We present a novel learning-based image restoration and enhancement technique for improving character recognition performance of OCR products for degraded documents or documents/text captured with mobile devices such as camera-phones. The proposed technique is language independent and can simultaneously increase the effective resolution and restore broken characters with artifacts due to image capturing device such as a low quality/low resolution camera, or due to previous pre-processing such as extracting text region from the document image. The proposed technique develops a predictive relationship between high-resolution training images and their low-resolution/degraded counterparts, and exploits this relationship in a probabilistic scheme to generate a high resolution image from a low quality, low-resolution text image. We present a fast and scalable implementation of the proposed character restoration algorithm to improve the text recognition for document/text images captured by mobile phones. Experimental results demonstrate that the system effectively increases OCR performance for documents captured by mobile imaging devices, from levels of 50% to levels of over 80% for non-latin document/scene text images at 120dpi.

We present a new dense multi-view registration technique for wide-baseline video/images that integrates a parametric optical flow-based approach with a sparse set of feature correspondences, based on a locally planar approximation of a nonplanar scene. The proposed method can deal with illuminance variations between the views, which is critically important for wide-baseline applications. It differs from existing work on wide-baseline image registration in that it requires only image information and provides dense matching without computing any camera calibration matrices or performing any prior scene segmentation. These characteristics render the method suitable for practical deployment in visual sensor networks, towards which the current work is directed. We demonstrate the performance of the proposed method on simulated multi-view images of a virtual 3D world composed of piece-wise smooth textured surfaces, as well as real wide-baseline images of nonplanar textured surfaces.

We propose a new adaptive filtering framework for local image registration, which compensates for the effect of local distortions/displacements without explicitly estimating a distortion/displacement field. To this effect, we formulate local image registration as a two-dimensional (2-D) system identification problem with spatially varying system parameters. We utilize a 2-D adaptive filtering framework to identify the locally varying system parameters, where a new block adaptive filtering scheme is introduced. We discuss the conditions under which the adaptive filter coefficients conform to a local displacement vector at each pixel. Experimental results demonstrate that the proposed 2-D adaptive filtering framework is very successful in modeling and compensation of both local distortions, such as Stirmark attacks, and local motion, such as in the presence of a parallax field. In particular, we show that the proposed method can provide image registration to: a) enable reliable detection of watermarks following a Stirmark attack in nonblind detection scenarios, b) compensate for lens distortions, and c) align multiview images with nonparametric local motion.

Image registration is a fundamental task in both image processing and computer vision. We present a novel method for local image registration based on adaptive filtering techniques. We utilize an adaptive filter to estimate and track correspondences among multiple images containing overlapping views of common scene regions. Image pixels are traversed in an order established by space-filling curves, to preserve the contiguity and hence track locally varying registration changes. The algorithm differs from pre-existing work on image registration in that it requires only local information and relatively low computational effort. These characteristics render the method suitable for deployment in imaging sensor networks, toward which the current work is directed. We evaluate the performance of the proposed algorithm using images captured with a digital camera in various real-world scenarios. Experimental results show that the proposed method can significantly improve accuracy and robustness over a global 2D parametric registration and can also outperform the local registration algorithm based on the Lucas-Kanade optical flow technique (Lucas, B. and Kanade, T., 1981).

In many surveillance video applications, it is of interest to recognize an object or a person, which occupies a small portion of a low-resolution, noisy video. This paper addresses the problem of super-resolution recovery of a region of interest from more than one low-resolution view of a scene recorded by multiple cameras. The multiple camera scenario alleviates the difficulty in registration of multiple frames of video that contain non-rigid or multiple object motion in the single camera case. With proper temporal registration of multiple videos, arbitrary scene motion can be handled. The success of super-resolution recovery from multiple views in real applications vitally depends on two factors: i) the accuracy of multiple view registration results, and ii) the accuracy of the camera and data acquisition model. We propose a system, which consists of a method for sub-pixel accurate spatio-temporal alignment of multiple video sequences for view registration and the projections onto convex sets method for super-resolution recovery. Experiments were implemented using two commercial analog video cameras, which do not perform on-board compression. Experimental results show that the super resolution recovery of dynamic scenes can be achieved as long as the multiple views of the scene can be registered with sub-pixel accuracy.