Uncertainty region based image enhancement

A computer usable program product comprising one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices, the stored program instructions comprising:

• program instructions to generate, from a first image using a model, a first uncertainty map, wherein an uncertainty level of a location in the first uncertainty map corresponds to a detection of a known structure in a portion of the first image;
• program instructions to generate, corresponding to the first uncertainty map, a first weighted image, the generating comprising assigning a first weight to a pixel of the first image, the first weight corresponding to the uncertainty level of a location in the first uncertainty map corresponding to the pixel;
• program instructions to generate, from a second image using the model, a second uncertainty map, wherein an uncertainty level of a location in the second uncertainty map corresponds to a detection of a known structure in a portion of the second image;
• program instructions to generate, corresponding to the second uncertainty map, a second weighted image, the generating comprising assigning a second weight to a pixel of the second image, the second weight corresponding to the uncertainty level of a location in the second uncertainty map corresponding to the pixel;
• and
• program instructions to combine the first image and the second image to form a composite image, the first image participating in the composite image according to the first weighted image and the second image participating in the composite image according to the second weighted image.

A computer system comprising one or more processors, one or more computer-readable memories, and one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, the stored program instructions comprising:

• program instructions to generate, from a first image using a model, a first uncertainty map, wherein an uncertainty level of a location in the first uncertainty map corresponds to a detection of a known structure in a portion of the first image;
• program instructions to generate, corresponding to the first uncertainty map, a first weighted image, the generating comprising assigning a first weight to a pixel of the first image, the first weight corresponding to the uncertainty level of a location in the first uncertainty map corresponding to the pixel;
• program instructions to generate, from a second image using the model, a second uncertainty map, wherein an uncertainty level of a location in the second uncertainty map corresponds to a detection of a known structure in a portion of the second image;
• program instructions to generate, corresponding to the second uncertainty map, a second weighted image, the generating comprising assigning a second weight to a pixel of the second image, the second weight corresponding to the uncertainty level of a location in the second uncertainty map corresponding to the pixel;
• and
• program instructions to combine the first image and the second image to form a composite image, the first image participating in the composite image according to the first weighted image and the second image participating in the composite image according to the second weighted image.