CN112287726B - Infrared sample image acquisition method and device - Google Patents
Infrared sample image acquisition method and device Download PDFInfo
- Publication number
- CN112287726B CN112287726B CN201910669497.9A CN201910669497A CN112287726B CN 112287726 B CN112287726 B CN 112287726B CN 201910669497 A CN201910669497 A CN 201910669497A CN 112287726 B CN112287726 B CN 112287726B
- Authority
- CN
- China
- Prior art keywords
- age
- image
- target
- images
- neural network
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/143—Sensing or illuminating at different wavelengths
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/178—Human faces, e.g. facial parts, sketches or expressions estimating age from face image; using age information for improving recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses an infrared sample image acquisition method and device. The method comprises the following steps: acquiring a plurality of image sets, wherein the initial infrared image in each image set is different face images of the same person in the same period; constructing each target image containing each target face area aiming at each image set; inputting each target image into a convolutional neural network model obtained by pre-training to obtain the age range of the person corresponding to each target face area; and removing the target images with abnormal age ranges in the image set to obtain residual target images, calculating the normal age ranges corresponding to all the residual target images, taking the residual target images contained in the normal age ranges as sample images, and taking the average value of the age ranges corresponding to the sample images as the age labeling result of the sample images. By applying the scheme provided by the embodiment of the invention, the age of the face in the infrared image can be predicted.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to an infrared sample image acquisition method and device.
Background
At present, a convolutional neural network method is mainly adopted for age prediction based on a monitored image. Specifically, a convolutional neural network model needs to be trained through a sample image and an accurate age labeling result, and then the age of the face in the image to be predicted can be predicted based on the trained convolutional neural network model.
However, the conventional age-labeled image set is a color image set, and a convolutional neural network model trained based on the image set can only predict the age of a human face in the color image. For infrared images, due to the lack of age-labeled data sets, a convolutional neural network model for predicting the age of a human face in the infrared images cannot be trained. Therefore, an infrared sample image acquisition method is urgently needed to predict the age of the human face in the infrared image.
Disclosure of Invention
The invention provides an infrared sample image acquisition method and device, which are used for carrying out age prediction on a human face in an infrared image. The specific technical scheme is as follows.
In a first aspect, an embodiment of the present invention provides an infrared sample image obtaining method, including:
acquiring a plurality of image sets, wherein the initial infrared images in each image set are different face images of the same person in the same period, and the number of the initial infrared images in each sample image set is greater than a preset number threshold;
detecting target face regions in each initial infrared image aiming at each image set, and constructing each target image containing each target face region; the size of each target image is a preset size;
inputting each target image into a convolutional neural network model obtained by pre-training to obtain the predicted age distribution of the person corresponding to each target face area, and determining the age range corresponding to each predicted age distribution; the convolutional neural network model is obtained by adjusting parameters in the initial convolutional neural network model to obtain a candidate neural network model and adjusting the candidate neural network model according to the difference value of the age distribution corresponding to each sample image output by the initial convolutional neural network model and the Gaussian distribution generated by the corresponding age labeling result and the difference value of the expected value of the age distribution corresponding to each sample image and the corresponding age labeling result after each sample image is input into the initial convolutional neural network model, wherein the predicted age distribution and the age distribution obey the Gaussian distribution, and each sample image is a color image;
and removing the target images with abnormal age ranges in the image set to obtain residual target images, calculating the normal age ranges corresponding to all the residual target images, taking the residual target images contained in the normal age ranges as sample images, and taking the average value of the age ranges corresponding to the sample images as the age labeling result of the sample images.
Optionally, for each image set, removing the target image with the abnormal age range in the image set to obtain the remaining target images includes:
for each image set, sequencing the target images according to the sequence of the minimum value of the age range corresponding to the target images in the image set from small to large;
determining a first age range located one quarter and a second age range located three quarters, and a minimum value of the first age range and a maximum value of the second age range;
and removing the target image with the age value smaller than the difference between the minimum value and the preset value and the target image with the age value larger than the sum of the maximum value and the preset value in the corresponding age range to obtain the residual target image.
Optionally, the calculating the normal age range corresponding to all the remaining target images includes:
calculating the mean value and the standard deviation of the age range corresponding to all the residual target images;
acquiring a preset hyper-parameter;
and calculating the product of the hyperparameter and the standard deviation, taking the difference between the mean value and the product as the minimum value of the normal age range, and taking the sum of the mean value and the product as the maximum value of the normal age range.
Optionally, the training process of the convolutional neural network model includes:
constructing an initial convolutional neural network model, wherein the initial convolutional neural network model comprises: a convolution layer, a pooling layer, a full-link layer;
acquiring each sample image and an age labeling result corresponding to each sample image; all the sample images are color images;
generating Gaussian distribution of age labeling results corresponding to the sample images;
inputting each sample image into the initial convolutional neural network model to obtain age distribution corresponding to each sample image, calculating a difference value of the age distribution corresponding to each sample image and Gaussian distribution generated by a corresponding age labeling result, and a difference value of an expected value of the age distribution corresponding to each sample image and a corresponding age labeling result, adjusting each parameter in the initial convolutional neural network model according to the calculation result to obtain a candidate neural network model, and adjusting the candidate neural network model to obtain the convolutional neural network model.
Optionally, the generating a gaussian distribution of the age labeling result corresponding to each sample image includes:
and constructing a Gaussian distribution taking the age labeling result corresponding to the sample image as the center and the preset standard deviation as the peak width as the Gaussian distribution of the age labeling result corresponding to the sample image for each sample image.
Optionally, after obtaining the convolutional neural network model, the method further includes:
acquiring test images and age labeling results corresponding to the test images;
determining the testing precision of the convolutional neural network model according to the testing images and age labeling results corresponding to the testing images;
and when the test precision is smaller than a preset precision threshold value, taking the current convolutional neural network model as an initial convolutional neural network model, returning to the step of acquiring each sample image and the age labeling result corresponding to each sample image, and taking the current convolutional neural network model as a final convolutional neural network model when the test precision is not smaller than the preset precision threshold value.
