CN115797560B - Near infrared spectrum imaging-based head model construction method and system - Google Patents
Near infrared spectrum imaging-based head model construction method and system Download PDFInfo
- Publication number
- CN115797560B CN115797560B CN202211504016.7A CN202211504016A CN115797560B CN 115797560 B CN115797560 B CN 115797560B CN 202211504016 A CN202211504016 A CN 202211504016A CN 115797560 B CN115797560 B CN 115797560B
- Authority
- CN
- China
- Prior art keywords
- head
- image
- bone
- skull
- region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses a head model construction method and a system based on near infrared spectrum imaging, wherein the technical scheme of the invention is that near infrared spectrum data with the wavelength of 1000-1100nm is extracted as a facial skull region imaging data source of the head of a target person, and the characteristic of severe short wave fluctuation is utilized to accurately identify the eye socket region, nasal cavity region, oral cavity region and other gully regions in the facial skull region of the person; near infrared spectrum data with the wavelength of 1800-2200nm is extracted to serve as a brain skull region imaging data source of the head of the target person, and gradient regions such as a hindbrain region in the brain skull region of the person can be accurately identified by utilizing the characteristic of gentle fluctuation of long waves, so that accurate head data of the person can be obtained; then, after the images formed by the two data are fused, an accurate head model can be constructed.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a head model construction method and system based on near infrared spectrum imaging.
Background
With the progress and development of society, the pursuit of self health is also increasing. Under the bidirectional push of the increase of demands and the development of technology, more and more medical instruments are developed and put into use; among them, medical instruments for head brain research are increasingly demanded.
An electroencephalogram (EEG) cap, a medical device for EEG research of EEG activities. By securing the electrodes to the head, the cap design may include helmets, frames, grids, and soft elastic caps to hug the head. In practical applications, caps with different shapes and sizes need to be designed according to different study types and patient requirements, for example: because of different development degrees, the adult, the child and the neonate need to collect head data according to the development condition of the skull, design a corresponding head model and finally manufacture a proper cap. However, in the process of designing a corresponding head model by collecting head data in the prior art, the head data is often collected by a camera or an infrared scanner, but the head data is limited to the pixel and detail resolution capability of the camera, and the fine skull change difference cannot be accurately collected; the head data collected by the prior art is often unreliable and cannot meet the actual demands of users.
Near infrared spectroscopy has been the fastest growing and most attractive spectroscopic analysis technique since the 90 s, an organic combination of spectrometry techniques and chemometrics. The spectrum imaging technology can divide the spectrum of a substance into tens to hundreds of wave bands, so that the identification capability of the fine spectrum characteristics of a target is greatly improved. At present, no related technical study for designing a head model and finally manufacturing an accurate hat by utilizing a near infrared spectrum imaging technology exists in the prior art. Therefore, how to construct an accurate head model through near infrared spectrum imaging is a technical problem that we need to solve.
Disclosure of Invention
The invention provides a head model construction method and a system based on near infrared spectrum imaging, which can acquire accurate figure head data so as to construct an accurate head model.
In order to solve the above technical problems, an embodiment of the present invention provides a method for constructing a head model based on near infrared spectrum imaging, including:
acquiring near infrared spectrum data of the head of a target person, extracting near infrared spectrum data corresponding to the spectrum wavelength of 1000-1100nm in the near infrared spectrum data to obtain first spectrum data, and extracting near infrared spectrum data corresponding to the spectrum wavelength of 1800-2200nm to obtain second spectrum data;
Generating a first head stereoscopic image and a second head stereoscopic image of the head of the target person according to the first spectral data and the second spectral data, respectively;
extracting a facial skull region in the first head stereo image to obtain a facial skull spectrum image; extracting a brain skull region in the second head three-dimensional image to obtain a brain skull spectrum image;
determining position reference data between the facial skull region and the cerebral skull region according to the spatial distance between the facial skull region and the cerebral skull region at the head of the target person;
according to the position reference data, the facial skull spectral image is taken as a bottom layer, the cerebral skull spectral image is taken as a top layer, and the facial skull spectral image and the cerebral skull spectral image are fused to obtain a target character head image;
and extracting three-dimensional data of the head of the target person according to the head image of the target person, and establishing a head model of the target person according to the three-dimensional data.
Preferably, the step of generating the first head stereoscopic image and the second head stereoscopic image of the head of the target person according to the first spectrum data and the second spectrum data, respectively, specifically includes:
Generating a first initial image of the head of the target person according to the first spectrum data, identifying an eye socket area, a nasal cavity area and an oral cavity area of the head of the target person in the first initial image, and performing characteristic amplification processing to obtain a first head three-dimensional image;
and generating a second initial image of the head of the target person according to the second spectrum data, identifying a hindbrain region of the head of the target person in the second initial image, and performing feature enhancement processing to obtain a second head stereoscopic image.
As a preferable scheme, the process of performing the feature amplification processing specifically includes:
gridding an orbit area, a nasal cavity area and an oral cavity area in the first initial image, and marking each grid;
performing resolution amplification processing on the orbit region, the nasal cavity region and the oral cavity region in the first initial image by a bicubic interpolation algorithm;
and setting a brightness threshold value, and reducing brightness of other areas except for an eye socket area, a nasal cavity area and an oral cavity area in the first initial image to obtain a first head stereo image.
As a preferable scheme, the process of performing the feature enhancement processing specifically includes:
After the resolution amplification treatment is carried out on the first initial image, determining the amplification factor according to the number of grids generated after the resolution amplification treatment is carried out on the grids of the original mark;
according to the magnification, performing resolution magnification processing on a hindbrain region in the second initial image through a nearest neighbor interpolation algorithm;
and increasing the brightness value of the hindbrain region according to the brightness threshold, and performing 50% transparency reduction treatment on other regions except the hindbrain region in the second initial image to obtain a second head stereoscopic image.
As a preferred solution, the step of extracting the facial skull region in the first head stereo image to obtain a facial skull spectrum image specifically includes: identifying skull features in the first head stereo image, extracting maxillary, nasal, lacrimal, zygomatic, lower turbinate, plow and mandibular regions; performing secondary extraction on the region between the maxilla and the mandible to form an oral region; secondly extracting the area between the lacrimal bones and the zygomatic bones to form an orbit area; and, performing secondary extraction on the area between the nasal bone, the lower turbinate bone and the plow bone to form a nasal cavity area; and extracting the area images corresponding to the oral cavity area, the eye socket area and the nasal cavity area to form facial skull spectrum images.
Extracting a skull region in the second head stereo image to obtain a skull spectrum image, which specifically comprises the following steps: identifying the skull features in the second head stereo image, and extracting frontal bone, parietal bone, temporal bone, ethmoid bone, sphenoid bone and occipital bone regions; performing secondary extraction on the area among the frontal bone, the parietal bone and the temporal bone to form a calvarial bone area; and performing secondary extraction on the region among the sieve bones, the sphenoid bones and the occipital bones to form a skull base bone region; and extracting the regional images corresponding to the calvaria bone region and the calvaria bone region to form a brain skull spectrum image.
