Patent attributes
A method which includes obtaining a plurality of images of tires that differ from one another in either one of or both of a tire type and a tire condition, the obtained images being regarded as teacher images; converting the teacher images into a size of a predetermined number of pixels; learning by a convolutional neural network using data of the plurality of converted teacher images as learning images, and setting parameters of the convolutional neural network; obtaining a tire image of a recognition-target tire and converting the obtained tire image into a size identical to that of the teacher images; and inputting the converted tire image of the recognition-target tire to the convolutional neural network and determining either one of or both of the type and the condition of the recognition-target tire.
