is converted into digital image data using a software decoding process.

Analog video frame capture and preview

Photographing people in a dark room with a compact camera using a flash often results in redeye. By scanning a photo effected by redeye into the computer, it is possible to digitally process the photo to correct redeye. We describe a process to automatically correct redeye with minimal user intervention. The redeye reduction process consists of three main blocks: create mask, pupil location, and replace color. The create mask block performs a segmentation of the data based on color information, and outputs a binary mask indicating the possible locations of redeye. The pupil location block processes the binary mask to determine a circular eye region. The replace color block changes the color of the circular eye region with some boundary adjustments. We have successfully tested this redeye reduction method on a large number of images. The algorithm is very user friendly and robust.

Automatic digital redeye reduction

A system and method for estimating motion between images performs correlation of candidate image blocks of a target digital image with potential image blocks of a reference digital image, in which pixel values of the images have been quantized, to estimate displacements of the candidate image blocks between the reference and target digital images. The correlation process may include a technique for counting the number of particular type bits in binary words. The counting technique involves performing bit-wise AND operations using a pair of masking binary words to derive first and second resulting binary words, shifting the second resulting binary word by a predefined number of bits and summing the first resulting binary word and the shifted binary word.

System and method for estimating motion between images

Distortion correction in an imaging system using parametric motion estimation. Parametric motion estimation is used to correct for geometric lens distortion and illumination changes. Models for geometric lens distortion and different illumination models are presented, as is a method for an iterative linearising method of solving the resulting sets of nonlinear equations.

Andrew J. Patti

Papers

Apparatus and a method for reducing red-eye in a digital image

Analog video frame capture and preview

Automatic digital redeye reduction

System and method for estimating motion between images

Correcting distortion in an imaging system using parametric motion estimation