Optionally, the constructing each target image including each target face region includes:
performing key point detection on each target face area to obtain coordinate information of each target key point of each target face area; wherein, each target key point is a point for identifying the human face contour feature;
and according to the coordinate information of each target key point of each target face region, aligning each target face region to obtain each target image which comprises each target face region and is located at a preset position.
In a second aspect, an embodiment of the present invention provides an infrared sample image acquiring apparatus, including:
the system comprises an image set acquisition module, a comparison module and a comparison module, wherein the image set acquisition module is used for acquiring a plurality of image sets, initial infrared images in each image set are different face images of the same person in the same period, and the number of the initial infrared images in each sample image set is greater than a preset number threshold;
the face region detection module is used for detecting a target face region in each initial infrared image aiming at each image set and constructing each target image containing each target face region; the size of each target image is a preset size;
the age range determining module is used for inputting each target image into a convolutional neural network model obtained by pre-training to obtain the predicted age distribution of the person corresponding to each target face area and determining the age range corresponding to each predicted age distribution; the method comprises the steps that after an initial convolutional neural network model is input into each sample image, the convolutional neural network model adjusts each parameter in the initial convolutional neural network model to obtain a candidate neural network model according to the difference value of the age distribution corresponding to each sample image output by the initial convolutional neural network model and the Gaussian distribution generated by the corresponding age labeling result and the difference value of the expected value of the age distribution corresponding to each sample image and the corresponding age labeling result, and the candidate neural network model is adjusted to obtain the convolutional neural network model, wherein the predicted age distribution and the age distribution are both subjected to Gaussian distribution, and each sample image is a color image;
and the infrared sample determining module is used for removing the target images with abnormal age ranges in the image set aiming at each image set to obtain the residual target images, calculating the normal age ranges corresponding to all the residual target images, taking the residual target images contained in the normal age ranges as sample images, and taking the mean value of the age ranges corresponding to the sample images as the age labeling result of the sample images.
Optionally, the infrared sample determination module includes:
the image sorting submodule is used for sorting the target images according to the sequence from small to large of the minimum value of the age range corresponding to the target images in each image set;
a value determination submodule for determining a first age range located at one quarter and a second age range located at three quarters, and a minimum value of the first age range and a maximum value of the second age range;
and the image determining submodule is used for removing the target image which comprises an age value smaller than the difference between the minimum value and a preset value and the target image which comprises an age value larger than the sum of the maximum value and the preset value in the corresponding age range to obtain the residual target image.
Optionally, the infrared sample determination module includes:
the numerical value calculation submodule is used for calculating the mean value and the standard deviation of the age range corresponding to all the residual target images;
the parameter acquisition sub-module is used for acquiring a preset hyper-parameter;
and the range determination submodule is used for calculating the product of the hyperparameter and the standard deviation, taking the difference between the mean value and the product as the minimum value of the normal age range, and taking the sum of the mean value and the product as the maximum value of the normal age range.
Optionally, the apparatus further comprises:
a network model construction module for constructing an initial convolutional neural network model, the initial convolutional neural network model comprising: a convolution layer, a pooling layer, and a full-link layer;
the system comprises a sample image acquisition module, a storage module and a display module, wherein the sample image acquisition module is used for acquiring each sample image and an age labeling result corresponding to each sample image; all the sample images are color images;
the Gaussian distribution generating module is used for generating Gaussian distribution of the age labeling result corresponding to each sample image;
and the network model training module is used for inputting each sample image into the initial convolutional neural network model to obtain the age distribution corresponding to each sample image, calculating the difference value of the age distribution corresponding to each sample image and the Gaussian distribution generated by the corresponding age labeling result, and calculating the difference value of the expected value of the age distribution corresponding to each sample image and the corresponding age labeling result, adjusting each parameter in the initial convolutional neural network model according to the calculation result to obtain a candidate neural network model, and adjusting the candidate neural network model to obtain the convolutional neural network model.
Optionally, the gaussian distribution generating module is specifically configured to:
and constructing a Gaussian distribution taking the age labeling result corresponding to the sample image as the center and the preset standard deviation as the peak width as the Gaussian distribution of the age labeling result corresponding to the sample image for each sample image.
Optionally, the apparatus further comprises:
the test image acquisition module is used for acquiring test images and age labeling results corresponding to the test images;
the test precision determining module is used for determining the test precision of the convolutional neural network model according to the test images and age labeling results corresponding to the test images;
and the processing module is used for taking the current convolutional neural network model as an initial convolutional neural network model when the test precision is smaller than a preset precision threshold value, triggering the sample image acquisition module, and taking the current convolutional neural network model as a final convolutional neural network model when the test precision is not smaller than the preset precision threshold value.
Optionally, the face region detection module includes:
the key point detection submodule is used for carrying out key point detection on each target face area to obtain the coordinate information of each target key point of each target face area; wherein, each target key point is a point for identifying the human face contour feature;
and the target image construction submodule is used for aligning each target face region according to the coordinate information of each target key point of each target face region to obtain each target image which comprises each target face region and is positioned at a preset position.
