Appears in Proc. Digital Image Computing: Techniques and Applications
Sydney, 8-10 December 1993, pages 124-129.
Copyright ? 1993 L. Hamey, A. Watson and T. Westcott.

MACHINE INSPECTION OF BISCUIT BAKE

Leonard G. C. Hamey (+)
Annesley J. Watson (*)
C. Tasman Westcott (*)

(+) Department of Computing, Macquarie University, NSW 2109 Australia (*) Arnott's Biscuits Limited, George St, Homebush, NSW 2140 Australia

ABSTRACT

A prototype system for automated assessment of biscuit bake has been developed. The system employs monochrome imaging and histogramming techniques to classify product samples as underbaked, correctly baked or overbaked. Two products have been investigated. Product A" exhibits uneven browing due to the formation of blisters. An intensity histogram suitably characterises the overall browning and the prototype system classifies samples of product A" with an error rate comparable to that of a trained inspector. Product B" browns most heavily on the perimeter on the biscuit. A boundary-distance histogram is used to classify samples of product B". In this case also, the system performance is comparable with a trained inspector.

1 INTRODUCTION

Inspection of baked goods is important to ensure correct taste, texture and appearance. Such inspection is normally performed by trained inspectors who examine the product and report unacceptable product. A major problem of this approach is the subjective nature of the inspection process and the long-term drift in product quality that results from the lack of immutable objective standards for comparison. Increasingly, then, the baking industry is turning to alternative technologies such as machine vision to provide objective inspection mechanisms [1, 2, 3, 4, 5].

We describe a prototype system for the inspection of the degree of bake of biscuits, as indicated by colour development with exposure to heat. In our initial experiments, two specific products were chosen (figure 1) because of their distinctive patterns of colour development during baking. Product A" is characterised by regions of high bake colour where a flakey thin blister forms on the top of the biscuit, and regions of low bake colour where blisters do not occur. The positions of the blisters are unpredictable.

Product B" bakes most heavily around the perimeter and the edges may be considered to be overbaked long before there is any futher development of colour in the centre of the biscuit. Clearly, then, the methods of bake assessment for products A" and B" need to be markedly different.