Preferably, the step of determining the position reference data between the skull region and the skull region according to the spatial distance between the skull region and the skull region at the head of the target person specifically includes:
respectively establishing a three-dimensional space coordinate system in the first head stereo image and the second head stereo image;
determining coordinate positions of maxilla, nasal bone, lacrimal bone, zygomatic bone, lower turbinate, plow-shaped bone and mandible in a three-dimensional space coordinate system in a facial skull region, and calculating space distances between every two to form a first distance sequence;
Determining coordinate positions of frontal bone, parietal bone, temporal bone, sieve bone, sphenoid bone and occipital bone in a three-dimensional space coordinate system of a brain skull region, and calculating space distances between every two to form a second distance sequence;
and determining the spatial distances of the facial skull region and the cerebral skull region at different positions according to the first distance sequence and the second distance sequence, and obtaining position reference data.
As a preferred solution, the step of fusing the facial skull spectral image and the cerebral skull spectral image to obtain the head image of the target person specifically includes:
determining a reference position area according to the position reference data; wherein the reference location area includes any one or more of a maxilla, a nasal bone, a lacrimal bone, a zygomatic bone, a lower turbinate, a plow bone, or a mandible; including any one or more of frontal bone, parietal bone, temporal bone, ethmoid bone, sphenoid bone, or occipital bone;
taking the facial skull spectrum image as a bottom layer, taking the cerebral skull spectrum image as a top layer, selecting a reference position area in the facial skull spectrum image as a first alignment point, and simultaneously selecting the reference position area in the cerebral skull spectrum image as a second alignment point;
And aligning and combining the facial skull spectrum image and the cerebral skull spectrum image according to the first alignment point and the second alignment point to obtain a head image of the target person.
Preferably, the step of extracting three-dimensional data of the head of the target person according to the head image of the target person and establishing a head model of the target person according to the three-dimensional data specifically includes:
extracting three-dimensional coordinate parameters of the skull from the coordinate positions of the maxilla, the nasal bone, the lacrimal bone, the zygomatic bone, the lower turbinate, the plow bone, the mandible, the frontal bone, the parietal bone, the temporal bone, the ethmoid bone, the sphenoid bone and the occipital bone of the head image of the target person in a three-dimensional space coordinate system;
and constructing an initial head model, inputting the three-dimensional coordinate parameters of the skull into the initial head model, and generating a target character head model.
Correspondingly, another embodiment of the present invention also provides a head model building system based on near infrared spectrum imaging, including: the device comprises a data extraction module, an image generation module, a region extraction module, a position reference module, an image fusion module and a model establishment module;
the data extraction module is used for obtaining near infrared spectrum data of the head of the target person, extracting near infrared spectrum data corresponding to the spectrum wavelength of 1000-1100nm in the near infrared spectrum data to obtain first spectrum data, and extracting near infrared spectrum data corresponding to the spectrum wavelength of 1800-2200nm to obtain second spectrum data;
The image generation module is used for generating a first head stereoscopic image and a second head stereoscopic image of the head of the target person according to the first spectrum data and the second spectrum data respectively;
the region extraction module is used for extracting the facial skull region in the first head stereo image to obtain a facial skull spectrum image; extracting a brain skull region in the second head three-dimensional image to obtain a brain skull spectrum image;
the position reference module is used for determining position reference data between the facial skull region and the cerebral skull region according to the spatial distance between the facial skull region and the cerebral skull region at the head of the target person;
the image fusion module is used for fusing the facial skull spectral image and the cerebral skull spectral image to obtain a head image of a target person according to the position reference data by taking the facial skull spectral image as a bottom layer and taking the cerebral skull spectral image as a top layer;
the model building module is used for extracting three-dimensional data of the head of the target person according to the head image of the target person and building a head model of the target person according to the three-dimensional data.
Preferably, the image generating module comprises a first generating unit and a second generating unit; the first generation unit is used for generating a first initial image of the head of the target person according to the first spectrum data, identifying an eye socket area, a nasal cavity area and an oral cavity area of the head of the target person in the first initial image, and performing feature amplification processing to obtain a first head three-dimensional image; the second generating unit is configured to generate a second initial image of the head of the target person according to the second spectrum data, identify a hindbrain region of the head of the target person in the second initial image, and perform feature enhancement processing to obtain a second head stereoscopic image.
As a preferred solution, the first generating unit is configured to perform a process of feature amplification processing, specifically: gridding an orbit area, a nasal cavity area and an oral cavity area in the first initial image, and marking each grid; performing resolution amplification processing on the orbit region, the nasal cavity region and the oral cavity region in the first initial image by a bicubic interpolation algorithm; and setting a brightness threshold value, and reducing brightness of other areas except for an eye socket area, a nasal cavity area and an oral cavity area in the first initial image to obtain a first head stereo image.
As a preferred solution, the second generating unit is configured to perform a process of feature enhancement processing, specifically: after the resolution amplification treatment is carried out on the first initial image, determining the amplification factor according to the number of grids generated after the resolution amplification treatment is carried out on the grids of the original mark; according to the magnification, performing resolution magnification processing on a hindbrain region in the second initial image through a nearest neighbor interpolation algorithm; and increasing the brightness value of the hindbrain region according to the brightness threshold, and performing 50% transparency reduction treatment on other regions except the hindbrain region in the second initial image to obtain a second head stereoscopic image.
Preferably, the region extraction module is configured to extract a facial skull region in the first head stereo image, and the step of obtaining a facial skull spectrum image specifically includes: identifying skull features in the first head stereo image, extracting maxillary, nasal, lacrimal, zygomatic, lower turbinate, plow and mandibular regions; performing secondary extraction on the region between the maxilla and the mandible to form an oral region; secondly extracting the area between the lacrimal bones and the zygomatic bones to form an orbit area; and, performing secondary extraction on the area between the nasal bone, the lower turbinate bone and the plow bone to form a nasal cavity area; and extracting the area images corresponding to the oral cavity area, the eye socket area and the nasal cavity area to form facial skull spectrum images.
The region extraction module is used for extracting a skull region in the second head stereo image, and specifically comprises the following steps of: identifying the skull features in the second head stereo image, and extracting frontal bone, parietal bone, temporal bone, ethmoid bone, sphenoid bone and occipital bone regions; performing secondary extraction on the area among the frontal bone, the parietal bone and the temporal bone to form a calvarial bone area; and performing secondary extraction on the region among the sieve bones, the sphenoid bones and the occipital bones to form a skull base bone region; and extracting the regional images corresponding to the calvaria bone region and the calvaria bone region to form a brain skull spectrum image.