As can be seen from the above, the method and the device for acquiring an infrared sample image according to the embodiments of the present invention can acquire a plurality of image sets, where an initial infrared image in each image set is a different face image of a same person in a same period, and the number of the initial infrared images in each sample image set is greater than a preset number threshold; detecting target face regions in each initial infrared image aiming at each image set, and constructing each target image containing each target face region; the size of each target image is a preset size; inputting each target image into a convolutional neural network model obtained by pre-training to obtain the predicted age distribution of the person corresponding to each target face area, and determining the age range corresponding to each predicted age distribution; the convolutional neural network model is obtained by adjusting parameters in the initial convolutional neural network model to obtain a candidate neural network model and adjusting the candidate neural network model according to the difference value of the age distribution corresponding to each sample image output by the initial convolutional neural network model and the Gaussian distribution generated by the corresponding age labeling result and the difference value of the expected value of the age distribution corresponding to each sample image and the corresponding age labeling result after each sample image is input into the initial convolutional neural network model, wherein the predicted age distribution and the age distribution obey the Gaussian distribution, and each sample image is a color image; according to each image set, removing target images with abnormal age ranges in the image set to obtain residual target images, calculating normal age ranges corresponding to all the residual target images, taking the residual target images contained in the normal age ranges as sample images, and taking the mean value of the age ranges corresponding to the sample images as the age labeling result of the sample images, so that the infrared sample images and the corresponding age labeling result can be determined through a convolutional neural network model, a convolutional neural network model for performing age prediction on the infrared images can be obtained through training of the determined infrared sample images, and the age prediction on the infrared images is realized. And, compare with artifical age calibration, this scheme can use manpower sparingly resource, improves the efficiency that the sample was obtained. Of course, not all of the advantages described above need to be achieved at the same time in the practice of any one product or method of the invention.
The innovation points of the embodiment of the invention comprise:
1. the infrared sample image and the corresponding age labeling result are determined through the convolutional neural network model, so that the convolutional neural network model for carrying out age prediction on the infrared image can be obtained through training of the determined infrared sample image, and the age prediction on the infrared image is realized. And, compare with artifical age calibration, this scheme can use manpower sparingly resource, improves the efficiency that the sample was obtained.
2. According to the scheme that after the initial convolutional neural network model is input into each sample image, the difference value of the age distribution corresponding to each sample image output by the initial convolutional neural network model and the Gaussian distribution generated by the corresponding age labeling result and the difference value of the expected value of the age distribution corresponding to each sample image and the corresponding age labeling result are adjusted, all parameters in the initial convolutional neural network model are adjusted to obtain the convolutional neural network model.
3. The testing precision of the convolutional neural network model obtained by training is detected through the testing image, and when the testing precision is low, the convolutional neural network model is updated through the sample image again, so that the testing precision of the finally obtained convolutional neural network can be ensured, and the accuracy of age prediction is improved.
4. The key point detection is carried out on the face area, the face area is aligned to obtain the target image, the situations of side faces and the like in the target image can be avoided, the face in the target image is enabled to be clearer, and the accuracy of age prediction is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is to be understood that the drawings in the following description are merely exemplary of some embodiments of the invention. For a person skilled in the art, without inventive effort, further figures can be obtained from these figures.
Fig. 1 is a schematic flow chart of an infrared sample image acquisition method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of an infrared sample image acquisition method according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of an infrared sample image acquisition method according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart of an infrared sample image acquisition method according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an infrared sample image acquiring apparatus according to an embodiment of the present invention.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It is to be understood that the described embodiments are merely a few embodiments of the invention, and not all embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive effort based on the embodiments of the present invention, are within the scope of the present invention.
It should be noted that the terms "comprising" and "having" and any variations thereof in the embodiments and drawings of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
The embodiment of the invention discloses an infrared sample image acquisition method and device, which can be used for carrying out age prediction on a human face in an infrared image. The following provides a detailed description of embodiments of the invention.
Fig. 1 is a schematic flow chart of an infrared sample image acquisition method according to an embodiment of the present invention. The method is applied to the electronic equipment. The method specifically comprises the following steps.
S110: acquiring a plurality of image sets, wherein the initial infrared images in each image set are different face images of the same person in the same period, and the number of the initial infrared images in each sample image set is greater than a preset number threshold.
In the embodiment of the invention, a large number of infrared face images can be collected, and infrared sample images which can be used for training a convolutional neural network model capable of carrying out age prediction on the infrared images are determined.
Specifically, multiple infrared face images of different people at the same time can be acquired by designing an acquisition mode. For example, millions (e.g., 500, 600, 700, etc.) of infrared face images may be collected, and an average of about 100 persons may be used as the initial infrared image.
The same period may be a predetermined period, such as 1 day, 30 days, 60 days, etc., which is not limited in the embodiments of the present invention.
S120: detecting target face areas in the initial infrared images aiming at each image set, and constructing each target image containing each target face area; the size of each target image is a preset size.
For example, the target face region in each of the initial infrared images included in each image set may be detected by the Faster-RCNN face detection framework. Alternatively, any known target detection algorithm may be used to detect the target face region in each initial infrared image included in each image set, which is not limited in the embodiment of the present invention.
After the target face regions in the initial infrared images included in each image set are detected, target images including the target face regions can be constructed.
S130: inputting each target image into a convolutional neural network model obtained by pre-training to obtain the predicted age distribution of the person corresponding to each target face area, and determining the age range corresponding to each predicted age distribution; the convolutional neural network model is obtained by adjusting parameters in the initial convolutional neural network model to obtain a candidate neural network model and adjusting the candidate neural network model according to the difference value of the age distribution corresponding to each sample image output by the initial convolutional neural network model and the Gaussian distribution generated by the corresponding age labeling result and the difference value of the expected value of the age distribution corresponding to each sample image and the corresponding age labeling result after each sample image is input into the initial convolutional neural network model, the predicted age distribution and the age distribution obey the Gaussian distribution, and each sample image is a color image.
In the embodiment of the invention, a convolutional neural network model capable of predicting the age of the face in the infrared image can be constructed in advance. Specifically, the color image with the age labeled can be used as a sample image, and then, after each sample image is input into the initial convolutional neural network model, each parameter in the initial convolutional neural network model is adjusted to obtain a candidate neural network model according to a difference value between an age distribution corresponding to each sample image output by the initial convolutional neural network model and a gaussian distribution generated by a corresponding age labeling result, and a difference value between an expected value of the age distribution corresponding to each sample image and a corresponding age labeling result, wherein the candidate neural network model can predict the age of the color image; and then adjusting the candidate neural network model to obtain a convolutional neural network model capable of predicting the age of the infrared image.
