Abstract: In some examples, it is disclosed a method for generating an image retrieval system configured to rank a plurality of images of cargo from a dataset of images, in response to a query corresponding to an image of cargo of interest generated using penetrating radiation. The method may involve obtaining a plurality of annotated training images including cargo, each of the training images being associated with an annotation indicating a type of the cargo in the training image, and training the image retrieval system by applying a deep learning algorithm to the obtained annotated training images. The training may involve applying, to the annotated training images, a feature extraction convolutional neural network, and applying an aggregated generalized mean pooling layer associated with image spatial information.

Abstract: A method is disclosed of generating a classifier configured to detect an object corresponding to a type of interest in an inspection image generated using penetrating radiation, the method including generating training data associated with a plurality of training images including objects corresponding to the type of interest, using a generative adversarial network including a generator and a discriminator. The method further includes training the classifier by applying a machine learning algorithm either using only the generated training data or a combination of real and generated data, wherein generating the training data includes training the generator and the discriminator using initial training data associated with a plurality of observed images generated using penetrating radiation, one or more observed images including an object corresponding to the type of interest.

Abstract: In one embodiment there is provided a method for inspecting a container, comprising: classifying an inspection image of the container in a matching class of one or more predetermined classes of containers of interest, each predetermined class comprising reference images associated with a type of containers of interest, wherein the inspection image is generated using transmission of inspection radiation through the container; comparing a shape model of the inspection image to corresponding shape models associated with reference images within the matching class; associating the inspection image with a matching reference image, based on the comparison; registering one or more zones of the inspection image with corresponding one or more zones of the matching reference image; and mapping differences between the inspection image and the matching reference image, based on the registration.

Abstract: In one embodiment there is provided a method for inspecting a container, comprising: classifying an inspection image of the container in a matching class of one or more predetermined classes of containers of interest, each predetermined class comprising reference images associated with a type of containers of interest, wherein the inspection image is generated using transmission of inspection radiation through the container; comparing a shape model of the inspection image to corresponding shape models associated with reference images within the matching class; associating the inspection image with a matching reference image, based on the comparison; registering one or more zones of the inspection image with corresponding one or more zones of the matching reference image; and mapping differences between the inspection image and the matching reference image, based on the registration.

Abstract: In one aspect, there is provided a method of denoising one or more inspection images comprising a plurality of pixels, comprising: receiving an inspection image generated by an inspection system configured to inspect one or more containers, the inspection image being corrupted by a Poisson-Gaussian noise and a variance of the noise being non-constant in the plurality of pixels, and denoising the received inspection image by applying, to the inspection image, a variance-stabilizing transformation for transforming the variance of the noise into a constant variance in the plurality of pixels, wherein the variance-stabilizing transformation is based on a descriptor associated with the angular divergence of the inspection radiation and the Poisson-Gaussian noise.

Abstract: In one embodiment, the disclosure relates to a method for determining a degree of homogeneity in one or more inspection images of cargo in one or more containers, comprising: determining whether a zone of interest in one or more processed inspection images comprises one or more patterns, wherein the one or more processed inspection images are processed from one or more inspection images generated by an inspection system configured to inspect the one or more containers; and in the event that one or more patterns is determined and that a variation in the determined one or more patterns is identified, classifying the one or more inspection images as having a degree of homogeneity below a predetermined homogeneity threshold.

Abstract: In one embodiment, the disclosure relates to a method for inspecting a load (101) in a container (100), comprising: classifying (S2) one or more patches (11) of a digitized inspection image (10), the digitized inspection image (10) being generated by an inspection system (1) configured to inspect the container (100) by transmission of inspection radiation (3) from an inspection radiation source (31) to an inspection radiation detector (32) through the container (100), wherein the classifying (S2) comprises: extracting (S21) one or more texture descriptors (V, P) of a patch (11), and classifying (S22) the patch (11), by comparing the one or more extracted texture descriptors (V, P) of the patch (11) to respective one or more reference texture descriptors (Vr, Wr, Pr) corresponding to respective one or more classes (202) of reference items (201), the one or more reference texture descriptors (Vr, Wr, Pr) of each class of reference items (201) being extracted from one or more reference images (20) of the one or

Abstract: In one aspect, there is provided a method of denoising one or more inspection images comprising a plurality of pixels, comprising: receiving an inspection image generated by an inspection system configured to inspect one or more containers, the inspection image being corrupted by a Poisson-Gaussian noise and a variance of the noise being non-constant in the plurality of pixels, and denoising the received inspection image by applying, to the inspection image, a variance-stabilizing transformation for transforming the variance of the noise into a constant variance in the plurality of pixels, wherein the variance-stabilizing transformation is based on a descriptor associated with the angular divergence of the inspection radiation and the Poisson-Gaussian noise.

Abstract: In one embodiment, the disclosure relates to a method for determining a degree of homogeneity in one or more inspection images of cargo in one or more containers, comprising: determining whether a zone of interest in one or more processed inspection images comprises one or more patterns, wherein the one or more processed inspection images are processed from one or more inspection images generated by an inspection system configured to inspect the one or more containers; and in the event that one or more patterns is determined and that a variation in the determined one or more patterns is identified, classifying the one or more inspection images as having a degree of homogeneity below a predetermined homogeneity threshold.

Abstract: In one embodiment, the disclosure relates to a method for inspecting a load (101) in a container (100), comprising: classifying (S2) one or more patches (11) of a digitized inspection image (10), the digitized inspection image (10) being generated by an inspection system (1) configured to inspect the container (100) by transmission of inspection radiation (3) from an inspection radiation source (31) to an inspection radiation detector (32) through the container (100), wherein the classifying (S2) comprises: extracting (S21) one or more texture descriptors (V, P) of a patch (11), and classifying (S22) the patch (11), by comparing the one or more extracted texture descriptors (V, P) of the patch (11) to respective one or more reference texture descriptors (Vr, Wr, Pr) corresponding to respective one or more classes (202) of reference items (201), the one or more reference texture descriptors (Vr, Wr, Pr) of each class of reference items (201) being extracted from one or more reference images (20) of the one or