G
Gerd Maderlechner
Researcher at Siemens
Publications - 44
Citations - 271
Gerd Maderlechner is an academic researcher from Siemens. The author has contributed to research in topics: Binary image & Hough transform. The author has an hindex of 9, co-authored 44 publications receiving 270 citations.
Papers
More filters
Proceedings ArticleDOI
Logo and word matching using a general approach to signal registration
TL;DR: The approach is based on a general theory for signal registration and is thus applicable to a broad variety of signal processing domains and has been fruitfully applied to solve speech and handwriting recognition as well as tasks in the field of document analysis.
Journal ArticleDOI
Classification of documents by form and content
TL;DR: A modular software system, which classifies a large variety of office documents according to layout form and textual content, consists of the following components: layout analysis, pre-classification, OCR interface, fuzzy string matching, text categorization, lexical, syntactical and semantic analysis.
Journal Article
'symbolic subtraction' of fixed formatted graphics and text from filled in forms
TL;DR: The 'symbolic difference' information in a form, from the fixed preprinted Sym(FF)-Sym(BF) means the recognition of the textual and graphical information of the blank filled-in text using the models of FF and BF.
Patent
Method of colour space encoding digital colour video signals, and system using such a method
TL;DR: For each pixel, a non-linear transformation of the RGB (RED/GREEN/BLUE) representation is carried out, in which process an imagined RGB color space, the three dimensions of which are represented by the colour parameters R, G and B and in which the relevant information word represents one space vector, is divided into colour-specific graduations which are equal with respect to sensation, so that a colour space having differently large volume elements in the RGB colour space is obtained.
Proceedings ArticleDOI
Conversion of high level information from scanned maps into geographic information systems
Gerd Maderlechner,Helmut Mayer +1 more
TL;DR: A system for automatic extraction of high level information from land register maps, e.g. parcels, buildings or roads, using explicit knowledge of the map and a mixed strategy by feedback cycles between the levels.