And a gaussian distribution, i.e., a normal distribution. If the random variable X follows a normal distribution with mathematical expectation of μ and variance σ ^2, it is denoted as N (μ, σ ^ 2). Its expected value μ determines its position and its standard deviation σ determines the amplitude of the distribution. A normal distribution when μ ═ 0 and σ ═ 1 is a standard normal distribution.
The expected value of the age distribution corresponding to each sample image is an expected value of a gaussian distribution, that is, an age value with the highest probability in the middle of the age distribution corresponding to each sample image.
After each target image including each target face area is obtained, each target image can be input into a convolutional neural network model obtained through pre-training, and the convolutional neural network model can output the predicted age distribution of the person corresponding to each target face area. Wherein each predicted age distribution follows a gaussian distribution, i.e. follows a normal distribution.
It will be appreciated that the accuracy of the age predicted by the convolutional neural network model is not particularly high, since the infrared image differs from the color image in characteristics. In the embodiment of the present invention, after the predicted age distribution of the person corresponding to each target face region is obtained, the age range corresponding to each predicted age distribution, that is, the age range included in each predicted age distribution, may be determined.
S140: and removing the target images with abnormal age ranges in the image set to obtain residual target images, calculating the normal age ranges corresponding to all the residual target images, taking the residual target images contained in the normal age ranges as sample images, and taking the average value of the age ranges corresponding to the sample images as the age labeling result of the sample images.
It will be appreciated that the age prediction results of hundreds of images of the same person at the same time period should be the same, i.e. the age range of each image included in each image set should be the same. However, in practical applications, the age ranges of the images obtained through step S130 may not be identical due to the fact that the images of other people are mixed into the personal image set, or due to the influence of the angles, illumination, and the like of different images.
In the embodiment of the present invention, for each image set, target images with an abnormal age range in the image set may be removed to obtain remaining target images.
In one implementation, a quartile range method may be used to remove target images with an abnormal age range in each image set, so as to obtain remaining target images. Specifically, as shown in fig. 2, the process may include the following steps.
S210: and for each image set, sequencing the target images according to the sequence of the minimum value of the age range corresponding to the target images in the image set from small to large.
For example, when 100 target images are included in any image set, the age ranges of 10 target images are 15-25, 80 target images are 30-40, and 10 target images are 40-50, the target images may be sorted according to the order from the smallest value of the age ranges from small to large, i.e., the order of 15, 30, and 40.
S220: a first age range located one quarter and a second age range located three quarters are determined, as well as a minimum value for the first age range and a maximum value for the second age range.
In the above example, the first age range located at one fourth is the age range 30-40 corresponding to the 25 th target image, and the second age range located at three quarters is the age range 30-40 corresponding to the 75 th target image. The minimum value of the first age range is 30 and the maximum value of the second age range is 40.
S230: and removing the target image which contains the difference between the age value smaller than the minimum value and the preset value in the corresponding age range and the target image which contains the age value larger than the sum of the maximum value and the preset value to obtain the residual target image.
The preset value may be any preset number, such as 3, 5, 6, etc., and the embodiment of the present invention is not limited thereto.
For example, when the preset value is 3, in the above example, the difference between the minimum value and the preset value is 27, the sum of the maximum value and the preset value is 43, the target image with the age value smaller than the difference between the minimum value and the preset value in the age range is 10 target images with the age range of 15 to 25, the target image with the age value larger than the sum of the maximum value and the preset value in the age range is 10 target images with the age range of 40 to 50, and the above determined target images are removed to obtain 80 target images with the age range of 30 to 40 as the remaining target images.
After obtaining the remaining target images, the normal age ranges corresponding to all the remaining target images may be calculated, for example, the mean and standard deviation of the age ranges corresponding to all the remaining target images may be calculated; acquiring a preset hyper-parameter; and calculating the product of the hyperparameter and the standard deviation, taking the difference between the mean value and the product as the minimum value of the normal age range, and taking the sum of the mean value and the product as the maximum value of the normal age range.
For example, it can be assumed that the results [ x1, x2, x3,.. xn ] of images of the same person at any one time period, predicted by the convolutional neural network model, are gaussian-distributed as follows:
adopting a 4-minute distance method for [ x1, x2, x 3.. ang.n ], eliminating obvious abnormal values to obtain the remaining m images and predicted values [ x1, x2, x 3.. ang.m ] of the m images, and calculating a statistical mean u and a standard deviation s of the m images by using a Grubbs (Grubbs) detection method aiming at the results of the m same people, and designing a hyper-parameter k by the following calculation formula:
μ-k*s≤xi≤μ+k*s
and (3) removing the images which are not in the range, obtaining the last [ x1, x2, x3,.. xh ] images in the range, counting the average value of the prediction range of the h images, and matching the average value with the h infrared images to form a new data set which is the infrared sample image as the age labeling result of the person.
As can be seen from the above, in the embodiment, the infrared sample image and the corresponding age labeling result can be determined through the convolutional neural network model, so that the convolutional neural network model for performing age prediction on the infrared image can be obtained through training of the determined infrared sample image, and the age prediction on the infrared image is realized. And, compare with artifical age calibration, this scheme can use manpower sparingly resource, improves the efficiency that the sample was obtained.
As an implementation manner of the embodiment of the present invention, as shown in fig. 3, the training process of the convolutional neural network model may include the following steps.
S310: constructing an initial convolutional neural network model, wherein the initial convolutional neural network model comprises the following steps: a convolution layer, a pooling layer, and a full-link layer.
The initial convolutional neural network model in the embodiment of the present invention may include data processing layers with parameters, such as convolutional layers, pooling layers, full-link layers, and the like. The number of the convolutional layer, the pooling layer, and the fully-connected layer may be one or more layers, as long as the age prediction can be achieved, which is not limited in the embodiment of the present invention.
S320: acquiring each sample image and an age labeling result corresponding to each sample image; each sample image is a color image.
For example, a color image with an age given to the common data set may be used as a sample image, and the age given to the color image may be used as an age given result corresponding to each sample image.
