The embodiment of the invention discloses a method and a device for identifying similar images, a server and a storage medium. The method comprises the steps of calculating and obtaining a low-dimensional feature vector hash code of each image by utilizing a image average hash algorithm; uniformly dividing the low-dimensional feature vector hash code of each image into at least two hash code blocks according to a preset rule, wherein each hash code block corresponds to one position index; dividing images with the same position index and the same hash code block into the same cluster, so as toobtain a plurality of image clusters; in each image cluster, recognizing similar images according to the distances between all images except the same hash code block corresponding to the same positionindex. According to the embodiment of the invention, the calculation complexity of similar image recognition is reduced. The calculation amount is reduced, and the high-efficiency calculation of theimage similarity is realized.