The Boeing Company
Systems and methods for model-based image analysis

Abstract:

A system for categorizing images is provided. The system is programmed to store a first training set of images. Each image of the first training set of images is associated with an image category of a plurality of image categories. The system is further programmed to analyze each image of the first training set of images to determine one or more features associated with each of the plurality of image categories and receive a second training set of images. The second training set of images includes one or more errors. The system is also programmed to analyze each image of the second training set of images to determine one or more features associated with an error category and generate a model to identify each of the image categories based on the analysis such that the model includes the error category in the plurality of image categories.