Preferably, the position reference module is specifically configured to: respectively establishing a three-dimensional space coordinate system in the first head stereo image and the second head stereo image; determining coordinate positions of maxilla, nasal bone, lacrimal bone, zygomatic bone, lower turbinate, plow-shaped bone and mandible in a three-dimensional space coordinate system in a facial skull region, and calculating space distances between every two to form a first distance sequence; determining coordinate positions of frontal bone, parietal bone, temporal bone, sieve bone, sphenoid bone and occipital bone in a three-dimensional space coordinate system of a brain skull region, and calculating space distances between every two to form a second distance sequence; and determining the spatial distances of the facial skull region and the cerebral skull region at different positions according to the first distance sequence and the second distance sequence, and obtaining position reference data.
As a preferred solution, the image fusion module is specifically configured to: determining a reference position area according to the position reference data; wherein the reference location area includes any one or more of a maxilla, a nasal bone, a lacrimal bone, a zygomatic bone, a lower turbinate, a plow bone, or a mandible; including any one or more of frontal bone, parietal bone, temporal bone, ethmoid bone, sphenoid bone, or occipital bone; taking the facial skull spectrum image as a bottom layer, taking the cerebral skull spectrum image as a top layer, selecting a reference position area in the facial skull spectrum image as a first alignment point, and simultaneously selecting the reference position area in the cerebral skull spectrum image as a second alignment point; and aligning and combining the facial skull spectrum image and the cerebral skull spectrum image according to the first alignment point and the second alignment point to obtain a head image of the target person.
As a preferred solution, the model building module is specifically configured to: extracting three-dimensional coordinate parameters of the skull from the coordinate positions of the maxilla, the nasal bone, the lacrimal bone, the zygomatic bone, the lower turbinate, the plow bone, the mandible, the frontal bone, the parietal bone, the temporal bone, the ethmoid bone, the sphenoid bone and the occipital bone of the head image of the target person in a three-dimensional space coordinate system; and constructing an initial head model, inputting the three-dimensional coordinate parameters of the skull into the initial head model, and generating a target character head model.
The embodiment of the invention also provides a computer readable storage medium, which comprises a stored computer program; wherein the computer program, when run, controls a device in which the computer readable storage medium is located to perform the near infrared spectroscopy imaging-based head model building method according to any one of the above.
The embodiment of the invention also provides a terminal device, which comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein the processor realizes the head model building method based on near infrared spectrum imaging according to any one of the above when executing the computer program.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
according to the technical scheme, near infrared spectrum data with the wavelength of 1000-1100nm is extracted to serve as a facial skull region imaging data source of the head of the target person, and the characteristic of severe short wave fluctuation is utilized to accurately identify the eye socket region, the nasal cavity region, the oral cavity region and other gully regions in the facial skull region of the person; near infrared spectrum data with the wavelength of 1800-2200nm is extracted to serve as a brain skull region imaging data source of the head of the target person, and gradient regions such as a hindbrain region in the brain skull region of the person can be accurately identified by utilizing the characteristic of gentle fluctuation of long waves, so that accurate head data of the person can be obtained; then, after the images formed by the two data are fused, an accurate head model can be constructed.
Drawings
Fig. 1: the method for constructing the head model based on the near infrared spectrum imaging comprises the following steps of;
fig. 2: the method is a schematic diagram of a target character head model constructed in the embodiment of the invention;
fig. 3: the structure schematic diagram of the head model building system based on near infrared spectrum imaging is provided for the embodiment of the invention;
fig. 4: the embodiment of the terminal equipment provided by the embodiment of the invention is a structural schematic diagram.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1, a step flowchart of a head model construction method based on near infrared spectrum imaging provided in an embodiment of the present invention includes steps 101 to 106, where each step is specifically as follows:
Step 101, near infrared spectrum data of the head of the target person is obtained, near infrared spectrum data corresponding to the spectrum wavelength of 1000-1100nm is extracted from the near infrared spectrum data to obtain first spectrum data, and near infrared spectrum data corresponding to the spectrum wavelength of 1800-2200nm is extracted to obtain second spectrum data.
Specifically, near infrared spectrometers are electromagnetic radiation waves between the visible and mid-infrared, and the ASTM material detection society defines the near infrared spectrum region as the region of 780-2526nm, the first non-visible region found in the absorption spectrum. The near infrared spectrum region is consistent with the frequency combination of vibration of the hydrogen-containing groups (O-H, N-H, C-H) in the organic molecules and the absorption region of frequency multiplication of each level, and the characteristic information of the hydrogen-containing groups of the organic molecules in the sample can be obtained by scanning the near infrared spectrum of the sample. For any particular near infrared spectroscopy instrument, there is its effective spectral range, which is largely dependent on the design of the instrument's optical path, the type of detector, and the light source. The wavelength range of a near infrared spectroscopy instrument is generally divided into two sections, a short-wave near infrared spectrum region of 700 to 1100nm and a long-wave near infrared spectrum region of 1100 to 2500 nm. The shortwaves have the characteristics of strong fluctuation and accurate identification aiming at the region of the gully; the long wave has the characteristics of smooth fluctuation and full identification aiming at the gradient area. The human head has deep gully regions such as an orbit region, a nasal cavity region, an oral cavity region and the like on the front face due to the condition of organ layout, and has a hindbrain gradient region such as a calvaria bone, a calvaria bone and the like on the hindbrain, so that the head data of the human cannot be accurately acquired by adopting a common near infrared light imaging technology in the prior art. Through a large number of experiments and tests, the research proves that short waves of 1000-1100nm in the near infrared spectrum can extract accurate data from deep gully areas such as an orbit area, a nasal cavity area, an oral cavity area and the like in the front face of a person, and long waves of 1800-2200nm can extract accurate data from hindbrain gradient areas such as calvaria bones and calvaria bones in the hindbrain. Therefore, near infrared spectrum data corresponding to two frequency bands of 1000-1100nm and 1800-2200nm are respectively extracted, corresponding images are respectively generated in the subsequent steps and then fused, and the head accurate model can be generated.
And 102, generating a first head stereoscopic image and a second head stereoscopic image of the head of the target person according to the first spectrum data and the second spectrum data respectively. In this embodiment, the step 102 specifically includes: step 1021 and step 1022.
Specifically, after generating corresponding images according to spectral data of different frequency bands, due to the proximity between the two frequency bands of 1000-1100nm and 1800-2200nm, we need to "zoom in" on the features of the two images to increase the significance of the features.
And 1021, generating a first initial image of the head of the target person according to the first spectrum data, identifying the eye socket area, the nasal cavity area and the oral cavity area of the head of the target person in the first initial image, and performing feature amplification processing to obtain a first head stereo image. In this embodiment, the step 1021 performs the feature amplification processing, specifically includes: gridding an orbit area, a nasal cavity area and an oral cavity area in the first initial image, and marking each grid; performing resolution amplification processing on the orbit region, the nasal cavity region and the oral cavity region in the first initial image by a bicubic interpolation algorithm; and setting a brightness threshold value, and reducing brightness of other areas except for an eye socket area, a nasal cavity area and an oral cavity area in the first initial image to obtain a first head stereo image.
