Information processing device, image generation method, and non-transitory computer-readable medium
AssigneesNEC Corporation, NEC Solution Innovators, Ltd.
InventorsKeisuke SUZUKI, Mitsuru NOMA, Osamu HISAMATSU, Yoshinori WADA, Masayuki ITABASHI
Life of this patent
Estimating the term…
Abstract
An information processing device includes a digitizing unit for generating numerical data indicating a time-series change of a biological signal from first image data indicating a waveform of the biological signal, and an image generation unit for generating second image data indicating a waveform of the biological signal by using the generated numerical data. The generated second image data can be used as training data for machine learning or can be used for decision making by a medical worker in diagnosis of a subject to be measured for the biological signal.
Claims8
An information processing device comprising:
- at least one memory storing instructions and
- at least one processor configured to execute the instructions to:
- receive first image data, the first image data comprising a graphical representation of a waveform of a biological signal and a graphical reference object indicating a physical scale of the biological signal;
- detect, from the first image data, a pixel group corresponding to the graphical representation of the waveform;
- determine, based on a dimension of the graphical reference object within the first image data, a conversion scale for converting pixel coordinates to physical units of the biological signal;
- generate, by applying the determined conversion scale to coordinates of pixels in the detected pixel group, numerical data indicating a time-series change of the biological signal in the physical units;
- and
- generate, from the numerical data, second image data by drawing a waveform of the biological signal in a predetermined coordinate system defined by the physical units, regardless of a pixel arrangement of the first image data.
An image generation method for causing at least one processor to execute:
- receiving first image data, the first image data comprising a graphical representation of a waveform of a biological signal and a graphical reference object indicating a physical scale of the biological signal;
- detecting, from the first image data, a pixel group corresponding to the graphical representation of the waveform;
- determining, based on a dimension of the graphical reference object within the first image data, a conversion scale for converting pixel coordinates to physical units of the biological signal;
- generating, by applying the determined conversion scale to coordinates of pixels in the detected pixel group, numerical data indicating a time-series change of the biological signal in the physical units;
- and
- generating, from the numerical data, second image data by drawing a waveform of the biological signal in a predetermined coordinate system defined by the physical units, regardless of a pixel arrangement of the first image data.
A non-transitory computer-readable medium storing an image generation program for causing a computer to execute:
- receive first image data, the first image data comprising a graphical representation of a waveform of a biological signal and a graphical reference object indicating a physical scale of the biological signal;
- detect, from the first image data, a pixel group corresponding to the graphical representation of the waveform;
- determine, based on a dimension of the graphical reference object within the first image data, a conversion scale for converting pixel coordinates to physical units of the biological signal;
- generate, by applying the determined conversion scale to coordinates of pixels in the detected pixel group, numerical data indicating a time-series change of the biological signal in the physical units;
- and
- generate, from the numerical data, second image data by drawing a waveform of the biological signal in a predetermined coordinate system defined by the physical units, regardless of a pixel arrangement of the first image data.
Dependencies are inferred from the claim text.