Ccc Information Services Inc.

Ccc Intelligent Solutions Inc.

Neda Hantehzadeh

Mohan Liu

Christoph Plenio

Ruxiao Bao

Ranjini Vaidyanathan

Steven Penny

Masatoshi Kato

Srinivasan Krishnaswamy

Mina Haratiannezhadi

Sagar Bachwani

Bhadresh Dhanani

Nazanin Makkinejad

Bahar Radfar

Anneke Hidayat

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). The tool displays each of a set of selected training images and enables a user to indicate, on the displayed selected training image, using an electronic pen, a touch screen or any other type of selector device, one or more sets of pixels within the displayed image that are associated with or that depict damage to the vehicle, one or more sets of pixels within the displayed image that are associated with or that depict a particular type of vehicle damage and/or one or more sets of pixels within the displayed image that are associated with or included in a particular segment of the depiction of the vehicle within the image. The marked or tagged images are then used to train an image model to detect vehicle damage, types of vehicle damage and/or vehicle segments in new vehicle images.

Tool for labelling training images for a vehicle characteristic detection model

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. 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 type of vehicle damage that is present at each of the image pixels at which damage exists, and which have also been annotated, on an image basis, to indicate the view and/or zoom level of the image.

Image processing systems for detecting types of damage to a vehicle

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.

Methods and systems of utilizing image processing systems to measure objects

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.

Image processing system using recurrent neural networks

Image processing system

Image processing system using convolutional neural networks

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.

Optimized vehicle license plate recognition

Growing community of inventors

Chicago, IL, United States of America

Neda Hantehzadeh