G06K9/38

Image processing apparatus, binary image production method, and image processing program
10769486 · 2020-09-08 · ·

Provided is an image processing apparatus including an acquisition unit configured to acquire a multi-valued image and a binarization unit configured to generate a binary image obtained by binarizing the multi-valued image, and the stated image processing apparatus is configured such that the binarization unit detects a closed region within the multi-valued image, and binarizes the inside of the closed region based on luminance inside the closed region and luminance around the closed region.

Multiple stage image based object detection and recognition

Systems, methods, tangible non-transitory computer-readable media, and devices for autonomous vehicle operation are provided. For example, a computing system can receive object data that includes portions of sensor data. The computing system can determine, in a first stage of a multiple stage classification using hardware components, one or more first stage characteristics of the portions of sensor data based on a first machine-learned model. In a second stage of the multiple stage classification, the computing system can determine second stage characteristics of the portions of sensor data based on a second machine-learned model. The computing system can generate an object output based on the first stage characteristics and the second stage characteristics. The object output can include indications associated with detection of objects in the portions of sensor data.

Real time multi-object tracking apparatus and method using global motion

Provided are a real time multi-object tracking apparatus and method which use global motion, including separating a background and multiple objects from a detected image, recognizing the multiple objects separated from the background; calculating global motion information of the recognized multiple objects, which is information oriented by the multiple objects, and correcting the recognized multiple objects using the calculated global motion information and tracking the multiple objects.

Real-time gesture detection and recognition

A device receives, as part of a gesture translation service, data that depicts gestures, wherein the data is image data or multimedia data. The device converts a set of frames that include the data to another set of frames that include modified data identifying a grayscale or black and white depiction of the gestures and generates graphical representations of the gestures identified by the modified data. The device selects, using a matching technique, a graphical representation of corresponding gestures that matches or satisfies a threshold level of similarity with the graphical representations of the gestures identified by the modified data. The device identifies response data that is representative of the corresponding gestures based on the response data being stored in association with an identifier of the graphical representation that has been selected. The device provides the response data to be displayed, via an interface, as text data or audio data.

Background blurred method and electronic device based on foreground image

A background blurred method includes steps as follows: obtaining a color image, an IR light frame image and an IR dark frame image, and calculating a differential image between the IR light frame image and the IR dark frame image to generate a binary image; obtaining a foreground image of the binary image; calculating an IR brightness mean value of the foreground image of the differential image; and filtering the color image to generate a background blurred image according to the IR brightness mean value.

METHOD AND SYSTEM FOR IDENTIFYING BOLD TEXT IN A DIGITAL DOCUMENT
20200265225 · 2020-08-20 ·

Disclosed herein is a method and device for identifying bold text in a digital document. The system receives image of digital document which comprises text. The system applies bounding box for each text in the image and scans predefined number of lines in each bounding box to identify width values of pixels. Thereafter, system identifies most occurring width value of pixels among the width values of pixels in each bounding box. The most occurring width value of pixels in each bounding box is identified as box width of corresponding bounding box. The system compares box width of each bounding box with threshold box width. If box width is greater than threshold box width, system identifies text of the bounding box whose box width exceeds threshold box width as bold text. The present disclosure efficiently identifies bold text in digital document based on width values of pixels with less computational power.

Image processing device and program
10748283 · 2020-08-18 · ·

An image processing device and a program capable of extracting a cell region as a diagnosis target more accurately may be provided. An image processing device is characterized by: first extraction means (control unit 21) for extracting a candidate region from a form image representing a form of a cell in a tissue sample; acquisition means (control unit 21) for acquiring biological substance information on at least one kind of the biological substance from images representing expression of one or more kinds of biological substances in the tissue sample; and second extraction means (control unit 21) for extracting a diagnosis target region from the candidate region based on characteristic information indicating characteristics of the candidate region and/or the biological substance information.

Image processing method and electronic apparatus for foreground image extraction

An image processing method and an electronic apparatus for foreground image extraction include steps: (A) acquiring frame images of a dynamic image, wherein each frame image has an RGB image and an IR image; (B) acquiring an RGB image representing a dark state as an RGB capture image, acquiring an IR image representing a light state as an IR light frame image, and acquiring one IR image representing the dark state as an IR dark frame image; (C) calculating a difference image between the IR light frame image and the IR dark frame image and binarizing the difference image to generate a binarized image; and (D) acquiring a plurality of foreground pixels corresponding to an IR foreground part of the binarized image of the RGB capture image and taking the foreground pixels as the foreground image, thereby reducing the impact of ambient light, background noise and calculation.

Nanostructure pixel sensor and method
10747985 · 2020-08-18 ·

The present invention provides a nanostructure pixel sensor and a method for use thereof. A nanostructure pixel sensor includes a plurality of nanostructure pixels comprising periodic nanostructures. Every nanostructure pixel is designed to achieve a specific optical response at a given wavelength illuminated by a light beam. A nanostructure pixel sensor generates a wavelength-dependent image pattern, which is sensitive to the surrounding environment. The sensor described in the present invention utilizes image patterns to detect analytes and/or determine amount of analytes on the sensor surface or in the vicinity of the sensor surface.

INFORMATION PROCESSING APPARATUS, ARITHMETIC PROCESSING DEVICE, AND METHOD OF CONTROLLING INFORMATION PROCESSING APPARATUS
20200257498 · 2020-08-13 · ·

An information processing apparatus includes: a first preprocessing arithmetic device configured to execute preprocessing for analog data from a first sensor; and a first post-processing arithmetic device connected to the first preprocessing arithmetic device and configured to execute post-processing for first preprocessed data, wherein the first preprocessing arithmetic device includes a first processor configured to: receive the analog data from the first sensor and convert the analog data into digital data; output feature data on the basis of a result of execution of feature extraction processing for the digital data; and output the feature data, and the first post-processing arithmetic device includes a second processor configured to: input the feature data; store the feature data in a first memory; and store, in the first memory, recognition result data based on a result of execution of recognition processing for the feature data.