Abstract: Methods, systems, and techniques for utilizing image processing systems to measure damage to vehicles include utilizing an image processing system to generate a heat map of an image of a damaged vehicle, where the heat map is indicative of a damaged area of the vehicle, and determining at least one measurement of the damaged area based on the heat map and a depth of field indicator corresponding to the image. In some embodiments, the image processing system also determines one or more types of damage of the damaged area, and/or also generates a segmentation map of the depicted vehicle and utilizes the segmentation map in conjunction with the heat map to measure damaged areas and locations thereof on the vehicle depicted within the image. In some embodiments, the techniques include determining the depth of field indicator of the image or portions thereof.

Abstract: A method and system is described which attempts to address the technical problems involved in analyzing images using advanced computer systems and making decisions about the future of a damaged automobile based on the images.

Abstract: A method and system is described which attempts to address the technical problems involved in analyzing images using advanced computer systems and making decisions about the future of a damaged automobile based on the images.

Abstract: A method and system is described which attempts to address the technical problems involved in analyzing images using advanced computer systems and making decisions about the future of a damaged automobile based on the images.

Abstract: Methods, systems, and techniques for utilizing image processing systems to measure damage to vehicles include utilizing an image processing system to generate a heat map of an image of a damaged vehicle, where the heat map is indicative of a damaged area of the vehicle, and determining at least one measurement of the damaged area based on the heat map and a depth of field indicator corresponding to the image. In some embodiments, the image processing system also determines one or more types of damage of the damaged area, and/or also generates a segmentation map of the depicted vehicle and utilizes the segmentation map in conjunction with the heat map to measure damaged areas and locations thereof on the vehicle depicted within the image. In some embodiments, the techniques include determining the depth of field indicator of the image or portions thereof.

Abstract: An image processing system analyzes each of a set of vehicle images to determine one or more types of vehicle damage present in the selected images. The image processing system uses a characterization engine in the form of a neural network based image model to process each of the pixels of each of the selected images to determine, for the particular pixels of the image (or of the object depicted within the image) at which damage exists, the type of damage that is present. The damage types may include a tear, a scratch, a dent, a missing piece, a misalignment or other types of damage.

Abstract: A tool used in an image processing system assists a user to train one or more statistical image models or classification engines (e.g., the CNN models) that are used to detect damaged areas on a vehicle, to detect damage types and/or to detect segments of the depiction of the vehicle. The tool enables a user to select and annotate various different training images to be used to train the models, wherein each of the training images depicts damage of one or more damage types to various different vehicles or automobiles (including automobiles of different years/makes/models).

Abstract: An image processing system analyzes each of a set of vehicle images to determine one or more vehicle segments present in the images. The image processing system uses a characterization engine in the form of a neural network based image model to process each of the pixels of each of the images to determine the particular pixels of the image (or of the object depicted within the image) within or associated with a particular vehicle segment, such as a vehicle door, bumper, right or left panel, rear panel, windshield, etc. The characterization engine or image model may be developed or trained using a training engine that analyzes a plurality of images of different vehicles damaged in various different manners which have been annotated, on a pixel by pixel basis, to indicate the segments of the vehicle to which the various pixels belong or depict, and which have also been annotated, on an image basis, to indicate the view and/or zoom level of the image.

Abstract: A method and system is described which attempts to address the technical problems involved in analyzing images using advanced computer systems and making decisions about the future of a damaged automobile based on the images.

Abstract: A method and system is described which attempts to address the technical problems involved in analyzing images using advanced computer systems and making decisions about the future of a damaged automobile based on the images.

Abstract: A method and system is described which attempts to address the technical problems involved in analyzing images using advanced computer systems and making decisions about the future of a damaged automobile based on the images.

Abstract: Techniques for optimizing vehicle license plate recognition in images and their decoding include training a set of convolutional neural networks (CNNs) by using images in which license plates are identified or labeled as a whole, rather than by license plate parts or key points, and rather than by the individual, segmented characters represented thereon. The trained CNNs may operate on target images of environments to localize images of license plates included therein and determine the issuing jurisdiction and/or ordered set of characters represented on detected license plates without utilizing character segmentation and/or per-character recognition techniques. As such, license plates depicted within target images are able to be detected and decoded with greater tolerances for lighting conditions, deformations or damages, occlusions, differing image resolutions, differing angles of capture, variations of other objects depicted within the images (such as dense or changing signage), etc.