In a method of processing an image, a first image including a plurality of objects and image information associated with the first image are obtained. Image processing information associated with an image operation to be performed on the first image is obtained based on an object among the plurality of objects included in the first image and a user command specified in at least one of voice information of a user and touch information from the user. A second image is generated by performing the image operation on the first image based on the image information and the image processing information.