The public data set may be, for example, AFAD: (Asian Face Age Dataset), a public Asian Face image Dataset, containing Face images around 160k and their Age labels; alternatively, the Face image data set may be a published asian Face image data set containing Face images of around 45k and their age labels.
S330: and generating the Gaussian distribution of the age labeling result corresponding to each sample image.
For example, a gaussian distribution having a preset standard deviation as a peak width centered on the age labeling result corresponding to the sample image may be constructed for each sample image as the gaussian distribution of the age labeling result corresponding to the sample image.
The preset standard deviation may be a preset value, and the specific value thereof is not limited in the embodiment of the present invention. It is understood that the smaller the above-mentioned preset standard deviation is, the sharper the peak of the gaussian distribution is generated, and the more concentrated the respective age values included therein are.
S340: inputting each sample image into the initial convolutional neural network model to obtain age distribution corresponding to each sample image, calculating a difference value of the age distribution corresponding to each sample image and Gaussian distribution generated by a corresponding age labeling result, and a difference value of an expected value of the age distribution corresponding to each sample image and the corresponding age labeling result, adjusting each parameter in the initial convolutional neural network model according to the calculation result to obtain a candidate neural network model, and adjusting the candidate neural network model to obtain the convolutional neural network model.
And after the sample image, the corresponding age labeling result and the Gaussian distribution of the age labeling result are obtained, the convolutional neural network model capable of carrying out age prediction on the infrared image can be trained. Specifically, each sample image may be input into the initial convolutional neural network model, a difference between an age distribution corresponding to each sample image output by the initial convolutional neural network model and a gaussian distribution generated by a corresponding age labeling result, and a difference between an expected value of the age distribution corresponding to each sample image and a corresponding age labeling result, each parameter in the initial convolutional neural network model is adjusted to obtain a candidate neural network model, and the candidate neural network model may perform age prediction on the color image; and then adjusting the candidate neural network model to obtain a convolutional neural network model capable of predicting the age of the infrared image.
Specifically, the loss function based on Gaussian distribution estimation and expected age estimation is constructed, face age labeling is converted into designed Gaussian distribution which is used as a label, the designed Gaussian distribution is compared with prediction generated by a model to generate a returned error, and each parameter in an initial convolutional neural network model is adjusted to obtain a candidate convolutional neural network model. Furthermore, the candidate convolutional neural network model is adjusted to a model capable of predicting the age of the single-channel infrared image, and the convolutional neural network model is obtained.
According to the method, after each sample image is input into an initial convolutional neural network model, the difference value of the age distribution corresponding to each sample image output by the initial convolutional neural network model and the Gaussian distribution generated by the corresponding age labeling result and the difference value of the expected value of the age distribution corresponding to each sample image and the corresponding age labeling result are adjusted to obtain the convolutional neural network model.
As an implementation manner of the embodiment of the present invention, in order to ensure accuracy of infrared image age prediction, precision detection may be performed on a trained convolutional neural network model.
Specifically, after obtaining the convolutional neural network model, as shown in fig. 4, the following steps may be further performed.
S410: and acquiring the test images and the age labeling results corresponding to the test images.
For example, a small number of infrared images containing a human face may be acquired as the test image. And, accurate age labeling is carried out on the test image manually.
S420: and determining the test precision of the convolutional neural network model according to the test images and the age labeling results corresponding to the test images.
For example, the test image may be input to the convolutional neural network model, the convolutional neural network model outputs an age distribution of each test image, and then an age expected value included in the age distribution and an age labeling result corresponding to each test image are compared to calculate an accuracy, and the accuracy may be determined as the test accuracy of the convolutional neural network.
When the accuracy is calculated, the difference between the expected age value included in the age distribution and the corresponding age labeling result of any test image can be calculated, and the difference is divided by the age labeling result to be used as the error rate. The value of 1 minus the error rate is then calculated as the accuracy of the test image. And taking the average value of the accuracy rate of each test image as the test precision of the convolutional neural network.
S430: and when the test precision is smaller than a preset precision threshold value, taking the current convolutional neural network model as an initial convolutional neural network model, returning to the step of acquiring each sample image and the age labeling result corresponding to each sample image, and taking the current convolutional neural network model as a final convolutional neural network model until the test precision is not smaller than the preset precision threshold value.
And when the test precision is smaller than the preset precision threshold value, the age prediction precision of the convolutional neural network model obtained by current training is low, and under the condition, the convolutional neural network model can be updated, so that the precision of the convolutional neural network model is improved.
Specifically, the current convolutional neural network model may be used as the initial convolutional neural network model, and the steps of obtaining each sample image and the age labeling result corresponding to each sample image, that is, steps S320 to S340, are executed. Namely, different sample images are obtained again, parameters of the convolutional neural network model are adjusted until the test precision meets the requirements, and the convolutional neural network model obtained through current training is used as the final convolutional neural network model.
The testing precision of the convolutional neural network model obtained by training is detected through the testing image, and when the testing precision is low, the convolutional neural network model is updated through the sample image again, so that the testing precision of the finally obtained convolutional neural network can be ensured, and the accuracy of age prediction is improved.
It can be understood that in the initial infrared image acquired by the electronic device, the face of the person may face forward, and there may be a case where the face of the person is not facing forward, such as a side face. When the face is not facing forward, the accuracy of the age prediction result may be affected.
As an implementation manner of the embodiment of the present invention, when the electronic device constructs each target image including each target face region, the electronic device may first perform key point detection on each target face region to obtain coordinate information of each target key point of each target face region; wherein, each target key point is a point for identifying the human face contour feature; and then aligning each target face area according to the coordinate information of each target key point of each target face area to obtain each target image which comprises each target face area and is provided with each target key point at a preset position.
For example, the key point detection may be performed on the target face region based on MTCNN (Multi-task Convolutional Neural Network), and the coordinate information in the coordinate system constructed in the initial infrared image of each target key point may be determined as the coordinate information of each target key point.
