Abstract: The presently-disclosed technology enables real-time inspection of a multitude of subcomponents of a component in parallel. For example, the component may be a semiconductor package, and the subcomponents may include through-silicon vias. One embodiment relates to a method for inspecting multiple subcomponents of a component for defects, the method comprising, for each subcomponent undergoing defect detection: extracting a subcomponent image from image data of the component; computing a transformed feature vector from the subcomponent image; computing pairwise distances from the transformed feature vector to each transformed feature vector in a training set; determining a proximity metric using said pairwise distances; and comparing the proximity metric against a proximity threshold to detect a defect in the subcomponent. Another embodiment relates to a product manufactured using a disclosed method of inspecting multiple subcomponents of a component for defects.

Abstract: The present disclosure provides methods and apparatus for rapidly classifying detected defects in subcomponents of a manufactured component or device. The defect classification may occur after defect detection or, because the classification may be sufficiently rapid to be performed in real-time, during defect detection, as part of the defect detection process. In an exemplary implementation, the presently-disclosed technology may be utilized to enable real-time classification of detected defects in multiple subcomponents of the component in parallel. The component may be, for example, a multi-chip package with silicon interposers, and the subcomponents may include, for example, through-silicon vias and solder joints. Defects in subcomponents of other types of components may be also be classified. One embodiment relates to a method of classifying detected defects in subcomponents of a manufactured component.

Abstract: In one embodiment, a computing system may obtain a high-resolution X-ray image and a number of low-resolution X-ray images of an object of interest. The system may divide each of the low-resolution X-ray images into a number of low-resolution patches. Each low-resolution patch may be associated with a portion of the object of interest. The system may input a set of low-resolution patches associated with a same portion of the object of interest into a machine-learning model. Each low-resolution patch of the set may be from a different low-resolution X-ray image. The machine-learning model may output a high-resolution patch for the same portion of the object of interest. The system may compare the high-resolution patch outputted by the machine-learning model to a corresponding portion of the high-resolution X-ray image of the object of interest and adjust one or more parameters of the machine-learning model based on the comparison.

Abstract: The presently-disclosed technology improves the resolution of an x-ray microscope so as to obtain super-resolution x-ray images having resolutions beyond the maximum normal resolution of the x-ray microscope. Furthermore, the disclosed technology provides for the rapid generation of the super-resolution x-ray images and so enables real-time super-resolution x-ray imaging for purposes of defect detection, for example. A method of super-resolution x-ray imaging using a super-resolving patch classifier is provided. In addition, a method of training the super-resolving patch classifier is disclosed. Other embodiments, aspects and features are also disclosed.

Abstract: The present disclosure provides methods and apparatus for rapidly classifying detected defects in subcomponents of a manufactured component or device. The defect classification may occur after defect detection or, because the classification may be sufficiently rapid to be performed in real-time, during defect detection, as part of the defect detection process. In an exemplary implementation, the presently-disclosed technology may be utilized to enable real-time classification of detected defects in multiple subcomponents of the component in parallel. The component may be, for example, a multi-chip package with silicon interposers, and the subcomponents may include, for example, through-silicon vias and solder joints. Defects in subcomponents of other types of components may be also be classified. One embodiment relates to a method of classifying detected defects in subcomponents of a manufactured component.

Abstract: The presently-disclosed technology enables real-time inspection of a multitude of subcomponents of a component in parallel. For example, the component may be a semiconductor package, and the subcomponents may include through-silicon vias. One embodiment relates to a method for inspecting multiple subcomponents of a component for defects, the method comprising, for each subcomponent undergoing defect detection: extracting a subcomponent image from image data of the component; computing a transformed feature vector from the subcomponent image; computing pairwise distances from the transformed feature vector to each transformed feature vector in a training set; determining a proximity metric using said pairwise distances; and comparing the proximity metric against a proximity threshold to detect a defect in the subcomponent. Another embodiment relates to a product manufactured using a disclosed method of inspecting multiple subcomponents of a component for defects.

Abstract: The presently-disclosed technology improves the resolution of an x-ray microscope so as to obtain super-resolution x-ray images having resolutions beyond the maximum normal resolution of the x-ray microscope. Furthermore, the disclosed technology provides for the rapid generation of the super-resolution x-ray images and so enables real-time super-resolution x-ray imaging for purposes of defect detection, for example. A method of super-resolution x-ray imaging using a super-resolving patch classifier is provided. In addition, a method of training the super-resolving patch classifier is disclosed. Other embodiments, aspects and features are also disclosed.

Abstract: The presently-disclosed technology improves the resolution of an x-ray microscope so as to obtain super-resolution x-ray images having resolutions beyond the maximum normal resolution of the x-ray microscope. Furthermore, the disclosed technology provides for the rapid generation of the super-resolution x-ray images and so enables real-time super-resolution x-ray imaging for purposes of defect detection, for example. A method of super-resolution x-ray imaging using a super-resolving patch classifier is provided. In addition, a method of training the super-resolving patch classifier is disclosed. Other embodiments, aspects and features are also disclosed.

