Fraunhofer-Institut für Produktionsanlagen und Konstruktionstechnik IPK

Filters

7
1
Reset filters

Settings
Now showing 1 - 7 of 7
No Thumbnail Available
Publication

A background maintenance model in the spatial-range domain

2004 , Kottow, D. , Köppen, M. , Ruiz del Solar, J.

In this article a background maintenance model defined by a finite set of codebook vectors in the spatial-range domain is proposed. The model represents its current state by a foreground and a background set of codebook vectors. Algorithms that dynamically update these sets by adding and removing codebook vectors are described. This approach is fundamentally different from algorithms that maintain a background representation at the pixel level and continously update their parameters. The performance of the model is demonstrated and compared to other background maintenance models using a suitable benchmark of video sequences.

View
No Thumbnail Available
Publication

Steady-state image processing

2001 , Köppen, M. , Ruiz del Solar, J.

This paper presents a new approach to the application mode of image processing operators, the so-called steady-state image processing. The approach reminds a steady-state genetic processing of images by considering each pixel of the image as an individual. So, some pixels are selected, processed and copied back into the image. This differs from the standard approach, where all image pixels are processed at once. The proposed approach offers many choices for variation, and allows for the assignment of dynamic measures to images. This will serve new families of soft computing methods as, e.g. immune-based algorithms, which need images as non-static objects in order to fulfill reasonable tasks. This paper also introduces some basic steady-state operators and exemplifies the analysis of an image by means of a small example. Also, it is shown how steady-state image processing can be applied in the context of texture segmentation. Steady-state image processing can be considered a way of processing images, which is deeply inspired by genetic algorithms.

View
No Thumbnail Available
Publication

Automatic generation of oriented filters for texture segmentation

1996 , Ruiz del Solar, J. , Köppen, M.

View
No Thumbnail Available
Publication

Temporal dynamical interactions between multiple layers of local image features for event detection in video sequences

2003 , Kottow, D. , Köppen, M. , Ruiz del Solar, J.

In this paper an approach for storing and employing local image features in video processing is presented. The approach is based on the usage of memory cells representing local image features and (non-fixed) spatial positions, which are organized in memory layers. By assigning frame-based recall function and learning procedure to the cells, the memory layers establish a content-based auto-associative memory. Thus, they can be applied to solve several event detection tasks, as it is exemplified by dynamic background supression in a traffic scene, and counting of persons halting before a shopping window in an indoor scene. The case studies suggest that information gathered from the cells (like cell history based scoring values) can be used in various manners for video processing tasks circumventing the need for object segmentation and tracking, typical in many conventional background-differencing methods.

View
No Thumbnail Available
Publication

Autopoiesis and image processing. Detection of structure and organization in images

1999 , Köppen, M. , Ruiz del Solar, J.

View
No Thumbnail Available
Publication

Soft-biometrics: Soft-computing for biometric-applications

2002 , Franke, K. , Ruiz del Solar, J. , Köppen, M.

A biometric system testifies the authenticity of a specific physiological or behavioral characteristic possessed by a user. New requirements for biometric systems such as robustness, higher recognition rates, tolerance for imprecision and uncertainty, and flexibility call for the use of new computing technologies. Soft- computing is increasingly being used in the development of biometric applications. Soft-biometrics corresponds to a new emerging paradigm that consists in the use of soft-computing technologies for the development of biometric applications. The aim of this paper is to motivate discussion on the application of soft-computing approaches to specific biometric measurements. The feasibility of soft-computing as a tool-set to biometric applications should be investigated. Finally, an application example on static signature verification is presented, providing evidence of the impact of soft-computing in biometrics.

View
No Thumbnail Available
Publication

Sewage pipe image segmentation using a neural based architecture

1996 , Ruiz del Solar, J. , Köppen, M.

View