@article{Muggleton:2018:10.1007/s10994-018-5710-8,
author = {Muggleton, S and Dai, WZ and Sammut, C and Tamaddoni-Nezhad, A and Wen, J and Zhou, ZH},
doi = {10.1007/s10994-018-5710-8},
journal = {Machine Learning},
pages = {1097--1118},
title = {Meta-Interpretive Learning from noisy images},
url = {http://dx.doi.org/10.1007/s10994-018-5710-8},
volume = {107},
year = {2018}
}

Download

TY  - JOUR
AB  - Statistical machine learning is widely used in image classification. However, most techniques (1) require many images to achieve high accuracy and (2) do not provide support for reasoning below the level of classification, and so are unable to support secondary reasoning, such as the existence and position of light sources and other objects outside the image. This paper describes an Inductive Logic Programming approach called Logical Vision which overcomes some of these limitations. LV uses Meta-Interpretive Learning (MIL) combined with low-level extraction of high-contrast points sampled from the image to learn recursive logic programs describing the image. In published work LV was demonstrated capable of high-accuracy prediction of classes such as regular polygon from small numbers of images where Support Vector Machines and Convolutional Neural Networks gave near random predictions in some cases. LV has so far only been applied to noise-free, artificially generated images. This paper extends LV by (a) addressing classification noise using a new noise-telerant version of the MIL system Metagol, (b) addressing attribute noise using primitive-level statistical estimators to identify sub-objects in real images, (c) using a wider class of background models representing classical 2D shapes such as circles and ellipses, (d) providing richer learnable background knowledge in the form of a simple but generic recursive theory of light reflection. In our experiments we consider noisy images in both natural science settings and in a RoboCup competition setting. The natural science settings involve identification of the position of the light source in telescopic and microscopic images, while the RoboCup setting involves identification of the position of the ball. Our results indicate that with real images the new noise-robust version of LV using a single example (i.e. one-shot LV) converges to an accuracy at least comparable to a thirty-shot statistical machine learner on bot
AU  - Muggleton,S
AU  - Dai,WZ
AU  - Sammut,C
AU  - Tamaddoni-Nezhad,A
AU  - Wen,J
AU  - Zhou,ZH
DO  - 10.1007/s10994-018-5710-8
EP  - 1118
PY  - 2018///
SN  - 0885-6125
SP  - 1097
TI  - Meta-Interpretive Learning from noisy images
T2  - Machine Learning
UR  - http://dx.doi.org/10.1007/s10994-018-5710-8
UR  - http://hdl.handle.net/10044/1/61840
VL  - 107
ER  - 

Download