The digital watermarking schemes of today use pixels (samples in the case of audio), frequency or other transform coefficients to embed the information. The drawback of such schemes is that the watermark is not embedded in the perceptually significant portions of the data. We refer to such techniques as first generation watermarking schemes. In this paper we introduce the concept of second generation watermarking schemes which, unlike first generation watermarking schemes, employ the notion of data features. We propose a scheme based on point features in images using a scale interaction technique based on 2D continuous wavelets. The features are used to compute a Voronoi partition of the image. The watermark is embedded in each segment using spread spectrum watermarking. In the recovery process the same features are detected, and again used to partition the image. Then the watermark is extracted from each segment separately.

It is straightforward to apply general schemes for authenticating digital data to the problem of authenticating digital images. However, such a scheme would not authenticate images that have undergone lossy compression, even though they may not have been manipulated otherwise. We propose a scheme for authenticating the visual content of digital images. This scheme is robust to compression noise, but will detect deliberate manipulation of the image-data. The proposed scheme is based on the extraction of feature-points from the image. These feature-points are defined so as to be relatively unaffected by lossy compression. The set of feature-points from a given image is encrypted using public key encryption, to generate the digital signature of the image. Authenticity is verified by comparing the feature-points of the image in question, with those recovered from the previously computed digital signature.

This paper proposes a technique for spatio-temporal segmentation to identify the objects present in the scene represented in a video sequence. This technique processes two consecutive frames at a time. A region-merging approach is used to identify the objects in the scene. Starting from an oversegmentation of the current frame, the objects are formed by iteratively merging regions together. Regions are merged based on their mutual spatio-temporal similarity. We propose a modified Kolmogorov-Smirnov test for estimating the temporal similarity. The region-merging process is based on a weighted, directed graph. Two complementary graph-based clustering rules are proposed, namely, the strong rule and the weak rule. These rules take advantage of the natural structures present in the graph. Experimental results on different types of scenes demonstrate the ability of the proposed technique to automatically partition the scene into its constituent objects.

This paper presents the Swiss Federal Institute of Technology (EPFL) proposal to MPEG-4 video coding standardization activity. The proposed technique is based on a novel approach to audio-visual data compression entitled dynamic coding. The newly born multimedia environment supports a plethora of applications which cannot be covered adequately by a single compression technique. Dynamic coding offers the opportunity to combine several compression techniques and segmentation strategies. Given a particular application, these two degrees of freedom can be constrained and assembled in order to produce a particular profile which meets the set of specifications dictated by the application. The basic principles of this approach are presented together with the data representation system. The major characteristics of dynamic coding are reviewed, along with simulation results showing the performance of such an approach in a very low bit-rate video coding environment.

A region merging technique for spatio-temporal segmentation of scenes is presented. The proposed technique is a bottom-up method and expects an initial set of regions. These regions are compared on the basis of a similarity measure that integrates both spatial and temporal information. The unsupervised merging procedure is based on a weighted, directed graph that is updated dynamically. Two graph based clustering rules are presented. These rules are used to cluster regions into ensembles that represent meaningful objects present in the scene. Experimental results demonstrate the efficiency of the proposed method.

For content based image retrieval using shape descriptors, most approaches so far extract shape information from a segmentation of the image. Shape features derived based on a specific segmentation are not suitable for images containing complex structures. Further, static segmentation based approaches are useful only for a small set of queries. In this paper we discuss the limitations of such boundary based shape features, and propose an alternative shape characterization technique based on orientation radiograms. A working image retrieval system based on this approach is described and sample results are presented for a full-image query.

A multichannel filtering-based texture segmentation method is applied to a variety of document image processing problems: text-graphics separation, address-block location, and bar code localization. In each of these segmentation problems, the text context or bar code in the image is considered to define a unique texture. Thus, all three document analysis problems can be posed as texture segmentation problems. Two-dimensional Gabor filters are used to compute texture features. Both supervised and unsupervised methods are used to identify regions of text or bar code in the document images. The performance of the segmentation and classification scheme for a variety of document images demonstrates the generality and effectiveness of the approach.>

The authors have implemented a texture-based supervised segmentation method to identify potential destination address blocks in envelope images. Texture features are computed by using a set of even symmetric Gabor filters. A one-layer neural network classifier is used to classify pixels into text and non-text categories using four texture features. The authors also present a simple heuristic to select the correct destination address block from among several candidates identified. The method works well on several envelope images.>