Measurement of the rennet clotting time of milk by digital image sequences (2D + t) processing

The aim of the work presented in this paper was to determine the rennet clotting time of milk by image sequences (2D + t) processing. A computer vision system (CVS) consisting of a computer coupled with a transmitted light microscope equipped with a digital camera was developed. Each image was decomposed into Red, Green, Blue (RGB) color components and luminance histograms, through algorithms implemented with Matlab 7.7 software. These algorithms computed and analyzed the R, G, B color components and luminance histogram peak in each image. It was shown that during milk coagulation, this histogram peak varies according to sigmoidal law Peak(t) = Peakmin + (Peakmax − Peakmin)/[1 + (t/TC)α], where TC is the rennet coagulation time.

► We acquire images sequences of rennet-induced milk during coagulation.
► We decompose each image of the sequences into its red, green and blue color components and luminance histograms.
► We extract from each color and luminance histogram the peak of histogram.
► Peaks of histograms change and decrease during coagulation.
► Milk coagulation can be controlled through red, green, blue color components and luminance.