Using learning in segmentation or recognition tasks has several advantages over classical model-based techniques. These include adaptivity to noise and changing environments, as well as in many cases, a simplified system generation procedure. Yet, learning from examples introduces a new challenge getting a representative data set of examples from which to learn. Applications of learning systems...

We explore recently proposed nonparametric Bayesian statistical models of image partitions. These models are attractive because they adapt to images of different complexity, successfully modeling uncertainty in size, shape, and structure of human segmentations of natural scenes. We improve upon them in a number of key ways to achieve performance comparable to state-of-the-art methods. Our first...

The aim of semantic image understanding is to reveal the semantic meaning behind the image pixel. We categorize semantic image understanding into two broad categories: pixel-level and image-level semantic image understanding. While pixel-level image understanding aims to obtain the semantic meaning of each pixel, image-level understanding aims to obtain the semantic meaning of the whole image, ...

In this article, we present how it is possible to recover physical parameters of objects such as reflectivity, emissivity and thermal inertia from the analysis of infrared images in outdoor scenes. Our approach is based on the extensive use of the physical laws that are at the origin of the formation of images. First, we derive a physical model that describes how surface patches of objects appe...

This paper proposes a new approach to the processing and analysis of medical images. We introduce the term and methodology of medical data understanding, as a new step in the way of starting from image processing, and followed by analysis and classification (recognition). The general view of the situation of the new technology of machine perception and image understanding in the context of the ...

h 1 The huge volume of data produced every day is posing a signifiant challenge to computer scientists since it is infeasible that this ata can be effectively processed and consistently interpreted by umans manually, even to a very small extent. Due to the automaion of many industrial processes and the advent of cheaper and igh-performance sensors, many aspects of life, including medial, commer...

The views, opinions, and findings contained in this report are those of the authors and should not be construed as an official Agency position, policy, or decision, unless so designated by other official documentation. Abstract In this Phase I effort, we designed a hybrid image understanding system consisting of neural network software running on parallel hardware and symbolic processing softwa...

Nearest Neighbour algorithms for pattern recognition have been widely studied. It is now well-established that they offer a quick and reliable method of data classification. In this paper we further develop the basic definition of the standard k-nearest neighbour algorithm to include the ability to resolve conflicts when the highest number of nearest neighbours are found for more than one train...

In this paper, we present a set of heterogeneous algorithms for computer vision tasks using the Image Understanding Architecture IUA]. The full-scale IUA developed jointly by Hughes Research Labs and University of Massachusetts at Amherst is a multiple level heterogeneous architecture. Each level is constructed to perform tasks most suitable to its mode of processing. The lowest level called CA...