Yoshihide SAWADA has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
Abstract: A transfer learning apparatus includes a transfer target data evaluator and an output layer adjuster. The transfer target data evaluator inputs a plurality of labeled transfer target data items each assigned a label of a corresponding evaluation item from among one or more evaluation items to a neural network apparatus having been trained by using a plurality of labeled transfer source data items and including in an output layer output units, the number of which is larger than or equal to the number of evaluation items, and obtains evaluation values output from the respective output units. The output layer adjuster preferentially assigns, to each of the one or more evaluation items, an output unit from which the evaluation value having the smallest difference from the label of the evaluation item is obtained with a higher frequency, as an output unit that outputs the evaluation value of the evaluation item.
Abstract: An image processing apparatus for estimating a position in an image which an operator who observes the image is likely to observe as the candidate of a next position is provided. The image processing apparatus includes a next observation estimating unit that estimates a position selected from among a plurality of positions using a parameter indicating an operation history and information regarding an estimation result at least at a current time on the basis of a probability value obtained from a predetermined probability distribution and a displayed image generating unit that generates an image to be displayed so that at least the candidate of the next position is visually recognizable.
Abstract: An image processing apparatus includes a divider that generates a plurality pieces of third image information on the basis of a plurality of pieces of first image information and a plurality of pieces of second image information, a determiner that determines, on the basis of information regarding a sample, a filter to be used for the plurality of pieces of third image information, and a processor that deconvolutes each of the plurality of pieces of third image information using the determined filter. An image sensor that has received first resulting light emitted from a sample that has received first light emitted from a first angle outputs the plurality of pieces of first image information. The image sensor that has received second resulting light emitted from the sample that has received second light emitted from a second angle outputs the plurality of pieces of second image information.
Abstract: A socket includes a first base member that includes a module mount unit allowing a module including an imaging device and an object to be placed thereon and an electric connector that electrically connects the imaging device to an external apparatus, a second base member having an opening, and an engagement unit that causes the first base member to be engaged with the second base member under a condition that the module placed on the module mount unit is sandwiched by the first and second base members. When the first base member is engaged with the second base member by the engagement unit under a condition that the module placed on the module mount unit is sandwiched by the first base member and the second base member, the electric connector is electrically connected to the imaging device, and the object receives illumination light from a light source through the opening.
Abstract: An exemplary image forming apparatus includes: an illumination system which sequentially emits illuminating light beams from multiple different irradiation directions; an image sensor which captures a plurality of different images in the multiple different irradiation directions, respectively; an image processing section which forms a high-resolution image; and a memory which stores data about the ratio of light rays that have been incident on a photoelectric conversion section of each pixel of the image sensor to light rays that have passed through the upper surface of a plurality of subpixels included in the pixel with respect to each of the multiple irradiation directions. The image processing section forms the high-resolution image based on the data that has been retrieved from the memory by extracting, as a vector, a set of pixel values associated with the multiple irradiation directions from pixel values that form each of the plurality of images.