Meta-learning for Image Processing Based on Case-Based Reasoning - Computational Intelligence in Healthcare: Advanced Methodologies - page 218

Chapter 11
Meta-learning for Image Processing Based on
Case-Based Reasoning
Anja Attig and Petra Perner
Institute of Computer Vision and Applied Computer Sciences, IBaI, Leipzig, Germany
[e-mail]
www.ibai-institut.de
Abstract. We propose a framework for model building in image processing by
meta-learning based on case-based reasoning. The model-building process is
seen as a classification process during which the signal characteristics are
mapped to the right image-processing parameters to ensure the best image-
processing output. The mapping function is realized by case-based reasoning.
Case-based reasoning is especially suitable for this kind of process, since it in-
crementally allows one to learn the model based on the incoming data stream.
To find the right signal/image description of the signal/image characteristics
that are in relationship to the signal-processing parameters is one important
aspect of this work. In connection with this work intensive studies of the
theoretical, structural, and syntactical behavior of the chosen image-processing
algorithm have to be done. Based on this analysis we can propose several sig-
nal/image descriptions. The selected image description should summarize the
cases into groups of similar case and map these to the same processing parame-
ters. Having found groups of similar cases, these should be summarized by pro-
totypes that allow fast retrieval of several groups of cases. This generalization
process should permit building up the model over the course of time based on
the incrementally obtained data stream. We studied this task for image segmen-
tation based on the Watershed-Transformation. First, we studied the theoretical
and the implementation aspects of the Watershed Transformation and drew
conclusions for suitable image descriptions. Four different descriptions were
chosen - statistical and texture features, marginal distributions of columns,
rows, and diagonal similarity between the regional minima of two images, and
the shape descriptor based on central moments. Our study showed that the
weighted statistical and texture features and the shape descriptor based on cen-
tral moments have yielded the best image description so far for the Watershed
Transformation. It can best separate the cases into groups having the same seg-
mentation parameters and it sorts out rotated and rescaled images. Generaliza-
tion over cases can also be performed over the groups of case. It helps to speed
up the retrieval process and to learn incrementally the general model.
1 Introduction
The aim of image processing is to develop methods for automatically extracting from
an image or a video the desired information. The developed system should assist a