A digital magazine server presents content retrieved from various sources to a user. The content may include various images, with images selected by the digital magazine server for presentation to a user along with additional content. Text associated with an image may also be retrieved and presented to the user along with the image. To improve presentation of images with text, the digital magazine server identifies features in an image and identifies regions of the image where text is capable of being presented without obscuring or being obscured by features of the image. The image is modified to present text associated with the image in one or more of the identified images, allowing the text to be presented without detracting from features of the image.