Specifically, for the regions of the ravines such as the orbit region, the nasal cavity region, the oral cavity region and the like, we perform feature amplification processing, divide the region image into individual grids by gridding processing, and mark each individual grid. Amplifying each grid through a bicubic interpolation algorithm; b spline curve interpolation adopted by the bicubic interpolation algorithm is used for interpolating 4 continuous points in each dimension, so that slopes among all points are continuous and abrupt changes are avoided; if the slope between adjacent squares is continuous in the two-dimensional case, no significant mosaic is visible to the human eye. Aiming at the deep gully regions such as the eye orbit region, the nasal cavity region, the oral cavity region and the like, the problem of abrupt change formed by the characteristic points in the amplifying process needs to be solved, so that the problem can be better solved by adopting a bicubic interpolation algorithm. Then, after the feature amplification, it is necessary to perform a luminance reduction process on the other regions than the region of the ravines in order to bring about a more accurate image in the subsequent image fusion.
Step 1022, generating a second initial image of the head of the target person according to the second spectrum data, identifying a hindbrain region of the head of the target person in the second initial image, and performing feature enhancement processing to obtain a second head stereoscopic image. In this embodiment, the step 1022 performs the feature enhancement processing, specifically: after the resolution amplification treatment is carried out on the first initial image, determining the amplification factor according to the number of grids generated after the resolution amplification treatment is carried out on the grids of the original mark; according to the magnification, performing resolution magnification processing on a hindbrain region in the second initial image through a nearest neighbor interpolation algorithm; and increasing the brightness value of the hindbrain region according to the brightness threshold, and performing 50% transparency reduction treatment on other regions except the hindbrain region in the second initial image to obtain a second head stereoscopic image.
Specifically, for the area with equal gradient of the hindbrain area, as the calvaria bone and the calvaria bone are gentle, the hindbrain area is amplified by the same multiple by utilizing the nearest neighbor interpolation algorithm, so that the position alignment in the subsequent image fusion is facilitated. The nearest neighbor interpolation algorithm replaces the enlarged blank grid by the adjacent pixel value, and is convenient for the gradient areas such as the hindbrain area. Then, after the brightness reduction process, the transparency reduction process is performed on the other regions than the hindbrain region, and the characteristics of the hindbrain region can be increased.
Step 103, extracting a facial skull region in the first head stereo image to obtain a facial skull spectrum image; and extracting the skull region in the second head stereo image to obtain a skull spectrum image. In the present embodiment, step 103 includes step 1031 and step 1032.
The step 1031 of extracting the facial skull region in the first head stereo image to obtain a facial skull spectrum image specifically includes: identifying skull features in the first head stereo image, extracting maxillary, nasal, lacrimal, zygomatic, lower turbinate, plow and mandibular regions; performing secondary extraction on the region between the maxilla and the mandible to form an oral region; secondly extracting the area between the lacrimal bones and the zygomatic bones to form an orbit area; and, performing secondary extraction on the area between the nasal bone, the lower turbinate bone and the plow bone to form a nasal cavity area; and extracting the area images corresponding to the oral cavity area, the eye socket area and the nasal cavity area to form facial skull spectrum images.
Step 1032 is a step of extracting a skull region in the second head stereo image to obtain a skull spectrum image, and specifically includes: identifying the skull features in the second head stereo image, and extracting frontal bone, parietal bone, temporal bone, ethmoid bone, sphenoid bone and occipital bone regions; performing secondary extraction on the area among the frontal bone, the parietal bone and the temporal bone to form a calvarial bone area; and performing secondary extraction on the region among the sieve bones, the sphenoid bones and the occipital bones to form a skull base bone region; and extracting the regional images corresponding to the calvaria bone region and the calvaria bone region to form a brain skull spectrum image.
Specifically, the skull is composed of 23 irregular bones, including 15 pieces of facial skull and 8 pieces of cerebral skull. The skull encloses the eye orbit, nasal cavity and oral cavity, and the left and right parts include maxilla, nasal bone, lacrimal bone, cheekbone, palate bone, lower turbinate bone, plow bone, mandible bone and free lingual bone. In near infrared spectrum data, in order to highlight the characteristics of the front face of the head and improve the data processing efficiency at the same time, the maxilla, the nasal bone, the lacrimal bone, the zygomatic bone, the inferior turbinate, the plow bone and the mandible are extracted and processed. The skull consists of calvaria bone and skull base bone, the calvaria bone comprises frontal bone, parietal bone, occipital bone, temporal bone and partial cheekbone and sphenoid bone large wings which are connected together through coronal suture, sagittal suture, herringbone suture and squamous suture; the skull base bone comprises a sieve bone, a sphenoid bone and an occipital bone, and forms a structure of a front fossa, a middle fossa and a rear fossa together. In near infrared spectrum data, in order to highlight the characteristics of the head hindbrain and improve the data processing efficiency, frontal bone, parietal bone, temporal bone, ethmoid bone, sphenoid bone and occipital bone regions with obvious characteristic points are extracted and processed.
Step 104, determining position reference data between the facial skull region and the cerebral skull region according to the spatial distance between the facial skull region and the cerebral skull region at the head of the target person.
In this embodiment, the step 104 specifically includes: steps 1041 to 1044. Step 1041, respectively establishing a three-dimensional space coordinate system in the first head stereo image and the second head stereo image; step 1042, determining coordinate positions of maxilla, nasal bone, lacrimal bone, zygomatic bone, lower turbinate, plow bone and mandible in a three-dimensional space coordinate system in the area of the facial skull, and calculating the space distance between every two to form a first distance sequence; step 1043, determining coordinate positions of frontal bone, parietal bone, temporal bone, ethmoid bone, sphenoid bone and occipital bone in the three-dimensional space coordinate system, and calculating the space distance between every two to form a second distance sequence; step 1044, determining spatial distances of the skull surface region and the skull surface region at different positions according to the first distance sequence and the second distance sequence, and obtaining position reference data.
Specifically, in order to realize the subsequent image fusion, a position reference needs to be established first, and the fusion is performed through the position reference. Firstly, the skull features in the skull region are formed into a sequence, and the distribution condition of various skull bones in a three-dimensional space coordinate system is utilized to establish the sequence through the space distance between the skull bones, namely a first distance sequence. A sequence is then formed for the skull features in the skull region, i.e. a second distance sequence. Finally, the spatial distance between each skull feature in the first distance sequence and the second distance sequence needs to be determined, and the mutual position relation of the skull region and the skull region in the head of the target person is determined through the position reference data.
And 105, according to the position reference data, taking the facial skull spectral image as a bottom layer and the cerebral skull spectral image as a top layer, and fusing the facial skull spectral image and the cerebral skull spectral image to obtain a target character head image.
In this embodiment, the step 105 specifically includes: steps 1051 through 1053. Step 1051, determining a reference position area according to the position reference data; wherein the reference location area includes any one or more of a maxilla, a nasal bone, a lacrimal bone, a zygomatic bone, a lower turbinate, a plow bone, or a mandible; including any one or more of frontal bone, parietal bone, temporal bone, ethmoid bone, sphenoid bone, or occipital bone; step 1052, taking the facial skull spectrum image as a bottom layer, taking the cerebral skull spectrum image as a top layer, selecting a reference position area in the facial skull spectrum image as a first alignment point, and simultaneously, selecting the reference position area in the cerebral skull spectrum image as a second alignment point; and 1053, aligning and combining the facial skull spectrum image and the cerebral skull spectrum image according to the first alignment point and the second alignment point to obtain a target person head image.
