image generation

A UNIFIED SYSTEM FOR AI-GENERATED IMAGE AUTHENTICATION AND MANAGEMENT

This article presents the development of an image generation system that employs digital watermarking and metadata embedding technologies to determine whether an image has been generated by an AI model. The system acts as an intermediary service between providers (web services with generation models) and end users, ensuring seamless integration of these technologies. With the growing volume of AI-generated content, distinguishing such images from authentic ones has become increasingly challenging.

USING NOISES FOR STABLE IMAGE GENERATION IN DIFFUSION MODELS

The foundation of this work lies in the study of the image generation process using diffusion models. The potential for increasing generation stability is demonstrated through an approach that involves using constant noise as a regularizer, with the addition of a mask of random noise constructed around each pixel of the input image within a random radius. The models were implemented using Python and TensorFlow, NumPy, and Keras libraries.

SYNTHESIS OF BIOMEDICAL IMAGES BASED ON GENERATIVE ADVERSARIAL NETWORKS

Mo­dern da­ta­ba­ses of bi­ome­di­cal ima­ges ha­ve be­en in­ves­ti­ga­ted. Bi­ome­di­cal ima­ging has be­en shown to be ex­pen­si­ve and ti­me con­su­ming. A da­ta­ba­se of ima­ges of pre­can­ce­ro­us and can­ce­ro­us bre­asts "BPCI2100" was de­ve­lo­ped. The da­ta­ba­se con­sists of 2,100 ima­ge fi­les and a MySQL da­ta­ba­se of me­di­cal re­se­arch in­for­ma­ti­on (pa­ti­ent in­for­ma­ti­on and ima­ge fe­atu­res). Ge­ne­ra­ti­ve ad­ver­sa­ri­al net­works (GAN) ha­ve be­en fo­und to be an ef­fec­ti­ve me­ans of ima­ge ge­ne­ra­ti­on.