Abstract: A text correction method and apparatus can take advantage of a greatly reduced number of error-ground truth pairs to train a deep learning model. To generate these error-ground truth pairs, different characters in a ground truth word are replaced with a symbol, not appearing in any ground truth words, to generate error words which are paired with that ground truth word to provide error-ground truth word pairs. This process may be repeated for all ground truth words for which training is to be performed. In embodiments, pairs of characters in a ground truth word may be replaced with a symbol to generate the error words which are paired with that ground truth word to provide error-ground truth word pairs. Again, this process may be repeated for all ground truth words for which training is to be performed.

Abstract: Provided is an ultrasound diagnostic apparatus including a transceiver that transmits and receives first ultrasound of a low acoustic output and second ultrasound of a high acoustic output, and a first hardware processor that generates the ultrasound image based on a first reception signal acquired by transmitting and receiving the first ultrasound. The first hardware processor includes a learning model formed of a neural network, and generates the ultrasound image based on an output result of the learning model.

Abstract: A method for extracting text from an input image and generating a document includes: generating an edges mask from the input image; generating an edges image that is derived from the edges mask; identifying, within the edges mask, one or more probable text areas; extracting a first set of text characters by performing a first optical character recognition (OCR) operation on each of one or more probable text portions, of the derived edges image, corresponding to each of the probable text areas; generating a modified image by erasing, from the input image, image characters corresponding to the first set of text characters extracted by the first OCR operation; and generating a document by overlaying the extracted first set of text characters on the modified image.

Abstract: An image processing apparatus includes a hardware processor that generates an image based on print data of a print job and print image data for forming an image quality adjustment patch at a predetermined cycle and executes replacement processing for replacing a predetermined image with the image quality adjustment patch based on an image quality state of an output product or a state of an image former.

Abstract: An image forming apparatus includes a conveyance section that conveys a first recording medium and a second recording medium, a sensor that detects information relating to the first recording medium and information relating to the second recording medium, and a hardware processor that causes the sensor to detect the information relating to the first recording medium conveyed first by the conveyance section and to detect the information relating to the second recording medium conveyed by the conveyance section after the first recording medium, and outputs the detected information relating to the second recording medium after the first recording medium.

Abstract: A neural network system includes: a first layer generating first layer outputs of pieces of training data; a second layer; and a numerical conversion layer. During training, the numerical conversion layer: receives the first layer outputs from the first layer, calculates a numerical conversion parameter corresponding to each of the pieces of training data, numerically converts each of components of each of the first layer outputs using the numerical conversion parameter to generate a numerical conversion layer output, and inputs the same to the second layer. The numerical conversion parameter corresponding to one of the pieces of training data is: calculated from the first layer outputs of the pieces of training data except the one of the pieces of training data, or calculated by weighting one of the first layer outputs of the pieces of training data including the one of the pieces of training data.

Abstract: An image forming apparatus includes a sensor that detects information relating to the first recording medium and information relating to the second recording medium; and a hardware processor that causes the sensor to detect information relating to the first recording medium conveyed first by the conveyance section and to detect information relating to the second recording medium conveyed by the conveyance section after the first recording medium, causes the conveyance section to operate such that the second recording medium is conveyed at a conveyance speed based on the information relating to the first recording medium, and causes the conveyance section to operate such that the second recording medium is conveyed at the conveyance speed maintained even when the information relating to the second recording medium after the first recording medium is detected to be different from the information relating to the first recording medium.

Abstract: A speech setting system includes a job execution device that executes a job, for which a plurality of parameters are set, in accordance with the plurality of parameters and a speech setting assistance server, and the speech setting assistance server determines a plurality of parameters based on speech information obtained from a speech, determines utterance order of the plurality of parameters as output order, and outputs speech output information for outputting the plurality of parameters by speech in accordance with the output order.

Abstract: An image forming system includes: a conveyor that conveys a recording material along a conveyance path; a detector that is disposed on the conveyance path and detects a characteristic of the recording material; a fixer that fixes a toner image formed on the recording material; and a hardware processor that: causes the detector to detect the characteristic during a warm-up of the fixer with respect to an image forming job, and based on the characteristic, sets an image forming condition in the image forming job.

Abstract: A colorimetry device includes an integrating sphere having a measurement opening part and a trap hole, a trap disposed to be able to open and close the trap hole, a lid that is non-reflective and disposed to be able to open and close the trap hole, an imaging means disposed at a position that allows taking, through the trap hole, an image of a specimen facing the measurement opening part, and a display means that displays an image taken by the imaging means. The trap is to move to a position at which the trap hole is closed by the trap at a time of measurement of light with an SCI method, the light being reflected from the specimen, and the lid is moved to a position at which the trap hole is closed by the lid at a time of measurement of the light with an SCE method.

