A connectionist approach to quality assessment of food products

Tirthankar Raychaudhuri; Jeffrey Yeh; Leonard Hamey; Samuel Sung; Tas Westcott

A connectionist approach to quality assessment of food products

Tirthankar Raychaudhuri, Jeffrey Yeh, Leonard Hamey, Samuel Sung, Tas Westcott

School of Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

Abstract

Colour development of a product is often vital in the food industry. The study of the baking of biscuits reveals interesting colour development characteristic curves. Neural network methods are used to both represent and classify products according to these characteristics. Using self-organising maps well-defined characteristic curves are extracted. Colour data histogrammed along these curves are then accurately classified by feedforward neural networks trained by backpropagation. Image segmentation is implicit within this colour histogramming technique. The overall system has been shown to considerably outperform a human expert.

Original language	English
Title of host publication	A.I. '95 : Eighth Australian Joint Conference on Artificial Intelligence
Editors	X Yao
Publisher	World Scientific Publishing
Pages	435-441
Number of pages	7
ISBN (Print)	9810224842
Publication status	Published - 1995
Event	Australian Joint Conference on Artificial Intelligence (8th : 1995) - Canberra, Australia Duration: 13 Nov 1995 → 17 Nov 1995

Conference

Conference	Australian Joint Conference on Artificial Intelligence (8th : 1995)
Country/Territory	Australia
City	Canberra
Period	13/11/95 → 17/11/95

Cite this

@inproceedings{366216a59c0a454888c3ef62d0a31827,

title = "A connectionist approach to quality assessment of food products",

abstract = "Colour development of a product is often vital in the food industry. The study of the baking of biscuits reveals interesting colour development characteristic curves. Neural network methods are used to both represent and classify products according to these characteristics. Using self-organising maps well-defined characteristic curves are extracted. Colour data histogrammed along these curves are then accurately classified by feedforward neural networks trained by backpropagation. Image segmentation is implicit within this colour histogramming technique. The overall system has been shown to considerably outperform a human expert.",

author = "Tirthankar Raychaudhuri and Jeffrey Yeh and Leonard Hamey and Samuel Sung and Tas Westcott",

year = "1995",

language = "English",

isbn = "9810224842",

pages = "435--441",

editor = "X Yao",

booktitle = "A.I. '95 : Eighth Australian Joint Conference on Artificial Intelligence",

publisher = "World Scientific Publishing",

address = "Singapore",

note = "Australian Joint Conference on Artificial Intelligence (8th : 1995) ; Conference date: 13-11-1995 Through 17-11-1995",

}

A connectionist approach to quality assessment of food products. / Raychaudhuri, Tirthankar; Yeh, Jeffrey; Hamey, Leonard et al.
A.I. '95 : Eighth Australian Joint Conference on Artificial Intelligence. ed. / X Yao. World Scientific Publishing, 1995. p. 435-441.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - A connectionist approach to quality assessment of food products

AU - Raychaudhuri, Tirthankar

AU - Yeh, Jeffrey

AU - Hamey, Leonard

AU - Sung, Samuel

AU - Westcott, Tas

PY - 1995

Y1 - 1995

N2 - Colour development of a product is often vital in the food industry. The study of the baking of biscuits reveals interesting colour development characteristic curves. Neural network methods are used to both represent and classify products according to these characteristics. Using self-organising maps well-defined characteristic curves are extracted. Colour data histogrammed along these curves are then accurately classified by feedforward neural networks trained by backpropagation. Image segmentation is implicit within this colour histogramming technique. The overall system has been shown to considerably outperform a human expert.

AB - Colour development of a product is often vital in the food industry. The study of the baking of biscuits reveals interesting colour development characteristic curves. Neural network methods are used to both represent and classify products according to these characteristics. Using self-organising maps well-defined characteristic curves are extracted. Colour data histogrammed along these curves are then accurately classified by feedforward neural networks trained by backpropagation. Image segmentation is implicit within this colour histogramming technique. The overall system has been shown to considerably outperform a human expert.

M3 - Conference proceeding contribution

SN - 9810224842

SP - 435

EP - 441

BT - A.I. '95 : Eighth Australian Joint Conference on Artificial Intelligence

A2 - Yao, X

PB - World Scientific Publishing

T2 - Australian Joint Conference on Artificial Intelligence (8th : 1995)

Y2 - 13 November 1995 through 17 November 1995

ER -

A connectionist approach to quality assessment of food products

Abstract

Conference

Fingerprint

Cite this