Automatic generation of morphological set recognition algorithms
Automatic generation of morphological set recognition algorithms
Computational vision
Object recognition by computer: the role of geometric constraints
Object recognition by computer: the role of geometric constraints
Ignorance, myopia, and naivete´ in computer vision systems
CVGIP: Image Understanding
Human and machine vision: computing perceptual organisation
Human and machine vision: computing perceptual organisation
Why progress in machine vision is so slow
Pattern Recognition Letters
Computability: a mathematical sketchbook
Computability: a mathematical sketchbook
Communications of the ACM
Knowledge-based image understanding systems: a survey
Computer Vision and Image Understanding
SUSAN—A New Approach to Low Level Image Processing
International Journal of Computer Vision
Genetic optimisation of the image feature extraction process
Pattern Recognition Letters
Image segmentation from consensus information
Computer Vision and Image Understanding
A New Model of Computation for Learning Vision Modules from Examples
Journal of Mathematical Imaging and Vision
Java Gently
Robot Vision
Java 1.1 Developer's Handbook; With Cdrom with Cdrom
Java 1.1 Developer's Handbook; With Cdrom with Cdrom
Goal-Directed Evaluation of Binarization Methods
IEEE Transactions on Pattern Analysis and Machine Intelligence
Adaptive Image Analysis for Aerial Surveillance
IEEE Intelligent Systems
A New Model of Computation for Learning Vision Modules from Examples
Journal of Mathematical Imaging and Vision
| Hi-index | 0.01 |
Recently the idea of designing a computer system whichautomatically connects a number of independent vision modulestogether to solve a given computer vision problem has attractedsignificant interest. However the main assumption of this endeavour,namely that the modules used as the building blocks of the visionsystem are essentially fixed, is questionable in the light ofprevious experience. Therefore it is important to be able to modifyeven the detailed operation of the basic modules used, somethingwhich is not practical using conventional techniques.This paper constructs a general method by which the computer code of avision module can be altered automatically to make it mimic a desiredbehaviour. The system which does this, termedL, modifies a basic module template using interaction with an Oracle as a guide. The Oracle is an entity which, when given an inputvalue, produces the corresponding output of the function which is to bemimicked. The system developed is based upon a new model of computationwhich endows it with the important properties that extracting thetemplate (i.e. structure) of any module‘s computer code, as well asdetermining the best questions to pose to the Oracle are both performedautomatically. Thus the L described has significant advantages overmany other models which might be used (e.g. Neural Networks).Dealing directly with this new model is not always convenient. Thereforea new computer language Madura is defined which provides ahigh-level interface to it. As Madura is syntactically similar to JAVA,it is simple to express the code of many basic vision modules in itsterms and the results of L (the Madura code of a module which mimics the Oracle) are similarly simple to understand and use.This paper shows a number of results which demonstrate how the L developed can learn many state-of-the-art initial vision algorithmsin a matter of minutes. The current and future impact of this work isalso examined.