Automated vehicle repair estimation by aggregate ensembling of multiple artificial intelligence functions is provided. A method comprises receiving a plurality of vehicle repair recommendation sets for a damaged vehicle, wherein each of the vehicle repair recommendation sets identifies at least one recommended vehicle repair operation of a plurality of the vehicle repair operations for the damaged vehicle; aggregating a plurality of the recommended vehicle repair operations; generating a composite vehicle repair recommendation set that identifies the aggregated recommended vehicle repair operations; and providing the composite vehicle repair recommendation set to one or more vehicle repair insurance claims management systems.

In various embodiments, a training application generates a perceptual video model. The training application computes a first feature value for a first feature included in a feature vector based on a first color component associated with a first reconstructed training video. The training application also computes a second feature value for a second feature included in the feature vector based on a first brightness component associated with the first reconstructed training video. Subsequently, the training application performs one or more machine learning operations based on the first feature value, the second feature value, and a first subjective quality score for the first reconstructed training video to generate a trained perceptual quality model. The trained perceptual quality model maps a feature value vector for the feature vector to a perceptual quality score.

The disclosure relates to systems, methods and computer readable media for providing network-based identification, generation and management of a unique damage (finger) print of vehicle(s) by geodetic mapping of stable key points onto a ground truth 3D model of the vehicle, and vehicle parts—identified from the raw images using supervised and unsupervised machine learning. Specifically, the disclosure relates to System and methods for the generation of unique damage print on a vehicle that is obtained from captured images of the damaged vehicle, photogrammetrically localized to a specific vehicle part, and the computer programs enabling the method, the damage print configured to be used, for example, in fraud detection in insurance claims.

A video processing apparatus configured to process a stream of video surveillance data, wherein the video surveillance data includes metadata associated with video data, the metadata describing at least one object in the video data. The apparatus comprises means for applying an image assessment algorithm to generate a reliability score for the metadata, and associating the reliability score with the metadata. The image assessment algorithm generates the reliability score based on an assessment of the image quality of the video data to which the metadata relates to indicate a likelihood that the metadata accurately describes the object. An image enhancement module applies image enhancement to video data if the reliability score of metadata associated with the video data indicates a low likelihood that the metadata accurately describes the object.

An image generation method obtains an original image. A character area, a background area, and a position of each flawless character in the original image are determined. The character area is segmented to obtain a first image of each flawless character. A background is removed from the first image to obtain a second image. First image processing is performed on the second image to obtain a third image. Second image processing is performed on the second image to obtain fourth images. Third image processing is performed on the fourth images respectively to obtain fifth images. A similarity between each fifth image and the third image is calculated. When the similarity is greater than a defect threshold, a background image is segmented. Brightness of the background image is adjusted. The target fourth image and adjusted background image are synthesized. The method can generate images with defective characters quickly.

A method for detecting fake images includes: obtaining an image for authentication, and hand-crafting a multi-attribute classifier to determine whether the image is authentic. Hand-crafting the multi-attribute classifier includes fusing at least an image classifier, an image spectrum classifier, a co-occurrence matrix classifier, and a one-dimensional (1D) power spectrum density (PSD) classifier. The multi-attribute classifier is trained by pre-processing training images to generate an attribute-specific training dataset to train each of the image classifier, the image spectrum classifier, the co-occurrence matrix classifier, and the 1D PSD classifier.

In some embodiments, the present specification describes methods for displaying a three-dimensional image of an isolated threat object or region of interest with a single touch or click and providing spatial and contextual information relative to the object, while also executing a view dependent virtual cut-away or rendering occluding portions of the reconstructed image data as transparent. In some embodiments, the method includes allowing operators to associate audio comments with a scan image of an object. In some embodiments, the method also includes highlighting a plurality of voxels, which are indicative of at least one potential threat item, in a mask having a plurality of variable color intensities, where the intensities may be varied based on the potential threat items.

Disclosed herein are methods of providing an image storage service, computer-readable recording mediums, and/or computing devices. The method of providing the image storage service includes selecting image data in a first format, determining an initial compression parameter for converting the selected image data in the first format into a second format, obtaining primary image data in the second format by transcoding the selected image data in the first format based on the initial compression parameter, searching for a desired compression parameter based on whether image quality of the primary image data satisfies a criterion, obtaining final image data in the second format by transcoding the selected image data in the first format based on the desired compression parameter, and storing final image data in the second format in the memory.

An object of the present invention is to provide a dispensing audit support apparatus and a dispensing audit support method with a high collation accuracy robustness. According to a dispensing audit support apparatus according to one aspect of the present invention, since a position, shape and size of a region of interest are set according to a position of a collation-target medicine in a captured image, and a position, shape and size of a master image are set according to the set region of interest, it is possible to avoid or reduce distortion of the medicine shape, blur, inclusion of an end part into the image, and the like due to the position and orientation of the collation-target medicine. Therefore, influence on collation accuracy is small, and it is possible to enhance the robustness of the collation accuracy.

“Feature points” in “point clouds” that are visible to multiple respective cameras (i.e., aspects of objects imaged by the cameras) are reported via wired and/or wireless communication paths to a compositing processor which can determine whether a particular feature point “moved” a certain amount relative to another image. In this way, the compositing processor can determine, e.g., using triangulation and recognition of common features, how much movement occurred and where any particular camera was positioned when a latter image from that camera is captured. Thus, “overlap” of feature points in multiple images is used so that the system can close the loop to generate a SLAM map. The compositing processor, which may be implemented by a server or other device, generates the SLAM map by merging feature point data from multiple imaging devices.