# US 12,112,515 B2 · Technique for generating a labeled set of images > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,112,515 B2 - Document ID: US12112515B2 - Status: Granted - Kind: B2 - Application number: 17/356,720 - Filed: 2021-06-24 - Published: 2021-12-30 - Granted: 2024-10-08 - Earliest claimed: 2020-06-26 - Assignees: Airbus Defence and Space GmbH - Applicants: Airbus Defence and Space GmbH - Inventors: Matthieu Ferrato; Rémi Rivière; Henrique Candeias - Web page: https://patentgrep.com/patent/US12112515B2 ## CPC - G06V 10/44: Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components - G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting - G06F 18/23: Clustering techniques - G06N 20/00: Machine learning - G06V 10/60: relating to illumination properties, e.g. using a reflectance or lighting model - G06V 10/764: using classification, e.g. of video objects - G06V 10/774: Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting - G06V 10/82: using neural networks - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A method for generating a labeled set of images for use in machine learning based stray light characterization for space-related optical systems. The method includes (a) obtaining a set of images simulated for a space-related optical system, wherein the images of the set of images contain stray light simulated for the space-related optical system, (b) for each image of the set of images, identifying one or more clusters of light contained in the respective image and labeling the respective image by the one or more clusters of light, wherein the one or more clusters of light include at least one cluster of stray light, and (c) creating, based on the labeled images of the set of images, a plurality of new labeled images by applying transformations to the labeled images to generate an augmented set of labeled images. ## Claims ### Claim 1 A method for generating a labeled set of images for use in machine learning based stray light characterization for space-related optical systems, the method comprising: (a) obtaining a set of images simulated for a space-related optical system, wherein the images of the set of images contain stray light simulated for the space-related optical system; (b) for each image of the set of images, identifying one or more clusters of light contained in a respective image, wherein the one or more clusters of light are identified using an unsupervised machine learning algorithm, and labeling the respective image by the one or more clusters of light, wherein the respective image is labeled pixel-wise, wherein each pixel of the respective image is assigned at least one label indicating to which of the one or more clusters of light the pixel belongs, wherein the one or more clusters of light comprise a cluster of nominal light, which is the most bright cluster of light contained in the respective image, wherein the one or more clusters of light further comprise at least one cluster of stray light, wherein each of the at least one cluster of stray light identified in the respective image is representative of a different shape of stray light contained in the respective image; and (c) creating, based on the labeled images of the set of images, a plurality of new labeled images by applying mathematical image transformations to the labeled images to generate an augmented set of labeled images, wherein the transformations comprise at least one of rotation, translation, scaling, amplitude adjustment or any other type of image transformation which creates variance in the newly created labeled images, and wherein at least one of the transformations applied to the labeled images is performed cluster-wise, such that each transformation is performed on one of the one or more clusters of light independently from the transformations performed on others of the one or more clusters of light, so that, for each cluster, a different transformation may be applied. ### Claim 2 (depends on 1) The method of claim 1, further comprising: using the augmented set of labeled images to train a model for machine learning based stray light characterization for a space-related optical system. ### Claim 3 (depends on 2) The method of claim 2, further comprising: performing stray light characterization on an image acquired by a space-related optical system using the trained model. ### Claim 4 (depends on 1) The method of claim 1, wherein, for each cluster among the one or more clusters of light, a separate label is assigned to each pixel of the respective image, indicating that the pixel belongs to a respective cluster. ### Claim 5 (depends on 1) The method of claim 1, wherein each image of the set of images simulated for the space-related optical system is simulated using a different laser ray injection point assumed for the space-related optical system. ### Claim 6 (depends on 5) The method of claim 5, wherein the one or more clusters of light comprise a cluster of nominal light associated with the laser ray injection point assumed for the space-related optical system for the respective image. ### Claim 7 (depends on 5) The method of claim 5, wherein the one or more clusters of light are identified from a 4-dimensional data cube in which each image of the set of images is represented as a 2-dimensional image, wherein each pixel of a respective 2-dimensional image is associated with a grayscale value and an indication of whether or not a respective pixel belongs to the laser ray injection point assumed for the space-related optical system for the respective image. ### Claim 8 (depends on 1) The method of claim 1, wherein a plurality of transformations applied to the labeled images is performed cluster-wise and wherein the augmented set of labeled images includes combinatorial permutations of the cluster-wise transformations. ### Claim 9 A non-transitory computer readable medium storing a computer program product comprising program code portions which, when executed on a computer system or one or more computing devices, cause the computer system of the one or more computing devices, to: (a) obtain a set of images simulated for a space-related optical system, wherein the images of the set of images contain stray light simulated for the space-related optical system; (b) for each image of the set of images, identify one or more clusters of light contained in a respective image, wherein the one or more clusters of light are identified using an unsupervised machine learning algorithm, and label the respective image by the one or more clusters of light, wherein the respective image is labeled pixel-wise, wherein each pixel of the respective image is assigned at least one label indicating to which of the one or more clusters of light the pixel belongs, wherein the one or more clusters of light comprise a cluster of nominal light, which is the most bright cluster of light contained in the respective image, wherein the one or more clusters of light further comprise at least one cluster of stray light, wherein each of the at least one cluster of stray light identified in the respective image is representative of a different shape of stray light contained in the respective image; and (c) create, based on the labeled images of the set of images, a plurality of new labeled images by applying mathematical image transformations to the labeled images to generate an augmented set of labeled images, wherein the transformations comprise at least one of rotation, translation, scaling, amplitude adjustment or any other type of image transformation which creates variance in the newly created labeled images, and wherein at least one of the transformations applied to the labeled images is performed cluster-wise, such that each transformation is performed on one of the one or more clusters of light independently from the transformations performed on others of the one or more clusters of light, so that, for each cluster, a different transformation may be applied. ### Claim 10 A computing unit for generating a labeled set of images for use in machine learning based stray light characterization for space-related optical systems, the computing unit comprising at least one processor and at least one memory, the at least one memory containing instructions executable by the at least one processor such that the computing unit is operable to: (a) obtain a set of images simulated for a space-related optical system, wherein the images of the set of images contain stray light simulated for the space-related optical system; (b) for each image of the set of images, identify one or more clusters of light contained in a respective image, wherein the one or more clusters of light are identified using an unsupervised machine learning algorithm, and label the respective image by the one or more clusters of light, wherein the respective image is labeled pixel-wise, wherein each pixel of the respective image is assigned at least one label indicating to which of the one or more clusters of light the pixel belongs, wherein the one or more clusters of light comprise a cluster of nominal light, which is the most bright cluster of light contained in the respective image, wherein the one or more clusters of light further comprise at least one cluster of stray light, wherein each of the at least one cluster of stray light identified in the respective image is representative of a different shape of stray light contained in the respective image; and (c) create, based on the labeled images of the set of images, a plurality of new labeled images by applying mathematical image transformations to the labeled images to generate an augmented set of labeled images, wherein the transformations comprise at least one of rotation, translation, scaling, amplitude adjustment or any other type of image transformation which creates variance in the newly created labeled images, and wherein at least one of the transformations applied to the labeled images is performed cluster-wise, such that each transformation is performed on one of the one or more clusters of light independently from the transformations performed on others of the one or more clusters of light, so that, for each cluster, a different transformation may be applied.