Abstract: The presently-disclosed technology improves the resolution of an x-ray microscope so as to obtain super-resolution x-ray images having resolutions beyond the maximum normal resolution of the x-ray microscope. Furthermore, the disclosed technology provides for the rapid generation of the super-resolution x-ray images and so enables real-time super-resolution x-ray imaging for purposes of defect detection, for example. A method of super-resolution x-ray imaging using a super-resolving patch classifier is provided. In addition, a method of training the super-resolving patch classifier is disclosed. Other embodiments, aspects and features are also disclosed.

Abstract: A method for automated content insertion into a video sequence. The video sequence comprising a sequence of frames is received. An automated determination is made of non-moving pixels in the sequence of frames. Thereafter, an automated identification is made of valid regions comprising the non-moving pixels which are suitable for unobtrusive content insertion. Other embodiments, aspects and features are also disclosed.

Abstract: In one embodiment, an image is broken up into multiple regions or segments, where each segment may be of arbitrary shape, and a transform (multi-scale or otherwise) is applied on the set of segments. In another embodiment, pattern adaptive prediction is used when predicting the next finer level of the transform pyramid. The pattern adaptive prediction uses the parent grid to determine what geometry of a filter is to be used when predicting the child grid. At the boundaries of the domain, the pattern adaptive prediction can coupled with the domain adaptive prediction technique.

Abstract: One embodiment relates to an automated method for estimating motion of an image segment. An image frame is segmented into irregularly-shaped image segments. Motion vectors of blocks of pixels in the image frame are estimated. A determination is made as to the blocks which overlap a segment, and candidate motion vectors are determined from the motion vectors for those overlapping blocks. A motion vector for the segment is selected from amongst the candidate motion vectors. Other embodiments, aspects, and features are also disclosed.

Abstract: One embodiment relates to a computer-implemented method for the automated extraction of objects from a video stream. The method includes an automated procedure for creating a temporal graph, and an automated procedure for cutting the graph into graph partitions. The method further includes an automated procedure for mapping the graph partitions to pixels in frames of the video stream. Other features, aspects and embodiments are also disclosed.

Abstract: One embodiment relates to a computer-implemented method of image segmentation using automated saddle point detection. An edge map is created by edge detection, and a distance map is generated based on the edge map. Saddle points are detected using the distance map. Connector pixels are determined using the saddle points, and connector pixels forming valid connecting paths are marked as edge pixels. Finally, flood filling is performed within edges to designate image segments. Other features, aspects and embodiments are also disclosed.

Abstract: The present application discloses a method of model-based measurement of semiconductor device features using a scatterometer system. The method includes at least the following steps. A cost function is defined depending upon a plurality of variable parameters of the scatterometer system and upon a plurality of variable parameters for computer-implemented modeling to determine measurement results. Constraints are established for the plurality of variable parameters of the scatterometer system and for the plurality of variable parameters for the computer-implemented modeling. A computer-implemented optimization procedure is performed to determine an optimized global set of parameters, including both the variable parameters of the scatterometer system and the variable parameters for the computer-implemented modeling, which result in a minimal value of the cost function. Finally, the optimized global set of parameters is applied to configure the scatterometer system and the computer-implemented modeling.

Abstract: The present application discloses a new technique which reduces the dimensionality of a feature model by re-use of data that has been obtained by a prior measurement. The data re-used from the prior measurement may range from parameters, such as geometrical dimensions, to more complex data that describe the electromagnetic scattering function of an underlying layer (for example, a local solution of the electric field properties).

Abstract: One embodiment disclosed relates to the use of object motion estimation to interlace a progressive video sequence. One of a plurality of consecutive frames is segmented and motion vectors for each segment are determined though object motion estimation. Interpolated motion vectors are used to construct at least one intermediate frame, and interlaced fields are extracted from the new sequence of frames that includes intermediate frames. An interlaced sequence with smooth, incremental motion is thus constructed from a progressive video sequence.

Abstract: A method and apparatus for temporally filtering a video sequence using motion compensation in which motion information captures the motion of objects is disclosed. Pixels from a current frame are aligned with matching pixels from previous and/or future frames according to the motion of the surrounding object of arbitrary shape. A weighted average of the corresponding pixels is taken for each pixel in the current frame to produce a filtered version of the current frame. The weights may be adjusted to compensate for similarities between the frames and for blur transitions near object boundaries. A lighting offset may also be used to prevent erroneous lighting shifts during filtering.

Abstract: One embodiment relates to a computer-implemented method of image segmentation using automated saddle point detection. An edge map is created by edge detection, and a distance map is generated based on the edge map. Saddle points are detected using the distance map. Connector pixels are determined using the saddle points, and connector pixels forming valid connecting paths are marked as edge pixels. Finally, flood filling is performed within edges to designate image segments. Other features, aspects and embodiments are also disclosed.

Abstract: One embodiment relates to a computer-implemented method for the automated extraction of objects from a video stream. The method includes an automated procedure for creating a temporal graph, and an automated procedure for cutting the graph into graph partitions. The method further includes an automated procedure for mapping the graph partitions to pixels in frames of the video stream. Other features, aspects and embodiments are also disclosed.