Optic disc segmentation unsupervised evaluation method and device based on unification of form and learning

The invention belongs to the technical field of optic disc segmentation, and provides an unsupervised evaluation method and device for optic disc segmentation based on unification of forms and learning. The method comprises the following steps: comparing a topological form parameter vector of a to-be-evaluated optic disk image with a feature representation of a vector matrix formed by topological form parameter vectors of a reference image set, and obtaining a first evaluation result according to similarity; inputting the feature vector of the optic disk image to be evaluated into a trained single-classification learning model based on an auto-encoder, and obtaining a second evaluation result according to the similarity between the input and the output of the single-classification learning model; and synthesizing the first evaluation result and the second evaluation result to obtain a comprehensive evaluation result of the optic disc image to be evaluated. According to the embodiment of the invention, an obje