Specifically, after the mutual position relationship between the facial skull region and the brain skull region in the head of the target person is determined through the step 104, since the facial skull region features are obvious and the brain skull region features are gentle, the image fusion is realized by taking the brain skull spectral image as the bottom layer and the brain skull spectral image as the top layer according to the facial skull spectral image. In the fusion process, one or more datum points are respectively determined in the facial skull region and the cerebral skull region, and then the merging can be completed after the alignment by using the position datum data, so that the accurate and complete head image of the target person is obtained.
And 106, extracting three-dimensional data of the head of the target person according to the head image of the target person, and establishing a head model of the target person according to the three-dimensional data.
In this embodiment, the step 106 specifically includes: step 1061 and step 1062. Step 1061, extracting three-dimensional coordinate parameters of the skull from the coordinate positions of the maxilla, nasal bone, lacrimal bone, zygomatic bone, lower turbinate, plow bone, mandible, frontal bone, parietal bone, temporal bone, sieve bone, sphenoid bone and occipital bone of the head image of the target person in a three-dimensional space coordinate system; step 1062, constructing an initial head model, inputting the three-dimensional coordinate parameters of the skull into the initial head model, and generating a target character head model.
Specifically, as shown in fig. 2, after obtaining a precise and complete target person head image, the required parameters established for the complete head model can be obtained for the skull three-dimensional coordinate parameters of the maxilla, nasal bone, lacrimal bone, zygomatic bone, lower turbinate, plow bone, mandible, frontal bone, parietal bone, temporal bone, ethmoid bone, sphenoid bone and occipital bone of the person head, thereby constructing the head model corresponding to the target person.
According to the technical scheme, near infrared spectrum data with the wavelength of 1000-1100nm is extracted to serve as a facial skull region imaging data source of the head of the target person, and the characteristic of severe short wave fluctuation is utilized to accurately identify the eye socket region, the nasal cavity region, the oral cavity region and other gully regions in the facial skull region of the person; near infrared spectrum data with the wavelength of 1800-2200nm is extracted to serve as a brain skull region imaging data source of the head of the target person, and gradient regions such as a hindbrain region in the brain skull region of the person can be accurately identified by utilizing the characteristic of gentle fluctuation of long waves, so that accurate head data of the person can be obtained; then, after the images formed by the two data are fused, an accurate head model can be constructed.
Example two
Referring to fig. 3, a schematic structural diagram of a head model building system based on near infrared spectrum imaging according to another embodiment of the present invention includes: the system comprises a data extraction module, an image generation module, a region extraction module, a position reference module, an image fusion module and a model establishment module.
The data extraction module is used for obtaining near infrared spectrum data of the head of the target person, extracting near infrared spectrum data corresponding to the spectrum wavelength of 1000-1100nm in the near infrared spectrum data to obtain first spectrum data, and extracting near infrared spectrum data corresponding to the spectrum wavelength of 1800-2200nm to obtain second spectrum data.
The image generation module is used for generating a first head stereoscopic image and a second head stereoscopic image of the head of the target person according to the first spectrum data and the second spectrum data respectively. In this embodiment, the image generation module includes a first generation unit and a second generation unit.
The first generating unit is used for generating a first initial image of the head of the target person according to the first spectrum data, identifying and performing feature amplification processing on an eye socket area, a nasal cavity area and an oral cavity area of the head of the target person in the first initial image, and obtaining a first head stereoscopic image. In this embodiment, the process of the first generating unit for performing the feature amplification processing specifically includes: gridding an orbit area, a nasal cavity area and an oral cavity area in the first initial image, and marking each grid; performing resolution amplification processing on the orbit region, the nasal cavity region and the oral cavity region in the first initial image by a bicubic interpolation algorithm; and setting a brightness threshold value, and reducing brightness of other areas except for an eye socket area, a nasal cavity area and an oral cavity area in the first initial image to obtain a first head stereo image.
The second generating unit is configured to generate a second initial image of the head of the target person according to the second spectrum data, identify a hindbrain region of the head of the target person in the second initial image, and perform feature enhancement processing to obtain a second head stereoscopic image. In this embodiment, the second generating unit is configured to perform a feature enhancement processing, specifically: after the resolution amplification treatment is carried out on the first initial image, determining the amplification factor according to the number of grids generated after the resolution amplification treatment is carried out on the grids of the original mark; according to the magnification, performing resolution magnification processing on a hindbrain region in the second initial image through a nearest neighbor interpolation algorithm; and increasing the brightness value of the hindbrain region according to the brightness threshold, and performing 50% transparency reduction treatment on other regions except the hindbrain region in the second initial image to obtain a second head stereoscopic image.
The region extraction module is used for extracting the facial skull region in the first head stereo image to obtain a facial skull spectrum image; and extracting the skull region in the second head stereo image to obtain a skull spectrum image.
In a first aspect of this embodiment, the region extraction module is configured to extract a facial skull region in the first head stereo image, and the step of obtaining a facial skull spectral image specifically includes: identifying skull features in the first head stereo image, extracting maxillary, nasal, lacrimal, zygomatic, lower turbinate, plow and mandibular regions; performing secondary extraction on the region between the maxilla and the mandible to form an oral region; secondly extracting the area between the lacrimal bones and the zygomatic bones to form an orbit area; and, performing secondary extraction on the area between the nasal bone, the lower turbinate bone and the plow bone to form a nasal cavity area; and extracting the area images corresponding to the oral cavity area, the eye socket area and the nasal cavity area to form facial skull spectrum images.
In a second aspect of this embodiment, the region extraction module is configured to extract a skull region in the second head stereo image, and the step of obtaining a skull spectral image specifically includes: identifying the skull features in the second head stereo image, and extracting frontal bone, parietal bone, temporal bone, ethmoid bone, sphenoid bone and occipital bone regions; performing secondary extraction on the area among the frontal bone, the parietal bone and the temporal bone to form a calvarial bone area; and performing secondary extraction on the region among the sieve bones, the sphenoid bones and the occipital bones to form a skull base bone region; and extracting the regional images corresponding to the calvaria bone region and the calvaria bone region to form a brain skull spectrum image.
The position reference module is used for determining position reference data between the facial skull region and the cerebral skull region according to the spatial distance between the facial skull region and the cerebral skull region at the head of the target person.
