Abstract: The present disclosure discloses a method and system for identifying a part of a vehicle and a vehicle inspection system. The method includes: acquiring a vehicle body image sequence of a vehicle to be identified; reconstructing the vehicle body by using a first vehicle body reconstruction model generated through a deep learning algorithm and on the basis of the vehicle body image sequence, so as to acquire a vehicle body reconstruction image of the vehicle to be identified; and identifying a boundary identifier of the vehicle to be identified on the basis of the vehicle body reconstruction image of the vehicle to be identified.

Abstract: This invention provides a scan method, scan system and radiation scan controller, and relates to the field of radiation. Wherein, the scan method of this invention comprises: obtaining detection data of an object to be inspected under radiation scanning using a detector; adjusting an accelerator output beam dose rate and/or an output electron beam energy level of a radiation emission device according to the detection data. With this method, working conditions of the accelerator of the radiation emission device may be adjusted according to the detection data detected by the detector, so that for a region having a larger mass thickness, a higher output beam dose rate or a higher electron beam output energy level is adopted to guarantee satisfied imaging technical indexes, for a region having a smaller mass thickness, a lower output beam dose rate or a lower electron beam output energy level is adopted to reduce the environmental dose level while guaranteeing satisfied imaging technical indexes.

Abstract: The present disclosure provides a spiral Computed Tomography (CT) device and a three-dimensional image reconstruction method.

Abstract: There is provided a semiconductor detector. According to an embodiment, the semiconductor detector may include a semiconductor detection material including a first side and a second side opposite to each other. One of the first side and the second side is a ray incident side that receives incident rays. The detector may further include a plurality of pixel cathodes disposed on the first side and a plurality of pixel anodes disposed on the second side. The pixel anodes and the pixel cathodes correspond to each other one by one. The detector may further include a barrier electrode disposed on a periphery of respective one of the pixel cathodes or pixel anodes on the ray incident side. According to the embodiment of the present disclosure, it is possible to effectively suppress charge sharing between the pixels and thus to improve an imaging resolution of the detector.

Abstract: Disclosed is a method and device for estimating weight of an object to be inspected in an inspection system. An effective atomic number and a high-energy gray value of the dual-energy corresponding to each pixel of the object to be inspected are obtained by a dual-energy radiation scanning. A mass-thickness value for a corresponding pixel is obtained from a pre-created mass-thickness attenuation curve by utilizing the effective atomic numbers and the high-energy gray value of the dual-energy for respective pixels. Weight information for at least a part of the object to be inspected is calculated by multiplying the mass-thickness value by the area of the pixel. Such a method may accurately calculate the weight of the object to be inspected and save the cost for a conventional weighing hardware.

Abstract: Disclosed is method and apparatus for creating a statistical average model of an enamel-dentine junction. The method includes steps of acquiring CT image data of a tooth; segmenting the CT image data to obtain a surface of an enamel-dentine junction; segmenting the obtained surface using a curvature-based clustering algorithm to remove a bottom of the enamel-dentine junction; spherical-parameterizing, by means of spherical harmonic analysis, the surface of the enamel-dentine junction after removal of the bottom; and aligning different samples of the tooth to obtain a statistical average model.

Abstract: Disclosed is a dual-energy ray imaging method and system. The method comprises: calculating the mass thicknesses of the materials in the overlapped area of two materials by using a calibrated surface fitting method, and then decomposing a pair of original high-energy and low-energy data for this pixel into two high-low-energy data sets corresponding to the two materials, and finally calculating and acquiring the composition result of different materials for each pixel. The disclosure is especially advantageous in that the problem of error recognition of materials due to the two overlapped materials can be eliminated and the stratified imaging of multiple materials can be achieved, thereby improving the accuracy of the substance recognition and reducing the rate of false positive and false negative which is very important to the applications in the field of security check and anti-smuggling.

Abstract: A method and an apparatus for estimating an image fuzziness are provided. The method may comprise: acquiring an image; obtaining a multi-scale representation of the image by performing a multi-scale transform on the image; calculating gradients of the image and a normalized histogram of the gradients at each scale based on the multi-scale representation; calculating error vectors between the normalized histogram of gradients at each scale and a normalized original histogram of gradients of the image; performing a weighted summing on the error vectors by using respective weights to obtain a summed result, wherein the weights are determined based on a reciprocal of the sums of squares of the gradients of the image at each scale; estimating the ambiguity of the image based on the summed result.

Abstract: This invention provides a scan method, scan system and radiation scan controller, and relates to the field of radiation. The scanning method includes obtaining detection data of an object to be inspected under radiation scanning using a detector, adjusting an accelerator output beam dose rate and/or an output electron beam energy level of a radiation emission device according to the detection data. With this method, working conditions of the accelerator of the radiation emission device may be adjusted according to the detection data detected by the detector, so that for a region having a larger mass thickness, a higher output beam dose rate or a higher electron beam output energy level is adopted to guarantee satisfied imaging technical indexes, for a region having a smaller mass thickness, a lower output beam dose rate or a lower electron beam output energy level is adopted to reduce the environmental dose level while guaranteeing satisfied imaging technical indexes.

