Illustrative embodiments are directed to methods, apparatus and computer program products for segmentation of X-ray tomography images via multiple reconstructions. A computed tomography scan of an object is received. The computed tomography scan is processed to generate an absorption reconstruction and a phase reconstruction from the computed tomography scan. First and second sets of seeds within the phase reconstruction are labeled as corresponding to a first phase by thresholding below a first threshold and corresponding to a second phase by thresholding above a second threshold, respectively. The absorption reconstruction is segmented automatically using an algorithm based on the first set of seeds, the second set of seeds and the absorption reconstruction. A final segmentation is produced based on a combination of the absorption reconstruction and the phase reconstruction.

A system to detect quality of a silk cocoon is disclosed. The plurality of subsystems includes an image processing subsystem, configured to process the captured image of the one or more silk cocoons for noise. The plurality of subsystems includes an object detection subsystem, configured to detect cocoon contours from processed image. The plurality of subsystems also includes a cocoon analysing subsystem, configured to identify shape of the cocoon from the detected cocoon contours by using a shape function, compute a set of the parameters, validate the set of parameters with prestored parameters and determine the quality of each of the one or more silk cocoons based on the results of validation. The system uses OpenCV functions of python to do such complex work of grading silk cocoons. Such process reduces manual labour all together.

A computerized system, apparatus, and method of grading collectibles. The system comprises a grading apparatus that receives at least one image of the collectible. The grading apparatus applies at least one processing routine to said at least one image. The grading apparatus generates a grade report of the collectible based at least on results of the at least one processing routine. The system comprises an encasing apparatus configured to encase the graded collectible within a protective slab.

A method of object identification includes: capturing an image of an object having a material presenting surface artifacts; detecting a boundary within the captured image; selecting a portion of the image depicting the surface material within the boundary; based on the selected portion of the image, determining attributes of the surface artifacts; generating, based on the determined attributes of the surface artifacts, a physical identifier corresponding to the object; and storing the generated physical identifier.

System and methods used to inspect a moving web (112) include a plurality of image capturing devices (113) that image a portion of the web at an imaging area. The image data captured by each of the image capturing devices at the respective imaging areas is combined to form a virtual camera data array (105) that represents an alignment of the image data associated with each of the imaging areas to the corresponding physical positioning of the imaging areas relative to the web. The image output signals generated by each of the plurality of image capturing devices may be processed by a single image processor, or a number of image processors (114) that is less than the number of image capturing devices. The processor or processors are arranged to generate the image data forming the virtual camera array.

First image data representing a first human wearing a first article of clothing may be received. The first image data, when rendered on a display, may include a first photometric artifact. A first generator network may be used to generate second image data from the first image data. The first photometric artifact may be removed from the second image data. A second generator network may be used to generate third image data from the second image data, the third image data representing the first human in a different pose relative to the first image data. Fourth image data representing the first article of clothing segmented from the first human may be generated and displayed on a display.

Systems and methods for authenticating handbags using a portable electronic device along with a bilinear convolutional neural network (CNN) model are described. One method includes using a portable electronic device comprising a camera, and a lens-accessory attached to the portable electronic device such that an optical feature of the lens-accessory is positioned in front of the camera. The portable electronic device acquires one or more pictures of a handbag and sends the one or more pictures to a bilinear CNN model via a network asset where an authenticity is determined. The systems and methods disclosed are capable of allowing the portable electronic device to be spaced apart from the handbag while acquiring pictures, and the lens-accessory can be between 10× and 50× magnification.

A method of digital measuring the color of fabrics based on digital camera, includes: making plain fabric samples; obtaining ground-truth color of plain fabrics using a spectrophotometer; capturing a raw format digital image of the plain fabrics using the digital camera and extracting raw camera responses of the plain fabrics; capturing a raw format digital image of a target fabric and extracting the raw camera responses of a ROI in the target fabric; calculating a Euclidean distance and a similarity coefficient between the raw camera responses of the ROI in the target fabric and the plain fabrics; normalizing the Euclidean distance and the similarity coefficient; calculating a weighting coefficient of each color data of the plain fabrics based on the normalized Euclidean distance and similarity coefficient; weighting every color data of plain fabrics with a corresponding weighting coefficient; and summing the weighted color data of the plain fabrics.

A method of analysing the quality of a welding area of an absorbent sanitary article is disclosed. During a learning step, a plurality of welding operations are performed both with a sufficient quality and with an insufficient quality, and the welding area generated for each welding operation is monitored via a camera. During a training step, the pixel data of the welding areas monitored during the learning step is processed for training a classifier configured to estimate a welding quality as a function of respective pixel data of a respective welding area. Accordingly, during a normal welding operating step, the welding quality may be estimate via the classifier, thereby improving the environmental sustainability of the production process.

Systems and methods for on-loom detection of faults in fabric. An image-capture trigger-mechanism triggers an imaging device to capture a first image of a section of the weaving area at a first instant during each weft insertion cycle and a second image of the section of weaving area may be captured at a second instant during each weft insertion cycle. The images may be timed to provide images of the warp yarns and the weft yarns at optimal instants during the weft insertion cycle. An image processor detects irregularities in the data received from the imaging device