In this embodiment, the location reference module is specifically configured to: respectively establishing a three-dimensional space coordinate system in the first head stereo image and the second head stereo image; determining coordinate positions of maxilla, nasal bone, lacrimal bone, zygomatic bone, lower turbinate, plow-shaped bone and mandible in a three-dimensional space coordinate system in a facial skull region, and calculating space distances between every two to form a first distance sequence; determining coordinate positions of frontal bone, parietal bone, temporal bone, sieve bone, sphenoid bone and occipital bone in a three-dimensional space coordinate system of a brain skull region, and calculating space distances between every two to form a second distance sequence; and determining the spatial distances of the facial skull region and the cerebral skull region at different positions according to the first distance sequence and the second distance sequence, and obtaining position reference data.
The image fusion module is used for fusing the facial skull spectral image and the cerebral skull spectral image to obtain a target character head image by taking the facial skull spectral image as a bottom layer and taking the cerebral skull spectral image as a top layer according to the position reference data.
In this embodiment, the image fusion module is specifically configured to: determining a reference position area according to the position reference data; wherein the reference location area includes any one or more of a maxilla, a nasal bone, a lacrimal bone, a zygomatic bone, a lower turbinate, a plow bone, or a mandible; including any one or more of frontal bone, parietal bone, temporal bone, ethmoid bone, sphenoid bone, or occipital bone; taking the facial skull spectrum image as a bottom layer, taking the cerebral skull spectrum image as a top layer, selecting a reference position area in the facial skull spectrum image as a first alignment point, and simultaneously selecting the reference position area in the cerebral skull spectrum image as a second alignment point; and aligning and combining the facial skull spectrum image and the cerebral skull spectrum image according to the first alignment point and the second alignment point to obtain a head image of the target person.
The model building module is used for extracting three-dimensional data of the head of the target person according to the head image of the target person and building a head model of the target person according to the three-dimensional data.
In this embodiment, the model building module is specifically configured to: extracting three-dimensional coordinate parameters of the skull from the coordinate positions of the maxilla, the nasal bone, the lacrimal bone, the zygomatic bone, the lower turbinate, the plow bone, the mandible, the frontal bone, the parietal bone, the temporal bone, the ethmoid bone, the sphenoid bone and the occipital bone of the head image of the target person in a three-dimensional space coordinate system; and constructing an initial head model, inputting the three-dimensional coordinate parameters of the skull into the initial head model, and generating a target character head model.
Example III
The embodiment of the invention also provides a computer readable storage medium, which comprises a stored computer program; the computer program controls the device where the computer readable storage medium is located to execute the method for constructing the head model based on near infrared spectrum imaging according to any one of the above embodiments when running.
Example IV
Referring to fig. 4, a schematic structural diagram of an embodiment of a terminal device according to an embodiment of the present invention is provided, where the terminal device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor implements the near infrared spectrum imaging-based head model building method according to any one of the foregoing embodiments when executing the computer program.
Preferably, the computer program may be divided into one or more modules/units (e.g., computer program) stored in the memory and executed by the processor to perform the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing the specified functions, which instruction segments are used for describing the execution of the computer program in the terminal device.
The processor may be a central processing unit (Central Processing Unit, CPU), or may be other general purpose processor, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc., or the general purpose processor may be a microprocessor, or any conventional processor, which is the control center of the terminal device, that connects the various parts of the terminal device using various interfaces and lines.
The memory mainly includes a program storage area, which may store an operating system, an application program required for at least one function, and the like, and a data storage area, which may store related data and the like. In addition, the memory may be a high-speed random access memory, a nonvolatile memory such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card), or the like, or may be other volatile solid-state memory devices.
It should be noted that the above-mentioned terminal device may include, but is not limited to, a processor, a memory, and those skilled in the art will understand that the above-mentioned terminal device is merely an example, and does not constitute limitation of the terminal device, and may include more or fewer components, or may combine some components, or different components.
The foregoing embodiments have been provided for the purpose of illustrating the general principles of the present invention, and are not to be construed as limiting the scope of the invention. It should be noted that any modifications, equivalent substitutions, improvements, etc. made by those skilled in the art without departing from the spirit and principles of the present invention are intended to be included in the scope of the present invention.
Claims (10)
1. The method for constructing the head model based on near infrared spectrum imaging is characterized by comprising the following steps of:
acquiring near infrared spectrum data of the head of a target person, extracting near infrared spectrum data corresponding to the spectrum wavelength of 1000-1100nm in the near infrared spectrum data to obtain first spectrum data, and extracting near infrared spectrum data corresponding to the spectrum wavelength of 1800-2200nm to obtain second spectrum data;
Generating a first head stereoscopic image and a second head stereoscopic image of the head of the target person according to the first spectral data and the second spectral data, respectively;
extracting a facial skull region in the first head stereo image to obtain a facial skull spectrum image; extracting a brain skull region in the second head three-dimensional image to obtain a brain skull spectrum image;
determining position reference data between the facial skull region and the cerebral skull region according to the spatial distance between the facial skull region and the cerebral skull region at the head of the target person;
according to the position reference data, the facial skull spectral image is taken as a bottom layer, the cerebral skull spectral image is taken as a top layer, and the facial skull spectral image and the cerebral skull spectral image are fused to obtain a target character head image;
and extracting three-dimensional data of the head of the target person according to the head image of the target person, and establishing a head model of the target person according to the three-dimensional data.
2. The method for constructing a head model based on near infrared spectrum imaging according to claim 1, wherein the step of generating a first head stereoscopic image and a second head stereoscopic image of the head of the target person from the first spectrum data and the second spectrum data, respectively, specifically comprises:
Generating a first initial image of the head of the target person according to the first spectrum data, identifying an eye socket area, a nasal cavity area and an oral cavity area of the head of the target person in the first initial image, and performing characteristic amplification processing to obtain a first head three-dimensional image;
and generating a second initial image of the head of the target person according to the second spectrum data, identifying a hindbrain region of the head of the target person in the second initial image, and performing feature enhancement processing to obtain a second head stereoscopic image.
3. The method for constructing a head model based on near infrared spectrum imaging according to claim 2, wherein the process of performing the feature amplification process specifically comprises:
gridding an orbit area, a nasal cavity area and an oral cavity area in the first initial image, and marking each grid;
performing resolution amplification processing on the orbit region, the nasal cavity region and the oral cavity region in the first initial image by a bicubic interpolation algorithm;
and setting a brightness threshold value, and reducing brightness of other areas except for an eye socket area, a nasal cavity area and an oral cavity area in the first initial image to obtain a first head stereo image.
4. A method for constructing a head model based on near infrared spectrum imaging as claimed in claim 3, wherein the process of performing feature enhancement processing specifically comprises:
after the resolution amplification treatment is carried out on the first initial image, determining the amplification factor according to the number of grids generated after the resolution amplification treatment is carried out on the grids of the original mark;
according to the magnification, performing resolution magnification processing on a hindbrain region in the second initial image through a nearest neighbor interpolation algorithm;
and increasing the brightness value of the hindbrain region according to the brightness threshold, and performing 50% transparency reduction treatment on other regions except the hindbrain region in the second initial image to obtain a second head stereoscopic image.