In one implementation, the key points may include, for example, key points of an eye region. Therefore, the target image which comprises the target face area and each key point of the eye area is located at the preset position can be constructed.
The key point detection is carried out on the face area, the face area is aligned to obtain the target image, the situations of side faces and the like in the target image can be avoided, the face in the target image is enabled to be clearer, and the accuracy of age prediction is improved.
It should be noted that the infrared sample image acquisition method provided by the embodiment of the present invention may also be applied to other types of images. For example, for a color image, the method provided in this embodiment may also be used to obtain an accurate sample image, and then train to obtain a convolutional neural network model for performing age prediction on a face in the color image, so as to improve accuracy of the age prediction.
As shown in fig. 5, an infrared sample image acquiring apparatus provided in an embodiment of the present invention may include:
an image set obtaining module 510, configured to obtain a plurality of image sets, where an initial infrared image in each image set is a different face image of the same person in the same period, and the number of initial infrared images in each sample image set is greater than a preset number threshold;
a face region detection module 520, configured to detect, for each image set, a target face region in each initial infrared image, and construct each target image including each target face region; the size of each target image is a preset size;
an age range determining module 530, configured to input each target image into a convolutional neural network model obtained through pre-training, obtain a predicted age distribution of a person corresponding to each target face region, and determine an age range corresponding to each predicted age distribution; the method comprises the steps that after an initial convolutional neural network model is input into each sample image, the convolutional neural network model adjusts each parameter in the initial convolutional neural network model to obtain a candidate neural network model according to the difference value of the age distribution corresponding to each sample image output by the initial convolutional neural network model and the Gaussian distribution generated by the corresponding age labeling result and the difference value of the expected value of the age distribution corresponding to each sample image and the corresponding age labeling result, and the candidate neural network model is adjusted to obtain the convolutional neural network model, wherein the predicted age distribution and the age distribution are both subjected to Gaussian distribution, and each sample image is a color image;
the infrared sample determining module 540 is configured to, for each image set, remove a target image with an abnormal age range in the image set to obtain remaining target images, calculate a normal age range corresponding to all remaining target images, use the remaining target images included in the normal age range as sample images, and use a mean value of the age ranges corresponding to the sample images as an age labeling result of the sample images.
As can be seen from the above, the infrared sample image acquisition apparatus provided in the embodiment of the present invention can determine the infrared sample image and the corresponding age labeling result through the convolutional neural network model, so that the convolutional neural network model for performing age prediction on the infrared image can be obtained through training of the determined infrared sample image, and thus the age prediction on the infrared image is realized. And, compare with artifical age calibration, this scheme can use manpower sparingly resource, improves the efficiency that the sample was obtained.
Optionally, the infrared sample determining module 540 includes:
the image sorting submodule is used for sorting the target images according to the sequence from small to large of the minimum value of the age range corresponding to the target images in each image set;
a value determination submodule for determining a first age range located at one quarter and a second age range located at three quarters, and a minimum value of the first age range and a maximum value of the second age range;
and the image determining submodule is used for removing the target image which comprises an age value smaller than the difference between the minimum value and a preset value and the target image which comprises an age value larger than the sum of the maximum value and the preset value in the corresponding age range to obtain the residual target image.
Optionally, the infrared sample determining module 540 includes:
the numerical value calculation submodule is used for calculating the mean value and the standard deviation of the age range corresponding to all the residual target images;
the parameter acquisition sub-module is used for acquiring a preset hyper-parameter;
and the range determination submodule is used for calculating the product of the hyperparameter and the standard deviation, taking the difference between the mean value and the product as the minimum value of the normal age range, and taking the sum of the mean value and the product as the maximum value of the normal age range.
Optionally, the apparatus further comprises:
a network model construction module for constructing an initial convolutional neural network model, the initial convolutional neural network model comprising: a convolution layer, a pooling layer, and a full-link layer;
the system comprises a sample image acquisition module, a storage module and a display module, wherein the sample image acquisition module is used for acquiring each sample image and an age labeling result corresponding to each sample image; all the sample images are color images;
the Gaussian distribution generating module is used for generating Gaussian distribution of the age labeling result corresponding to each sample image;
and the network model training module is used for inputting each sample image into the initial convolutional neural network model to obtain the age distribution corresponding to each sample image, calculating the difference value of the age distribution corresponding to each sample image and the Gaussian distribution generated by the corresponding age labeling result, and calculating the difference value of the expected value of the age distribution corresponding to each sample image and the corresponding age labeling result, adjusting each parameter in the initial convolutional neural network model according to the calculation result to obtain a candidate neural network model, and adjusting the candidate neural network model to obtain the convolutional neural network model.
Optionally, the gaussian distribution generating module is specifically configured to:
and constructing a Gaussian distribution taking the age labeling result corresponding to the sample image as the center and the preset standard deviation as the peak width as the Gaussian distribution of the age labeling result corresponding to the sample image for each sample image.
Optionally, the apparatus further comprises:
the test image acquisition module is used for acquiring test images and age labeling results corresponding to the test images;
the test precision determining module is used for determining the test precision of the convolutional neural network model according to the test images and age labeling results corresponding to the test images;
and the processing module is used for taking the current convolutional neural network model as an initial convolutional neural network model when the test precision is smaller than a preset precision threshold value, triggering the sample image acquisition module, and taking the current convolutional neural network model as a final convolutional neural network model when the test precision is not smaller than the preset precision threshold value.
Optionally, the face region detecting module 520 includes:
the key point detection submodule is used for carrying out key point detection on each target face area to obtain the coordinate information of each target key point of each target face area; wherein, each target key point is a point for identifying the human face contour feature;
and the target image construction submodule is used for aligning each target face region according to the coordinate information of each target key point of each target face region to obtain each target image which comprises each target face region and is positioned at a preset position.
