Abstract: A computer implemented method comprising: receiving a report on a condition of a human or animal subject, composed by a user based on a scan of the subject; inputting the current report and the scan into a trained machine learning model; and based on the report and the scan, the machine learning model generating one or more suggestions for updating the text of the report. The method further comprises causing a user interface to display to the user one or more suggestions for updating the text of the report, with each respective suggestion visually linked in the user interface to a corresponding subregion within at least one image of the scan based upon which the respective suggestion was generated.

Abstract: A computer implemented method comprising: receiving a report on a condition of a human or animal subject, composed by a user based on a scan of the subject; inputting the current report and the scan into a trained machine learning model; and based on the report and the scan, the machine learning model generating one or more suggestions for updating the text of the report. The method further comprises causing a user interface to display to the user one or more suggestions for updating the text of the report, with each respective suggestion visually linked in the user interface to a corresponding subregion within at least one image of the scan based upon which the respective suggestion was generated.

Abstract: An image processing system is described which has a memory holding at least one image depicting at least one person previously unseen by the image processing system. The system has a trained probabilistic model which describes a relationship between image features, context, identities and a plurality of names of people, wherein at least one of the identities identifies a person depicted in the image without an associated name in the plurality of names. The system has a feature extractor which extracts features from the image, and a processor which predicts an identity of the person depicted in the image using the extracted features and the probabilistic model.

Abstract: An image processing system is described which has a memory holding at least one image depicting at least one person previously unseen by the image processing system. The system has a trained probabilistic model which describes a relationship between image features, context, identities and a plurality of names of people, wherein at least one of the identities identifies a person depicted in the image without an associated name in the plurality of names. The system has a feature extractor which extracts features from the image, and a processor which predicts an identity of the person depicted in the image using the extracted features and the probabilistic model.

Abstract: A computer implemented method comprising: receiving a report on a condition of a human or animal subject, composed by a user based on a scan of the subject; inputting the current report and the scan into a trained machine learning model; and based on the report and the scan, the machine learning model generating one or more suggestions for updating the text of the report. The method further comprises causing a user interface to display to the user one or more suggestions for updating the text of the report, with each respective suggestion visually linked in the user interface to a corresponding subregion within at least one image of the scan based upon which the respective suggestion was generated.

Abstract: An image processing system is described which has a memory holding at least one image depicting at least one person previously unseen by the image processing system. The system has a trained probabilistic model which describes a relationship between image features, context, identities and a plurality of names of people, wherein at least one of the identities identifies a person depicted in the image without an associated name in the plurality of names. The system has a feature extractor which extracts features from the image, and a processor which predicts an identity of the person depicted in the image using the extracted features and the probabilistic model.

Abstract: An image processing system is described which has a memory holding at least one image depicting at least one person previously unseen by the image processing system. The system has a trained probabilistic model which describes a relationship between image features, context, identities and a plurality of names of people, wherein at least one of the identities identifies a person depicted in the image without an associated name in the plurality of names. The system has a feature extractor which extracts features from the image, and a processor which predicts an identity of the person depicted in the image using the extracted features and the probabilistic model.

Abstract: An image processing system is described which has a memory holding at least one image depicting at least one person previously unseen by the image processing system. The system has a trained probabilistic model which describes a relationship between image features, context, identities and a plurality of names of people, wherein at least one of the identities identifies a person depicted in the image without an associated name in the plurality of names. The system has a feature extractor which extracts features from the image, and a processor which predicts an identity of the person depicted in the image using the extracted features and the probabilistic model.

Abstract: The system includes five components: (1) a sensor array, (2) a processor, (3) a transmitter, (4) a receiver-stimulator, and (5) an implantable electrode array. The olfactory implant system generates odor fingerprints by detecting odors with an array of chemical sensors and then transmitting variable spatio-temporal stimulation patterns for an electrode array with electrode stimulating points positioned at different locations in the olfactory cortex (e.g., stimulating the olfactory bulb). Different patterns of activity in the olfactory cortex are thereby generated which mimic the sense of smell in a subject. Once trained the system should be usable by a subject to detect or correctly identify one or more odors.

Abstract: The system includes five components: (1) a sensor array, (2) a processor, (3) a transmitter, (4) a receiver-stimulator, and (5) an implantable electrode array. The olfactory implant system generates odor fingerprints by detecting odors with an array of chemical sensors and then transmitting variable spatio-temporal stimulation patterns for an electrode array with electrode stimulating points positioned at different locations in the olfactory cortex (e.g., stimulating the olfactory bulb). Different patterns of activity in the olfactory cortex are thereby generated which mimic the sense of smell in a subject. Once trained the system should be usable by a subject to detect or correctly identify one or more odors.

Abstract: An optical fiber drawing installation is equipped with an oscillating pulley that applies torsion to the fiber alternately in one rotation direction and then in the opposite direction. To control the torsion applied to the fiber, images are formed of the fiber and the pulley. The images are analyzed to determine the position of the fiber relative to the pulley. The torsion is calculated from the calculated position, on the assumption that the fiber rolls on the pulley.

Abstract: The invention relates to an inductive thermal plasma torch comprising a confinement tube that comprises, longitudinally in relation to the tube, metal fingers which are insulated from each other, an ignition device that comprises an igniter (4) and an igniter support (1, 3), the purpose of the igniter (4) being to initiate a discharge in the plasma of the torch, the support having an electrically conductive end (1) which is connected to the electrical earth (2) of the plant and another, electrically insulating, end (3) which carries the igniter, the ignition device also comprising an electrically conductive connection (5) connecting the igniter (4) to the electrically conductive end (1) of the support so that the igniter is able to initiate the discharge in the plasma, the electrically conductive connection (5) having a section that is sufficiently narrow to limit the intensity of the current capable of passing through the igniter (4) in order to avoid electrical arcing by capacitive discharge between the ign

Abstract: The invention relates to an inductive thermal plasma torch comprising a confinement tube that comprises, longitudinally in relation to the tube, metal fingers which are insulated from each other, an ignition device that comprises an igniter (4) and an igniter support (1, 3), the purpose of the igniter (4) being to initiate a discharge in the plasma of the torch, the support having an electrically conductive end (1) which is connected to the electrical earth (2) of the plant and another, electrically insulating, end (3) which carries the igniter, the ignition device also comprising an electrically conductive connection (5) connecting the igniter (4) to the electrically conductive end (1) of the support so that the igniter is able to initiate the discharge in the plasma, the electrically conductive connection (5) having a section that is sufficiently narrow to limit the intensity of the current capable of passing through the igniter (4) in order to avoid electrical arcing by capacitive discharge between the ign

Abstract: An optical fiber drawing installation is equipped with an oscillating pulley that applies torsion to the fiber alternately in one rotation direction and then in the opposite direction. To control the torsion applied to the fiber, images are formed of the fiber and the pulley. The images are analyzed to determine the position of the fiber relative to the pulley. The torsion is calculated from the calculated position, on the assumption that the fiber rolls on the pulley.