Abstract: Provided is an inter-shaft distance measuring device for measuring a distance between two shafts or an amount of a change in the distance that includes: measuring elements that are respectively in contact with peripheral surfaces of the two shafts at a time of measurement and that are used as measurement references; a moving mechanism that includes an elastic member and that holds the measuring elements to move the measuring elements relatively and adds a force in opposite directions separating the measuring elements by an elastic force of the elastic member; and a measurer that measures the change in the distance between the measuring elements. In a state at the time of the measurement, the measuring elements between the two shafts add a pressing force by the moving mechanism respectively to the two shafts in directions widening the distance, and the state at the time of the measurement is maintainable.

Abstract: An image forming apparatus includes: a hardware processor that quantizes each pixel with a dither pattern divided according to a resolution in a predetermined direction, and sets a recording amount of each pixel by adding up processing results of the quantization.

Abstract: An image inspection device which enables the user to know the cause of an abnormality in a read image. The image inspection device includes: an image reader outputting a read image generated by reading an image formed on a sheet of paper by an image forming device; an image inspection section inspecting the read image and outputting an inspection result which takes the read image determined not to have an abnormality as a normal image and the read image determined to have the abnormality as an abnormal image; an inspection result report generator generating an inspection result report according to the read image and the inspection result; an inspection result report output section outputting the inspection result report; and a controller performing control to cause the inspection result report output section to output the normal image and the abnormal image in a comparable manner.

Abstract: A content aware and style aware neural network based data augmentation model generates augmented data sets to train neural network based handwriting recognition models to recognize individuals' handwriting. The augmented data sets may be generated so as to be artificial, and to lack personal or confidential information. The data augmentation model may generate content reference sets of individual characters generated in different fonts, and style reference sets of pluralities of characters of a particular style, for example, an individual's handwriting.

Abstract: An ultrasound signal processing device including a transmitter, a receiver, an observation point setter, and a frame generator. The transmitter repeatedly performs a transmission event, changing a position of a transducer array for each transmission event, the transmission event including selecting the transducer array from transducers on an ultrasound probe and outputting a drive signal driving the transducer array to transmit focused transmitted ultrasound. The receiver receives signals from the ultrasound probe to generate signal sequences, the signals being based on reflected ultrasound acquired by the ultrasound probe. The observation point setter sets observation points corresponding to positions in the subject. The frame generator generates a frame acoustic line signal based on the signal sequences corresponding to each of the observation points. The observation points are set such that observation points in a region shallower than a focal region each correspond to only one transmission event.

Abstract: A gas flow rate estimation device includes a first calculation unit that calculates, by using an average movement vector of a gas region included in an image, a gas passage time for leaked gas to pass through the gas region, a second calculation unit that calculates a gas volume in the gas region by using a gas concentration thickness product of the gas region, and a third calculation unit that calculates an estimated value of a flow rate of the gas by using the gas passage time and the gas volume.

Abstract: A recording medium conveyance device includes a storage, a conveyer that conveys a conveyed object, an ultrasonic sensor that outputs a value indicating an attenuation amount of an ultrasonic wave caused by the conveyed object, and a hardware processor. The hardware processor executes a type detection process of detecting a type of the conveyed object based on output of the ultrasonic sensor and storing the type in the storage and an overlay detection process of detecting whether the conveyed object is in an overlay state in which a gap is present based on output of the ultrasonic sensor, and switches to either one of the type detection process and the overlay detection process. The hardware processor executes the type detection process when the type is not stored in the storage and executes the overlay detection process when the type is stored in the storage.

Abstract: A measurement method is provided for non-destructive inspection of a magnetic material as an inspection target in a non-magnetic body. The method includes application of a magnetic field from a magnetic field applying unit to the inspection target through a surface of the non-magnetic body, and measurement of a magnetic field from the inspection target with a magnetic sensor on the surface of the non-magnetic body adjacent to the magnetic field applying unit at positions having different distances from the magnetic field applying unit in a first direction away from the magnetic field applying unit. The magnetic field from the inspection target is attenuated with the distances. In the method, first and second measurements are performed with the magnetic field applying unit respectively arranged on one side and on the other side in the first direction relative to the positions where the magnetic sensor performs measurement.

Abstract: A gas detection device, a gas detection method, and a gas detection program according to the present invention detect gas on the basis of an image obtained by imaging a detection target. The gas detection device, the gas detection method, and the gas detection program; generated accumulated data obtained by accumulating a number of times of gas detection in a predetermined unit of accumulation, on the basis of a plurality of images captured at a plurality of times different from each other in a predetermined period; and generate a mask image for suppressing notification of detected gas on the basis of the generated accumulated data.

Abstract: A fabric treatment agent for use in textile printing by a sublimable color material, including an aromatic heterocyclic compound, wherein a molecular weight A of the aromatic heterocyclic compound satisfies the following relational formula (1).