Abstract: An apparatus is provided. The apparatus includes a communications interface to receive raw data from an external source. The raw data includes a representation of a first object and a second object. The apparatus further includes a memory storage unit to store the raw data. In addition, the apparatus includes a neural network engine to receive the raw data. The neural network engine is to generate a segmentation map and a boundary map. The apparatus also includes a post-processing engine to identify the first object and the second object based on the segmentation map and the boundary map.

Abstract: Systems and methods for use in training a convolutional neural network (CNN) for image and video transformations. The CNN is trained by adding noise to training data set images, transforming both the noisy image and the source image, and then determining the difference between the transformed noisy image and the transformed source image. The CNN is further trained by using an object classifier network and noting the node activation levels within that classifier network when transformed images (from the CNN) are classified. By iteratively adjusting the CNN to minimize a combined loss function that includes the differences between the node activation levels for the transformed references images and when transformed source are classified and the differences between the transformed noisy image and the transformed source image, the artistic style being transferred is maintained in the transformed images.

Abstract: Systems and methods relating to image processing and artificial intelligence. Given a small number of defect images, a multitude of other defect images can be generated to serve as training data sets for training artificially intelligent systems to recognize and detect similar defects. Given original images showing defects, a clean image of the background of the original images is created. The defect image is then isolated from each of the original images. The characteristics of each defect image are determined and characteristics of similar defects are also determined, either from other images or from subject matter experts. Based on these characteristics of similar defects, multiple other defect images are then generated. The generated defect images are combined with the clean image to result in defect images with a suitable background. Each of the resulting images can be used in training systems in recognizing and detecting defects.

Abstract: Systems and methods relating to image processing and artificial intelligence. Given a small number of defect images, a multitude of other defect images can be generated to serve as training data sets for training artificially intelligent systems to recognize and detect similar defects. Given original images showing defects, a clean image of the background of the original images is created. The defect image is then isolated from each of the original images. The characteristics of each defect image are determined and characteristics of similar defects are also determined, either from other images or from subject matter experts. Based on these characteristics of similar defects, multiple other defect images are then generated. The generated defect images are combined with the clean image to result in defect images with a suitable background. Each of the resulting images can be used in training systems in recognizing and detecting defects.

Abstract: Systems and methods for use in training a convolutional neural network (CNN) for image and video transformations. The CNN is trained by adding noise to training data set images, transforming both the noisy image and the source image, and then determining the difference between the transformed noisy image and the transformed source image. The CNN is further trained by using an object classifier network and noting the node activation levels within that classifier network when transformed images (from the CNN) are classified. By iteratively adjusting the CNN to minimize a combined loss function that includes the differences between the node activation levels for the transformed references images and when transformed source are classified and the differences between the transformed noisy image and the transformed source image, the artistic style being transferred is maintained in the transformed images.