BEHNKE AND ROJAS: NEURAL ABSTRACTION PYRAMID, IJCNN'98 1 Neural Abstraction Pyramid: A hierarchical image understanding architecture
نویسنده
چکیده
|A hierarchical neural architecture for image interpretation is proposed that is based on image pyramids and cellular neural networks and that is inspired by the principles of information processing found in the visual cortex. Algorithms for this architecture are de ned in terms of local interactions of processing elements and utilize horizontal as well as vertical feedback loops. The goal is to transform a given image into a sequence of representations with increasing level of abstraction and decreasing level of detail. A rst application, the binarization of handwriting, has been implemented and shown to improve the acceptance rate of an automatic ZIP-code recognition system without decreasing its reliability. Keywords|image interpretation, cellular neural networks, hierarchy, image pyramids, horizontal and vertical feedback,
منابع مشابه
Recognition of Handwritten ZIP Codes in a Postal Sorting System
In this article, we describe the OCR and image processing algorithms used to read destination addresses from nonstandard letters (flats) by the Siemens postal automation system currently in use by the Deutsche Post AG.The article concentrates mainly on the two classifiers used to recognize handprinted digits. One of them is a complex time delayed neural network (TDNN) used to classify scaled di...
متن کاملPredicting away the Delay
This paper describes a method to reduce the effects of the system immanent delay for the RoboCup small size league. It explains how we solved the task by predicting the movement of our robots using a neural network. We have successfully field-tested the system at several RoboCup competitions with our FU-Fighters team. The predictions improve speed and accuracy of play.
متن کاملPredicting Away Robot Control Latency
This paper describes a method to reduce the effects of the system immanent control delay for the RoboCup small size league. It explains how we solved the task by predicting the movement of our robots using a neural network. Recently sensed robot positions and orientations as well as the most recent motion commands sent to the robot are used as input for the prediction. The neural network is tra...
متن کاملÊê Ùð Êó׸ëúò Òò¸ääö× Ãòòôôôòò¸òò Öòòòöö Öö Óø× Blockinð Ööö Íòòúö××øý Óó Öððò¸áò×øøøùøø Óó Óñôùøøö Ë Blockin Blockin Blockinò Ìù×øöº¸½½½½½ Öððò¸öññòý
Team Leader: Ra ul Rojas ( ollege professor) Team Members: Sven Behnke (s ienti sta ): general design Lars Knipping (s ienti sta ): behavior ontrol Bernhard Frots hl (s ienti sta ): web site, me hani s A him Liers (s ienti sta , did not attend ompetition): ele troni s Wolf Lindstrot (student): behavior ontrol Mark Simon (student): omputer vision, user interfa e Kirill Koule hov (student): beha...
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 2003