Information Measure Based Skeletonisation
نویسندگان
چکیده
Automatic determination of proper neural network topology by trimming over-sized networks is an important area of study, which has previously been addressed using a variety of techniques. In this paper, we present Information Measure Based Skeletonisation (IMBS), a new approach to this problem where superfluous hidden units are removed based on their information measure (1M). This measure, borrowed from decision tree induction techniques, reflects the degree to which the hyperplane formed by a hidden unit discriminates between training data classes. We show the results of applying IMBS to three classification tasks and demonstrate that it removes a substantial number of hidden units without significantly affecting network performance.
منابع مشابه
Flux driven medial curve extraction
In this document it is described the implementation of the flux driven automatic centerline extraction algorithm proposed by Bouix et al. in 2004. This is based on a skeletonisation algorithm initially proposed by Siddiqi et al. in 2002, using properties of an average outward flux measure to distinguish skeletal points from non-skeletal ones. This information is combined with a topology preserv...
متن کاملSkeletonisation as mobile robot navigation
In this paper, a novel skeletonisation algorithm is presented that draws on techniques developed for mobile robot mapping and navigation and offers a number of advantages over existing skeletonisation methods. First, because the algorithm works by hopping from one landmark position in the image to another, it has to visit far fewer pixels to find a skeleton compared to conventional algorithms. ...
متن کاملAn Adaptive GIS Tool For Image Characterisation
GIS systems often rely on low-level, pixel-based representations of satellite scenes. The purpose of this paper is to show the advantages of using an intermediate representation incorporating multiple criteria in scene characterisation, as well as a framework for monitoring changes over time based on features of interest. A Conceptual Spaces framework, in conjunction with navigation-based skele...
متن کاملStrokes Detection for Skeletonisation of Characters Shapes
Skeletonisation is a key process in character recognition in natural images. Under the assumption that a character is made of a stroke of uniform colour, with small variation in thickness, the process of recognising characters can be decomposed in the three steps. First the image is segmented, then each segment is transformed into a set of connected strokes (skeletonisation), which are then abs...
متن کاملRefined Homotopic Thinning Algorithms and Quality Measures for Skeletonisation Methods
Topological skeletons are shape descriptors that have been applied successfully in practical applications. However, many skeletonisation methods lack accessibility, mainly due to the need for manual parameter adjustment and the shortage of tools for comparative analysis. In this paper we address these problems. We propose two new homotopypreserving thinning algorithms: Flux-ordered adaptive thi...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1991