The SYN-OCT dataset contains a total of 200,000 synthetic cross-sectional circumpapillary optical coherence tomography (OCT) images, comprising of 100,000 images from a generative image model for ...

Underwater computer vision faces significant challenges from light scattering, absorption, and poor illumination, which severely impact underwater vision tasks. To address these issues, ViT-Clarity, ...

Penn Engineering's Yue Yang co-developed CoSyn, a tool that trains open source AI models to read complex, text-rich images, with the goal of spurring scientific discoveries. In the race to develop AI ...

Data is pretty much everything when it comes to training AI systems, but accessing enough data to produce quality products that live up to their promise is a major challenge, even for companies with ...

In the race to develop AI that understands complex images like financial forecasts, medical diagrams and nutrition labels—essential for AI to operate independently in everyday settings—closed-source ...

Researchers have developed a method to use an image generation AI model to create realistic images of single cells, which are then used as 'synthetic data' to train an AI model to better carry out ...

An example of a cell image before and after segmentation, a process which allows researchers to distinguish single cells from each other and their background. Observing individual cells through ...