5. The method for constructing a head model based on near infrared spectrum imaging according to claim 2, wherein the step of determining the position reference data between the skull region and the skull region according to the spatial distance between the skull region and the skull region at the head of the target person specifically comprises:
respectively establishing a three-dimensional space coordinate system in the first head stereo image and the second head stereo image;
Determining coordinate positions of maxilla, nasal bone, lacrimal bone, zygomatic bone, lower turbinate, plow-shaped bone and mandible in a three-dimensional space coordinate system in a facial skull region, and calculating space distances between every two to form a first distance sequence;
determining coordinate positions of frontal bone, parietal bone, temporal bone, sieve bone, sphenoid bone and occipital bone in a three-dimensional space coordinate system of a brain skull region, and calculating space distances between every two to form a second distance sequence;
and determining the spatial distances of the facial skull region and the cerebral skull region at different positions according to the first distance sequence and the second distance sequence, and obtaining position reference data.
6. The method for constructing a head model based on near infrared spectrum imaging as claimed in claim 5, wherein said step of fusing said facial skull spectral image and said cerebral skull spectral image with said facial skull spectral image as a bottom layer and said cerebral skull spectral image as a top layer according to said position reference data, comprises the steps of:
determining a reference position area according to the position reference data; wherein the reference location area includes any one or more of a maxilla, a nasal bone, a lacrimal bone, a zygomatic bone, a lower turbinate, a plow bone, or a mandible; including any one or more of frontal bone, parietal bone, temporal bone, ethmoid bone, sphenoid bone, or occipital bone;
Taking the facial skull spectrum image as a bottom layer, taking the cerebral skull spectrum image as a top layer, selecting a reference position area in the facial skull spectrum image as a first alignment point, and simultaneously selecting the reference position area in the cerebral skull spectrum image as a second alignment point;
and aligning and combining the facial skull spectrum image and the cerebral skull spectrum image according to the first alignment point and the second alignment point to obtain a head image of the target person.
7. The method for constructing a head model based on near infrared spectroscopy according to claim 6, wherein the step of extracting three-dimensional data of the head of the target person from the head image of the target person and constructing the head model of the target person from the three-dimensional data comprises:
extracting three-dimensional coordinate parameters of the skull from the coordinate positions of the maxilla, the nasal bone, the lacrimal bone, the zygomatic bone, the lower turbinate, the plow bone, the mandible, the frontal bone, the parietal bone, the temporal bone, the ethmoid bone, the sphenoid bone and the occipital bone of the head image of the target person in a three-dimensional space coordinate system;
and constructing an initial head model, inputting the three-dimensional coordinate parameters of the skull into the initial head model, and generating a target character head model.
8. A near infrared spectroscopy imaging-based head model building system, comprising: the device comprises a data extraction module, an image generation module, a region extraction module, a position reference module, an image fusion module and a model establishment module;
the data extraction module is used for obtaining near infrared spectrum data of the head of the target person, extracting near infrared spectrum data corresponding to the spectrum wavelength of 1000-1100nm in the near infrared spectrum data to obtain first spectrum data, and extracting near infrared spectrum data corresponding to the spectrum wavelength of 1800-2200nm to obtain second spectrum data;
the image generation module is used for generating a first head stereoscopic image and a second head stereoscopic image of the head of the target person according to the first spectrum data and the second spectrum data respectively;
the region extraction module is used for extracting the facial skull region in the first head stereo image to obtain a facial skull spectrum image; extracting a brain skull region in the second head three-dimensional image to obtain a brain skull spectrum image;
the position reference module is used for determining position reference data between the facial skull region and the cerebral skull region according to the spatial distance between the facial skull region and the cerebral skull region at the head of the target person;
The image fusion module is used for fusing the facial skull spectral image and the cerebral skull spectral image to obtain a head image of a target person according to the position reference data by taking the facial skull spectral image as a bottom layer and taking the cerebral skull spectral image as a top layer;
the model building module is used for extracting three-dimensional data of the head of the target person according to the head image of the target person and building a head model of the target person according to the three-dimensional data.
9. A computer readable storage medium, wherein the computer readable storage medium comprises a stored computer program; wherein the computer program, when run, controls a device in which the computer readable storage medium is located to perform the near infrared spectroscopy imaging based head model building method according to any one of claims 1-7.
10. A terminal device comprising a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the near infrared spectroscopy imaging-based head model construction method according to any one of claims 1-7 when the computer program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211504016.7A CN115797560B (en) | 2022-11-28 | 2022-11-28 | Near infrared spectrum imaging-based head model construction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211504016.7A CN115797560B (en) | 2022-11-28 | 2022-11-28 | Near infrared spectrum imaging-based head model construction method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115797560A CN115797560A (en) | 2023-03-14 |
| CN115797560B true CN115797560B (en) | 2023-07-25 |
Family
ID=85442388
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211504016.7A Active CN115797560B (en) | 2022-11-28 | 2022-11-28 | Near infrared spectrum imaging-based head model construction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115797560B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103353443A (en) * | 2013-06-18 | 2013-10-16 | 西北农林科技大学 | Near infrared spectrum based discrimination method for Zhongning fructus lycii |
| JP2014110844A (en) * | 2012-12-05 | 2014-06-19 | Shimadzu Corp | Biomedical measurement device, and position measuring device for use in the same |
| FR3015710A1 (en) * | 2013-12-20 | 2015-06-26 | Inst Nat Rech Inf Automat | DATA DISPLAY SYSTEM CHARACTERIZING THE BRAIN ACTIVITY OF AN INDIVIDUAL, ASSOCIATED METHOD AND COMPUTER PROGRAM |
| CN106780591A (en) * | 2016-11-21 | 2017-05-31 | 北京师范大学 | A kind of craniofacial shape analysis and Facial restoration method based on the dense corresponding points cloud in cranium face |
| CN107478598A (en) * | 2017-09-01 | 2017-12-15 | 广东省智能制造研究所 | A kind of near-infrared spectral analytical method based on one-dimensional convolutional neural networks |
