Embodiments of the invention disclose an image processing method and apparatus. A specific embodiment of the method comprises the steps of obtaining a target image including a polygonal image; inputting the target image to a pre-trained convolutional neural network to obtain an eigenvector of the target image, wherein the convolutional neural network is used for representing a corresponding relationship between the image and the eigenvector, and the eigenvector is a vector comprising a type feature, a position feature and a key point feature of the polygonal image; and based on the type feature, the position feature and the key point feature, identifying an image region of the polygonal image. The accuracy of polygonal image identification is improved.