The above device embodiment corresponds to the method embodiment, and has the same technical effect as the method embodiment, and for the specific description, refer to the method embodiment. The device embodiment is obtained based on the method embodiment, and for specific description, reference may be made to the method embodiment section, which is not described herein again.
Those of ordinary skill in the art will understand that: the figures are schematic representations of one embodiment, and the blocks or processes shown in the figures are not necessarily required to practice the present invention.
Those of ordinary skill in the art will understand that: modules in the devices in the embodiments may be distributed in the devices in the embodiments according to the description of the embodiments, or may be located in one or more devices different from the embodiments with corresponding changes. The modules of the above embodiments may be combined into one module, or further split into multiple sub-modules.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. An infrared sample image acquisition method is characterized by comprising the following steps:
acquiring a plurality of image sets, wherein the initial infrared images in each image set are different face images of the same person in the same period, and the number of the initial infrared images in each image set is greater than a preset number threshold;
detecting target face regions in each initial infrared image aiming at each image set, and constructing each target image containing each target face region; the size of each target image is a preset size;
inputting each target image into a convolutional neural network model obtained by pre-training to obtain the predicted age distribution of the person corresponding to each target face area, and determining the age range corresponding to each predicted age distribution; the convolutional neural network model is obtained by adjusting parameters in the initial convolutional neural network model to obtain a candidate neural network model and adjusting the candidate neural network model according to the difference value between the age distribution corresponding to each sample image output by the initial convolutional neural network model and the Gaussian distribution generated by the corresponding age labeling result and the difference value between the expected value of the age distribution corresponding to each sample image and the corresponding age labeling result after each sample image is input into the initial convolutional neural network model, wherein the predicted age distribution and the age distribution corresponding to each sample image are subject to the Gaussian distribution, and each sample image is a color image;
for each image set, removing target images with abnormal age ranges in the image set to obtain residual target images, calculating normal age ranges corresponding to all the residual target images, taking the residual target images contained in the normal age ranges as sample images, and taking the mean value of the age ranges corresponding to the sample images as the age labeling result of the sample images;
wherein, for each image set, removing the target image with abnormal age range in the image set to obtain the remaining target images comprises:
for each image set, sequencing the target images according to the sequence from small to large of the minimum value of the age range corresponding to the target images in the image set;
determining a first age range located one quarter and a second age range located three quarters, and a minimum value of the first age range and a maximum value of the second age range;
and removing the target image in the corresponding age range, wherein the target image comprises the difference between the minimum value of which the age value is smaller than the first age range and a preset value, and the target image of which the age value is larger than the sum of the maximum value and the preset value, so as to obtain the residual target image.
2. The method of claim 1, wherein the calculating the normal age range for all remaining target images comprises:
calculating the mean value and the standard deviation of the age range corresponding to all the residual target images;
acquiring a preset hyper-parameter;
and calculating the product of the hyperparameter and the standard deviation, taking the difference between the mean value and the product as the minimum value of the normal age range, and taking the sum of the mean value and the product as the maximum value of the normal age range.
3. The method of claim 1, wherein the training process of the pre-trained convolutional neural network model comprises:
constructing an initial convolutional neural network model, wherein the initial convolutional neural network model comprises the following components: a convolution layer, a pooling layer, and a full-link layer;
acquiring each sample image and an age labeling result corresponding to each sample image; all the sample images are color images;
generating Gaussian distribution of age labeling results corresponding to the sample images;
inputting each sample image into the initial convolutional neural network model to obtain age distribution corresponding to each sample image, calculating a difference value of the age distribution corresponding to each sample image and Gaussian distribution generated by a corresponding age labeling result, and a difference value of an expected value of the age distribution corresponding to each sample image and a corresponding age labeling result, adjusting each parameter in the initial convolutional neural network model according to the calculation result to obtain a candidate neural network model, and adjusting the candidate neural network model to obtain the convolutional neural network model.
4. The method of claim 3, wherein the generating the Gaussian distribution of the age labeling result corresponding to each sample image comprises:
and constructing a Gaussian distribution taking the age labeling result corresponding to the sample image as the center and the preset standard deviation as the peak width as the Gaussian distribution of the age labeling result corresponding to the sample image for each sample image.
5. The method of claim 3, wherein after obtaining the pre-trained convolutional neural network model, the method further comprises:
acquiring test images and age labeling results corresponding to the test images;
determining the testing precision of the convolutional neural network model obtained by pre-training according to the testing images and the age labeling results corresponding to the testing images;
and when the test precision is smaller than a preset precision threshold value, taking the current convolutional neural network model as an initial convolutional neural network model, returning to the step of acquiring each sample image and the age labeling result corresponding to each sample image, and taking the current convolutional neural network model as a final convolutional neural network model when the test precision is not smaller than the preset precision threshold value.
6. The method of any one of claims 1-5, wherein constructing each target image containing each of the target face regions comprises:
performing key point detection on each target face area to obtain coordinate information of each target key point of each target face area; each target key point is a point for identifying the human face contour feature;
and according to the coordinate information of each target key point of each target face region, aligning each target face region to obtain each target image which comprises each target face region and is located at a preset position.