| CN108416277A (en) * | 2018-02-11 | 2018-08-17 | 广州市碳码科技有限责任公司 | A kind of cardioelectric monitor method, apparatus, terminal and computer readable storage medium |
| CN109496338A (en) * | 2017-12-05 | 2019-03-19 | 北京师范大学 | Based on personal feature through cranium brain map generation method, air navigation aid and its system |
| CN209133055U (en) * | 2018-08-13 | 2019-07-19 | 中国医学科学院基础医学研究所 | Skull and brain model |
| CN110046551A (en) * | 2019-03-18 | 2019-07-23 | 中国科学院深圳先进技术研究院 | A kind of generation method and equipment of human face recognition model |
| CN110811551A (en) * | 2019-10-16 | 2020-02-21 | 杨扬 | Oral cavity analysis system and method based on near infrared spectrum |
| CN111879724A (en) * | 2020-08-05 | 2020-11-03 | 中国工程物理研究院流体物理研究所 | Human skin mask identification method and system based on near infrared spectrum imaging |
| CN112184898A (en) * | 2020-10-21 | 2021-01-05 | 安徽动感智能科技有限公司 | Digital human body modeling method based on motion recognition |
| CN114569076A (en) * | 2022-03-01 | 2022-06-03 | 丹阳慧创医疗设备有限公司 | Positioning method, device and storage medium for near-infrared brain function imaging device |
| WO2022167801A1 (en) * | 2021-02-04 | 2022-08-11 | Cortirio Limited | Near-infrared imaging system for identifying a target feature in an object |
| CN115100217A (en) * | 2022-05-07 | 2022-09-23 | 清华大学 | Method, device, equipment and medium for extracting brain region in head and neck CT (computed tomography) image |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102020125422A1 (en) * | 2020-09-29 | 2022-03-31 | Claas Selbstfahrende Erntemaschinen Gmbh | NIR sensor calibration method |
-
2022
- 2022-11-28 CN CN202211504016.7A patent/CN115797560B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014110844A (en) * | 2012-12-05 | 2014-06-19 | Shimadzu Corp | Biomedical measurement device, and position measuring device for use in the same |
| CN103353443A (en) * | 2013-06-18 | 2013-10-16 | 西北农林科技大学 | Near infrared spectrum based discrimination method for Zhongning fructus lycii |
| FR3015710A1 (en) * | 2013-12-20 | 2015-06-26 | Inst Nat Rech Inf Automat | DATA DISPLAY SYSTEM CHARACTERIZING THE BRAIN ACTIVITY OF AN INDIVIDUAL, ASSOCIATED METHOD AND COMPUTER PROGRAM |
| CN106780591A (en) * | 2016-11-21 | 2017-05-31 | 北京师范大学 | A kind of craniofacial shape analysis and Facial restoration method based on the dense corresponding points cloud in cranium face |
| CN107478598A (en) * | 2017-09-01 | 2017-12-15 | 广东省智能制造研究所 | A kind of near-infrared spectral analytical method based on one-dimensional convolutional neural networks |
| CN109496338A (en) * | 2017-12-05 | 2019-03-19 | 北京师范大学 | Based on personal feature through cranium brain map generation method, air navigation aid and its system |
| CN108416277A (en) * | 2018-02-11 | 2018-08-17 | 广州市碳码科技有限责任公司 | A kind of cardioelectric monitor method, apparatus, terminal and computer readable storage medium |
| CN209133055U (en) * | 2018-08-13 | 2019-07-19 | 中国医学科学院基础医学研究所 | Skull and brain model |
| CN110046551A (en) * | 2019-03-18 | 2019-07-23 | 中国科学院深圳先进技术研究院 | A kind of generation method and equipment of human face recognition model |
| CN110811551A (en) * | 2019-10-16 | 2020-02-21 | 杨扬 | Oral cavity analysis system and method based on near infrared spectrum |
| CN111879724A (en) * | 2020-08-05 | 2020-11-03 | 中国工程物理研究院流体物理研究所 | Human skin mask identification method and system based on near infrared spectrum imaging |
| CN112184898A (en) * | 2020-10-21 | 2021-01-05 | 安徽动感智能科技有限公司 | Digital human body modeling method based on motion recognition |
| WO2022167801A1 (en) * | 2021-02-04 | 2022-08-11 | Cortirio Limited | Near-infrared imaging system for identifying a target feature in an object |
| CN114569076A (en) * | 2022-03-01 | 2022-06-03 | 丹阳慧创医疗设备有限公司 | Positioning method, device and storage medium for near-infrared brain function imaging device |
| CN115100217A (en) * | 2022-05-07 | 2022-09-23 | 清华大学 | Method, device, equipment and medium for extracting brain region in head and neck CT (computed tomography) image |
Non-Patent Citations (4)
| Title |
|---|
| "Measurement of the optical properties of a two-layer model of the human head using broadband near-infrared spectroscopy";Olivia Pucci .etc;《APPLIED OPTICS》;第49卷(第32期);6324-6332 * |
| "一种基于近红外光谱成像的可穿戴式设备的设计";陈娇;《中国医疗设备》;第33卷(第12期);46-49、69 * |
| "基于近红外光谱建立PE、PP和PET的识别分类模型";张毅民 等;《现代化工》;第36卷(第3期);182-186 * |
| Sergii Golovynskyi .etc."Optical windows for head tissues in near-infrared and short-wave infrared regions: Approaching transcranial light applications".《JOURNAL OF BIOPHOTONICS》.2018,第11卷(第12期),1-12. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115797560A (en) | 2023-03-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4748199B2 (en) | Vein imaging apparatus and vein imaging method | |
| US8111878B2 (en) | Vein authentication device and vein authentication method | |
| WO2021036314A1 (en) | Facial image processing method and apparatus, image device, and storage medium | |
| Wu et al. | Two-stage mesh deep learning for automated tooth segmentation and landmark localization on 3D intraoral scans | |
| JP2010267086A (en) | Vein imaging apparatus, displacement interpolation method, and program | |
| CN106887039A (en) | The three-D imaging method and system of a kind of organ and focus based on medical image | |
| DE112009000099T5 (en) | Image signatures for use in a motion-based three-dimensional reconstruction | |
| JP6630455B2 (en) | Asymmetry reduction method | |
| Ambeth Kumar et al. | Exploration of an innovative geometric parameter based on performance enhancement for foot print recognition | |
| Heinrich et al. | Automatic human identification based on dental X-ray radiographs using computer vision | |
| KR102461343B1 (en) | Automatic tooth landmark detection method and system in medical images containing metal artifacts | |
| Nowinski et al. | Three-dimensional stereotactic atlas of the adult human skull correlated with the brain, cranial nerves, and intracranial vasculature | |
| EP4191528A1 (en) | Methods and systems for image registration | |
| CN111540008A (en) | Positioning method, device, system, electronic equipment and storage medium | |
| Pojda et al. | Integration and application of multimodal measurement techniques: relevance of photogrammetry to orthodontics | |
| CN115830675A (en) | Method and device for tracking fixation point, intelligent glasses and storage medium | |
| CN115797560B (en) | Near infrared spectrum imaging-based head model construction method and system | |
| Liu et al. | An Improved Hybrid Network With a Transformer Module for Medical Image Fusion | |
| Andrews et al. | Validation of three-dimensional facial imaging captured with smartphone-based photogrammetry application in comparison to stereophotogrammetry system | |
| Zadnik et al. | Image acquisition device for smart-city access control applications based on iris recognition | |
| JP5056662B2 (en) | Subcutaneous pattern acquisition device, subcutaneous pattern acquisition method, and structure template | |
| JP2010087795A (en) | Vein imaging apparatus and thumbnail image creation method | |
| Lacher et al. | Low-cost surface reconstruction for aesthetic results assessment and prediction in breast cancer surgery | |
| ES2943287T3 (en) | Method of verifying the identity of a user by identifying an object within an image that has a biometric characteristic of the user and separating a portion of the image comprising the biometric characteristic from other portions of the image | |
| Hori et al. | A novel identification method using perceptual degree of concordance of occlusal surfaces calculated by a Python program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |