PARTICIPATING GENERATIVE MACHINE LEARNING MODELS FOR FUNCTIONAL TESTING

摘要

A system includes a display device, a memory configured to store a visual analysis application and image data including a plurality of images including detectable objects; and a processor operatively connected to the memory and the display device. The processor is configured to run the visual analysis application to learn generative factors of objects detected in the plurality of images, to visualize the generative factors in a user interface provided to the display device, to grouped combinations of the generative factors and receive values to be applied to the generative factors to control object features to create generated objects by applying the values of the generative factors to the objects detected in the plurality of images to relate the generated objects to the original images combine to produce generated images and to apply a discriminator to the generated images to reject unrealistic images.