7. An infrared sample image acquisition device, comprising:
the system comprises an image set acquisition module, a face recognition module and a face recognition module, wherein the image set acquisition module is used for acquiring a plurality of image sets, initial infrared images in each image set are different face images of the same person in the same period, and the number of the initial infrared images in each image set is greater than a preset number threshold;
the face region detection module is used for detecting a target face region in each initial infrared image aiming at each image set and constructing each target image containing each target face region; the size of each target image is a preset size;
the age range determining module is used for inputting each target image into a convolutional neural network model obtained by pre-training to obtain the predicted age distribution of the person corresponding to each target face area and determining the age range corresponding to each predicted age distribution; the convolutional neural network model is obtained by adjusting parameters in the initial convolutional neural network model to obtain a candidate neural network model and adjusting the candidate neural network model according to the difference value between the age distribution corresponding to each sample image output by the initial convolutional neural network model and the Gaussian distribution generated by the corresponding age labeling result and the difference value between the expected value of the age distribution corresponding to each sample image and the corresponding age labeling result after each sample image is input into the initial convolutional neural network model, wherein the predicted age distribution and the age distribution corresponding to each sample image are subject to the Gaussian distribution, and each sample image is a color image;
the infrared sample determining module is used for removing target images with abnormal age ranges in each image set to obtain residual target images, calculating normal age ranges corresponding to all the residual target images, taking the residual target images contained in the normal age ranges as sample images, and taking the average value of the age ranges corresponding to the sample images as an age labeling result of the sample images;
wherein the infrared sample determination module comprises:
the image sorting submodule is used for sorting the target images according to the sequence from small to large of the minimum value of the age range corresponding to the target images in each image set;
a value determination submodule for determining a first age range located at one quarter and a second age range located at three quarters, and a minimum value of the first age range and a maximum value of the second age range;
and the image determining submodule is used for removing the target image in the corresponding age range, wherein the target image comprises the difference between the minimum value of the age value smaller than the first age range and a preset value, and the target image comprises the sum of the age value larger than the maximum value and the preset value, so that the residual target image is obtained.
8. The apparatus of claim 7, wherein the infrared sample determination module comprises:
the numerical value calculation submodule is used for calculating the mean value and the standard deviation of the age range corresponding to all the remaining target images;
the parameter acquisition sub-module is used for acquiring a preset hyper-parameter;
and the range determination submodule is used for calculating the product of the hyperparameter and the standard deviation, taking the difference between the mean value and the product as the minimum value of the normal age range, and taking the sum of the mean value and the product as the maximum value of the normal age range.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910669497.9A CN112287726B (en) | 2019-07-24 | 2019-07-24 | Infrared sample image acquisition method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910669497.9A CN112287726B (en) | 2019-07-24 | 2019-07-24 | Infrared sample image acquisition method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112287726A CN112287726A (en) | 2021-01-29 |
| CN112287726B true CN112287726B (en) | 2022-06-24 |
Family
ID=74418760
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910669497.9A Active CN112287726B (en) | 2019-07-24 | 2019-07-24 | Infrared sample image acquisition method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112287726B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113456031A (en) * | 2021-08-09 | 2021-10-01 | 首都医科大学附属北京天坛医院 | Training device and prediction device of brain state prediction model and electronic equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503623A (en) * | 2016-09-27 | 2017-03-15 | 中国科学院自动化研究所 | Facial image age estimation method based on convolutional neural networks |
| CN107045622A (en) * | 2016-12-30 | 2017-08-15 | 浙江大学 | The face age estimation method learnt based on adaptive age distribution |
-
2019
- 2019-07-24 CN CN201910669497.9A patent/CN112287726B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503623A (en) * | 2016-09-27 | 2017-03-15 | 中国科学院自动化研究所 | Facial image age estimation method based on convolutional neural networks |
| CN107045622A (en) * | 2016-12-30 | 2017-08-15 | 浙江大学 | The face age estimation method learnt based on adaptive age distribution |
Non-Patent Citations (1)
| Title |
|---|
| 年龄估计技术综述;丁大钧;《知乎https-//zhuanlan.zhihu.com/p/53229759》;20181215;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112287726A (en) | 2021-01-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112307796B (en) | Age prediction method and device for infrared image | |
| EP3292512B1 (en) | Full reference image quality assessment based on convolutional neural network | |
| CN110766095B (en) | Defect detection method based on image gray level features | |
| EP2803015A2 (en) | Two stage categorization of objects in images | |
| CN114663335A (en) | Image defect detection method, device, electronic equipment and medium | |
| CN108053025B (en) | Multi-column neural network medical image analysis method and device | |
| KR101313051B1 (en) | Method and device for recognizing pulse repetition interval modulation type of a radar signal | |
| CN114463609B (en) | Method and device for determining fluorescent mixed points in cell microscopic image | |
| CN115496740A (en) | Lens defect detection method and system based on convolutional neural network | |
| Lehr et al. | Classification of similar objects of different sizes using a reference object by means of convolutional neural networks | |
| CN108470194B (en) | Feature screening method and device | |
| CN112287726B (en) | Infrared sample image acquisition method and device | |
| Baker et al. | Deep Convolutional Networks do not Perceive Illusory Contours. | |
| Pessa et al. | Mapping images into ordinal networks | |
| Davari et al. | On Mathews correlation coefficient and improved distance map loss for automatic glacier calving front segmentation in SAR imagery | |
| Gaata et al. | No-reference quality metric based on fuzzy neural network for subjective image watermarking evaluation | |
| Islam et al. | How certain are tansformers in image classification: uncertainty analysis with Monte Carlo dropout | |
| CN111179226B (en) | Visual field diagram identification method and device and computer storage medium | |
| Wei et al. | Label smoothing technique for ordinal classification in cloud assessment | |
| KR20220167827A (en) | Smart factory system capable of detecting defects based on artificial intelligence | |
| CN113808088A (en) | Pollution detection method and system | |
| CN111860334A (en) | Cascade vehicle type classification method and device based on confusion matrix | |
| Xie et al. | An optimal orientation certainty level approach for fingerprint quality estimation | |
| Zhang et al. | No-reference image quality assessment based on multi-order gradients statistics | |
| Kang et al. | CST-YOLO: A Novel Method for Blood Cell Detection Based on Improved YOLOv7 and CNN-Swin Transformer |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20211124 Address after: 215100 floor 23, Tiancheng Times Business Plaza, No. 58, qinglonggang Road, high speed rail new town, Xiangcheng District, Suzhou, Jiangsu Province Applicant after: MOMENTA (SUZHOU) TECHNOLOGY Co.,Ltd. Address before: Room 601-a32, Tiancheng information building, No. 88, South Tiancheng Road, high speed rail new town, Xiangcheng District, Suzhou City, Jiangsu Province Applicant before: MOMENTA (SUZHOU) TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |