Chemical machine vision: Automated extraction of chemical metadata from raster images

Standard

Chemical machine vision: Automated extraction of chemical metadata from raster images. / Gkoutos, Georgios V; Rzepa, Henry; Clark, Richard M; Adjei, Osei; Johal, Harpal.

In: Journal of Chemical Information and Computer Sciences, Vol. 43, No. 5, 2003, p. 1342-1355.

Research output: Contribution to journalArticlepeer-review

Harvard

Gkoutos, GV, Rzepa, H, Clark, RM, Adjei, O & Johal, H 2003, 'Chemical machine vision: Automated extraction of chemical metadata from raster images', Journal of Chemical Information and Computer Sciences, vol. 43, no. 5, pp. 1342-1355. https://doi.org/10.1021/ci034017n

APA

Gkoutos, G. V., Rzepa, H., Clark, R. M., Adjei, O., & Johal, H. (2003). Chemical machine vision: Automated extraction of chemical metadata from raster images. Journal of Chemical Information and Computer Sciences, 43(5), 1342-1355. https://doi.org/10.1021/ci034017n

Vancouver

Gkoutos GV, Rzepa H, Clark RM, Adjei O, Johal H. Chemical machine vision: Automated extraction of chemical metadata from raster images. Journal of Chemical Information and Computer Sciences. 2003;43(5):1342-1355. https://doi.org/10.1021/ci034017n

Author

Gkoutos, Georgios V ; Rzepa, Henry ; Clark, Richard M ; Adjei, Osei ; Johal, Harpal. / Chemical machine vision: Automated extraction of chemical metadata from raster images. In: Journal of Chemical Information and Computer Sciences. 2003 ; Vol. 43, No. 5. pp. 1342-1355.

Bibtex - Download

@article{00f4c1b9f202411ebc6eea80c4c356f3,
title = "Chemical machine vision: Automated extraction of chemical metadata from raster images",
abstract = "We present a novel application of machine vision methods for the identification of chemical composition diagrams from two-dimensional digital raster images. The method is based on the use of Gabor wavelets and an energy function to derive feature vectors from digital images. These are used for training and classification purposes using a Kohonen network for classification with the Euclidean distance norm. We compare this method with previous approaches to transforming such images to a molecular connection table, which are designed to achieve complete atom connection table fidelity but at the expense of requiring human interaction. The present texture-based approach is complementary in attempting to recognize higher order features such as the presence of a chemical representation in the original raster image. This information can be used for providing chemical metadata descriptors of the original image as part of a robot-based Internet resource discovery tool. ",
author = "Gkoutos, {Georgios V} and Henry Rzepa and Clark, {Richard M} and Osei Adjei and Harpal Johal",
year = "2003",
doi = "10.1021/ci034017n",
language = "English",
volume = "43",
pages = "1342--1355",
journal = "Journal of Chemical Information and Computer Sciences",
issn = "0095-2338",
publisher = "American Chemical Society",
number = "5",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Chemical machine vision: Automated extraction of chemical metadata from raster images

AU - Gkoutos, Georgios V

AU - Rzepa, Henry

AU - Clark, Richard M

AU - Adjei, Osei

AU - Johal, Harpal

PY - 2003

Y1 - 2003

N2 - We present a novel application of machine vision methods for the identification of chemical composition diagrams from two-dimensional digital raster images. The method is based on the use of Gabor wavelets and an energy function to derive feature vectors from digital images. These are used for training and classification purposes using a Kohonen network for classification with the Euclidean distance norm. We compare this method with previous approaches to transforming such images to a molecular connection table, which are designed to achieve complete atom connection table fidelity but at the expense of requiring human interaction. The present texture-based approach is complementary in attempting to recognize higher order features such as the presence of a chemical representation in the original raster image. This information can be used for providing chemical metadata descriptors of the original image as part of a robot-based Internet resource discovery tool.

AB - We present a novel application of machine vision methods for the identification of chemical composition diagrams from two-dimensional digital raster images. The method is based on the use of Gabor wavelets and an energy function to derive feature vectors from digital images. These are used for training and classification purposes using a Kohonen network for classification with the Euclidean distance norm. We compare this method with previous approaches to transforming such images to a molecular connection table, which are designed to achieve complete atom connection table fidelity but at the expense of requiring human interaction. The present texture-based approach is complementary in attempting to recognize higher order features such as the presence of a chemical representation in the original raster image. This information can be used for providing chemical metadata descriptors of the original image as part of a robot-based Internet resource discovery tool.

UR - http://hdl.handle.net/2160/12071

U2 - 10.1021/ci034017n

DO - 10.1021/ci034017n

M3 - Article

C2 - 14502466

VL - 43

SP - 1342

EP - 1355

JO - Journal of Chemical Information and Computer Sciences

JF - Journal of Chemical Information and Computer Sciences

SN - 0095-2338

IS - 5

ER -

View graph of relations
Citation formats