Open Access

For the efficient management of large image databases, the automated characterization of images and the usage of that characterization for searching and ordering tasks is highly desirable. The purpose of the project SEMACODE is to combine the still unsolved problem of content-oriented characterization of images with scale-invariant object recognition and modelbased compression methods. To achieve this goal, existing techniques as well as new concepts related to pattern matching, image encoding, and image compression are examined. The resulting methods are integrated in a common framework with the aid of a content-oriented conception. For the application, an image database at the library of the university of Frankfurt/Main (StUB; about 60000 images), the required operations are developed. The search and query interfaces are defined in close cooperation with the StUB project “Digitized Colonial Picture Library”. This report describes the fundamentals and first results of the image encoding and object recognition algorithms developed within the scope of the project.

Classically, encoding of images by only a few, important components is done by the Principal Component Analysis (PCA). Recently, a data analysis tool called Independent Component Analysis (ICA) for the separation of independent influences in signals has found strong interest in the neural network community. This approach has also been applied to images. Whereas the approach assumes continuous source channels mixed up to the same number of channels by a mixing matrix, we assume that images are composed by only a few image primitives. This means that for images we have less sources than pixels. Additionally, in order to reduce unimportant information, we aim only for the most important source patterns with the highest occurrence probabilities or biggest information called „Principal Independent Components (PIC)“. For the example of a synthetic picture composed by characters this idea gives us the most important ones. Nevertheless, for natural images where no a-priori probabilities can be computed this does not lead to an acceptable reproduction error. Combining the traditional principal component criteria of PCA with the independence property of ICA we obtain a better encoding. It turns out that this definition of PIC implements the classical demand of Shannon’s rate distortion theory.

We consider the problem of unifying a set of equations between second-order terms. Terms are constructed from function symbols, constant symbols and variables, and furthermore using monadic second-order variables that may stand for a term with one hole, and parametric terms. We consider stratified systems, where for every first-order and second-order variable, the string of second-order variables on the path from the root of a term to every occurrence of this variable is always the same. It is shown that unification of stratified second-order terms is decidable by describing a nondeterministic decision algorithm that eventually uses Makanin's algorithm for deciding the unifiability of word equations. As a generalization, we show that the method can be used as a unification procedure for non-stratified second-order systems, and describe conditions for termination in the general case.

It is well known that artificial neural nets can be used as approximators of any continous functions to any desired degree. Nevertheless, for a given application and a given network architecture the non-trivial task rests to determine the necessary number of neurons and the necessary accuracy (number of bits) per weight for a satisfactory operation. In this paper the problem is treated by an information theoretic approach. The values for the weights and thresholds in the approximator network are determined analytically. Furthermore, the accuracy of the weights and the number of neurons are seen as general system parameters which determine the the maximal output information (i.e. the approximation error) by the absolute amount and the relative distribution of information contained in the network. A new principle of optimal information distribution is proposed and the conditions for the optimal system parameters are derived. For the simple, instructive example of a linear approximation of a non-linear, quadratic function, the principle of optimal information distribution gives the the optimal system parameters, i.e. the number of neurons and the different resolutions of the variables.