Method of monitoring the appearance of the surface of a tire

A method for detecting an anomaly on the surface of a tire by digital processing of the image of the surface of a tire, wherein a combination of filters able to identify the signature of the image of an anomaly present on the surface of the tire is selected comprising the steps in the course of which:

• A—the image of a given anomaly present on the surface of at least one tire is produced,
• B—with the aid of a collection formed of a plurality of filters ((F1(ƒ), F2(ƒ), . . . , (FL(ƒ), (F1(ƒ), F2(ƒ), . . . , FM(ƒ))), a multivariate image (Fƒ(x)=(F1ƒ(x), F2ƒ(x), . . . , FLƒ(x)), Fƒ(x)=(F1ƒ(x), F2ƒ(x), . . . , FMƒ(x))) of the said surface is constructed, in a space of the filters, in which each pixel is represented in the form of a pixel vector (Fƒ(x)), the components of each pixel vector having a value corresponding to the value of this pixel in the image transformed with the aid of each of the filters of the said collection,
• C—with the aid of a linear function (ζ), this multivariate image is transformed from the space of the filters into a spectral space of given dimension (L, M) whose variables are the filters or combinations of filters of the said collection, so as to form a spectral image (Fƒ(x)=(F1ƒ(x), F2ƒ(x), . . . , FLƒ(x)), c′(x)=(c′1(x), c′2(x), c′N(x)), c(x)=(c1(x), c2(x), . . . , cK(x))),
• D—a classifier is constructed by determining, for this anomaly, those zones representative of the spectral space which contain, in a statistically representative manner, the points of the spectral image of the said anomaly transformed into the said spectral space (Fƒ(x)=(F1ƒ(x), F2ƒ(x), . . . , FLƒ(x)), c′(x)=(c′1(x), c′2(x), . . . , c′N(x)) c(x)=(c1(x), c2(x), . . . , cK(x))).