Abstract: An inspection method and system for inspecting whether there is any liquor in goods is provided. The method includes: acquiring a radiation image of goods being inspected; processing on the radiation image to obtain an ROI; inspecting on the ROI using a liquor goods inspection model to determine if the ROI of the radiation image contains liquor goods. The above solution performs liquor inspection on scanned images of goods, especially containers, so as to intelligently assist the image inspectors.

Abstract: A semiconductor may include a semiconductor detection material including a first side and a second side opposite to each other, a cathode disposed on the first side, and an anode disposed on the second side. The anode includes an array of pixel anodes defining detection pixels of the semiconductor detector, and intermediate anodes disposed between adjacent ones of the pixel anodes. According to an embodiment of the present disclosure, it is possible to achieve signal correction to improve the energy resolution and the signal-to-noise ratio of the detector.

Abstract: A vehicle inspection method and system are disclosed. In one aspect, the method includes acquiring a transmission image of an inspected vehicle. The method further includes acquiring a transmission image template of a vehicle model corresponding to the model of the inspected vehicle from a database. The method further includes performing registration on the transmission image of the inspected vehicle and the transmission image template. The method further includes determining a difference between a transmission image after the registration and a transmission image template after the registration, to obtain a difference area of the transmission image of the vehicle relative to the transmission image template. The method further includes processing the difference area to determine whether the vehicle carries a suspicious object or not.

Abstract: The present disclosure provides a method and a system for inspecting goods. The method includes the steps of: obtaining a transmission image and a HSCODE of inspected goods; processing the transmission image to obtain a region of interest; retrieving from a model library a model created based on the HSCODE, in accordance with the HSCODE of the inspected goods; and determining whether there are any goods not registered in a customs declaration that are contained in the region of interest based on the model. With the above solution, it is possible to inspect goods in a container efficiently, so as to find out whether there are goods not indicated in the customs declaration that are concealed in the container.

Abstract: An inspection method and system for inspecting whether there is any liquor in goods is provided. The method includes: acquiring a radiation image of goods being inspected; processing on the radiation image to obtain an ROI; inspecting on the ROI using a liquor goods inspection model to determine if the ROI of the radiation image contains liquor goods. The above solution performs liquor inspection on scanned images of goods, especially containers, so as to intelligently assist the image inspectors.

Abstract: A method of evaluating an image quality for an imaging system and the imaging system are provided. The method in some examples includes: acquiring an image to be evaluated which is generated by the imaging system; extracting a number of sub-images from the image; obtaining a coefficient vector indicating a degree of sparsity by applying a sparse decomposition on the sub-images based on a pre-set redundant sparse representation dictionary; and performing a linear transformation on the coefficient vector so as to obtain an evaluation value for the image quality. The sparse dictionary is learned by only using a few high quality perspective images, and then the image quality is evaluated based on the sparse degree of the image obtained by using the sparse dictionary. A convenient and rapid no-reference image quality evaluation is achieved.

Abstract: A method and device for reconstructing a CT image and a storage medium are disclosed. CT scanning is performed on an object to be inspected to obtain projection data. The projection data is processed using a first convolutional neural network to obtain processed projection data. The first convolutional neural network comprises a plurality of convolutional layers. A back-projection operation is performed on the processed projection data to obtain a reconstructed image.

Abstract: A method and device for reconstructing a CT image and a storage medium are disclosed. CT scanning is performed on an object to be inspected to obtain projection data on a first scale. Projection data on a plurality of other scales is generated from the projection data on the first scale. Projection data on each scale is processed on the corresponding scale by using a first convolutional neural network to obtain processed projection data, and a back-projection operation is performed on the processed projection data to obtain a CT image on the corresponding scale. CT images on the plurality of scales are fused to obtain a reconstructed image of the object to be inspected.

Abstract: The present disclosure relates to a method and device for estimating a point spread function. In one implementation, a method includes capturing, by a scanning device, an image by scanning a plurality of rectangle blocks which are same sized and closely arranged, wherein the plurality of rectangle blocks are made of different materials and/or have different mass thicknesses, and an incident direction of rays is perpendicular to a scanning direction and a surface of the plurality of rectangle blocks arranged closely during scanning; obtaining line spread functions for two directions along a length side and a width side of each of the rectangle blocks based on the scanned image, and obtaining standard deviation parameters of the line spread functions; and combining the standard deviation parameters for the two directions to obtain a two dimensional Point Spread Function (PSF) parameter so as to estimate the point spread function.

Abstract: The present disclosure provides a method and a system for inspecting goods. The method comprises steps of: obtaining a transmission image of inspected goods; processing the transmission image to obtain a suspicious region; extracting local texture features of the suspicious region and classifying the local texture features of the suspicious region based on a pre-created model to obtain a classification result; extracting a contour line shape feature of the suspicious region and comparing the contour line shape feature with a pre-created standard template to obtain a comparison result; and determining that the suspicious region contains a high atomic number matter based on the classification result and the comparison result.

Abstract: The present disclosure provides a low-angle self-swinging type computed tomography (CT) apparatus, which is provided with an X-ray accelerator and a plurality of rows of detectors and is configured to include a slip ring, such that the slip ring with the accelerator and the detectors thereon is capable of performing a single-pendulum reciprocating movement while an objected to be inspected passes through the slip ring, a three dimension CT image of the object is displayed, thereby achieving accurate inspection for large-scale objects, such as van containers.