GasHolesJ- a software tool for measurement of gas holes in cheese

Abstract

The aim of this paper is to present an approach for objective and automatic detection and measure the gas holes in Swiss-type of cheese (Emmental) by computer vision techniques. Samples of four brands of Emmental cheese are bought from the marketplace. The cheese is factory cut into slices. Each slice of the cheese is captured at both sides by a digital camera and the images are saved locally in a computer. A standalone computer program called GasHolesJ is developed for processing the images. The program uses techniques for performing manual thresholding and nineteen algorithms for global auto thresholding are implemented in it. The results images obtained after performing manual and auto thresholding are analyzed and a difference operation between them is performed, in order to compare the efficiency of each auto threshold algorithms with the efficiency of manual threshold technique. The results show that six algorithms for global auto thresholding are effective enough for detection gas holes in Emmental cheese.