The invention provides a pavement disease recognition method based on image analysis. The pavement disease recognition method based on image analysis comprises the following steps: step one, acquiring pavement images; step two, preprocessing the pavement images; step three, carrying out segmentation processing on the diseases in the preprocessed pavement images; step four, carrying out feature extraction and measurement on the diseases in the pavement images, specifically carrying out feature extraction and measurement on the diseases in the pavement images in the step three by using an outline area algorithm and an edge detection algorithm successively; and step five, outputting results, specifically accurately positioning the classified and measured diseases on the basis of the geographical location information in the step one through a controller and then outputting the results. By the technical scheme of the invention, labor can be relieved, interference of artificial subjective factors is eliminated, road conditions can be evaluated quickly and accurately, and the shortcomings that cracks are classified by manual judgment, working efficiency is low, error rate is relatively high and the like are overcome.