JBIG2 is a new standard for lossy and lossless compression of bi-level images. It exploits model-based coding for text and halftones; as well as nearby neighbor based coding for generic bi-level images. It can achieve compression ratios of up to three times those of existing standards for lossless textual image compression. JBIG2 also allows loss to be introduced while maintaining "visually lossless" quality for textual images, for which it can yield compression ratios of up to eight times those of existing standards. It produces even greater compression ratios when exploiting similarities between multiple pages and efficiently codes and integrates both scanned and generated bi-level images. JBIG2 was developed for applications having widely differing requirements such as facsimile, document storage and archiving, Web image coding, wireless data transmission, print spooling, and even teleconferencing. Accordingly, JBIG2 is structured as a "toolkit" of alternate capabilities to be selected based on the requirements of such applications.

We describe a segmentation method and associated file format for storing images of color documents. We separate each page of the document into three layers, containing the background (usually one or more photographic images), the text, and the color of the text. Each of these layers has different properties, making it desirable to use different compression methods to represent the three layers. The background layers are compressed using any method designed for photographic images, the text layers are compressed using a token-based representation, and the text color layers are compressed by augmenting the representation used for the text layers. We also describe an algorithm for segmenting images into these three layers. This representation and algorithm can produce very highly-compressed document files that nonetheless retain excellent image quality.

The Joint Bi-Level Image Experts Group (JBIG), an international study group affiliated with ISO/IEC and ITU-T, is in the process of drafting a new standard for lossy and lossless compression of bilevel images. The new standard, informally referred to as JBIG2, will support model-based coding for text and halftones to permit compression ratios up to three times those of existing standards for lossless compression. JBIG2 will also permit lossy preprocessing without specifying how it is to be done, In this case, compression ratios up to eight times those of existing standards may be obtained with imperceptible loss of quality. It is expected that JBIG2 will become an international standard by 2000.

We address the problem of locating a gray-level pattern in a gray-level image. The pattern can have been transformed by an affine transformation, and may have undergone some additional changes. We define a difference function based on comparing each pixel of the pattern with a window in the image, and search efficiently for transformations that minimize the difference function. The search is guaranteed: it will always find the transformation minimising the difference function, and not get fooled by a local minimum; it is also efficient, in that it does not need to examine every transformation in order to achieve this guarantee. This technique can be applied to object location, motion tracking, optical flow, or block-based motion compensation in video image sequence compression (e.g., MPEG).

The Hausdorff distance is a measure defined between two point sets representing a model and an image. In the past, it has been used to search images for instances of a model that has been translated or translated and scaled by finding transformations that bring a large number of model features close to image features, and vice versa. The Hausdorff distance is reliable even when the image contains multiple objects, noise, spurious features, and occlusions. We apply it to the task of locating an affine transformation of a model in an image; this corresponds to determining the pose of a planar object that has undergone weak perspective projection. We develop a rasterised approach to the search and a number of techniques that allow us to quickly locate all transformations of the model that satisfy two quality criteria; we can also quickly locate only the best transformation. We discuss an implementation of this approach, and present some examples of its use.>

We present a method for navigating a robot from an initial position to a specified landmark in its visual field, using a sequence of monocular images. The location of the landmark with respect to the robot is determined using the change in size and position of the landmark in the image as the robot moves. The landmark location is estimated after the first three images are taken, and this estimate is refined after each motion. One of the novel aspects of this method is that it uses no explicit three-dimensional information.>

The Hausdorff distance measures the extent to which each point of a model set lies near some point of an image set and vice versa. An efficient method of computing this distance is developed, based on a multi-resolution tessellation of the space is possible transformations of the model set. One of the key ideas is that entire cells in this tessellation can be ruled out quickly, without actually computing the Hausdorff distance for many of them. Emphasis is placed on the case in which the model is allowed to translate and scale (independently in x and y) with respect to the image. This four-dimensional transformation space is searched rapidly while guaranteeing that no match will be missed. Some examples of identifying an object in a cluttered scene are presented, including cases where the object is partially hidden from view.>

The authors describe a model-based method for tracking nonrigid objects moving in a complex scene. The method operates by extracting two-dimensional models of an object from a sequence of images. The basic idea underlying the technique is to decompose the image of a solid object moving in space into two components: a two-dimensional motion and a two-dimensional shape change. The motion component is factored out and the shape change is represented explicitly by a sequence of two-dimensional models, one corresponding to each image frame. The major assumption underlying the method is that the two-dimensional shape of an object will change slowly from one frame to the next. There is no assumption, however, that the two-dimensional image motion between successive frames will be small.>

The Hausdorff distance measures the extent to which each point of a model set lies near some point of an image set and vice versa. Thus, this distance can be used to determine the degree of resemblance between two objects that are superimposed on one another. Efficient algorithms for computing the Hausdorff distance between all possible relative positions of a binary image and a model are presented. The focus is primarily on the case in which the model is only allowed to translate with respect to the image. The techniques are extended to rigid motion. The Hausdorff distance computation differs from many other shape comparison methods in that no correspondence between the model and the image is derived. The method is quite tolerant of small position errors such as those that occur with edge detectors and other feature extraction methods. It is shown that the method extends naturally to the problem of comparing a portion of a model against an image.>

Efficient algorithms are provided for computing the Hausdorff distance between a binary image and all possible relative positions (translations) of a model, or a portion of that model. The computation is in many ways similar to binary correlation. However, it is more tolerant of perturbations in the locations of points because it measures proximity rather than exact superposition.>