CN112287772A - Fingerprint trace detection method, fingerprint detection device and computer readable storage medium - Google Patents
Fingerprint trace detection method, fingerprint detection device and computer readable storage medium Download PDFInfo
- Publication number
- CN112287772A CN112287772A CN202011080076.1A CN202011080076A CN112287772A CN 112287772 A CN112287772 A CN 112287772A CN 202011080076 A CN202011080076 A CN 202011080076A CN 112287772 A CN112287772 A CN 112287772A
- Authority
- CN
- China
- Prior art keywords
- image
- original
- characteristic
- training
- fingerprint
- 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.)
- Granted
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
- G06V40/12—Fingerprints or palmprints
- G06V40/1347—Preprocessing; Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06V10/20—Image preprocessing
Abstract
The invention provides a fingerprint trace detection method, which comprises the following steps: acquiring an original training image or an image to be detected; carrying out contrast ratio limiting adaptive histogram equalization processing on the original training image or the image to be detected; reducing the width and height of the processed original training image or the image to be detected, and expanding the number of channels of the processed original training image or the image to be detected to obtain a characteristic training image or a characteristic image; respectively carrying out image preprocessing on each characteristic training image, and obtaining an image set to be trained; training an image set to be trained through a preset convolutional neural network to obtain a characteristic convolutional neural network; and calculating and analyzing to obtain the characteristic fingerprint information of the characteristic image according to the characteristic convolution neural network. Compared with the related technology, the fingerprint trace detection method has the advantages of high fingerprint trace detection definition, high detection speed and real-time detection.
Description
[ technical field ] A method for producing a semiconductor device
The present invention relates to the field of object detection, and in particular, to a fingerprint trace detection method, a fingerprint detection apparatus, and a computer-readable storage medium.
[ background of the invention ]
In recent years, with the development of deep learning technology, the target detection algorithm has made a great breakthrough, wherein the detection algorithm is gradually applied to criminal investigation equipment, mainly applied to fingerprint trace detection devices.
In the related art, a fingerprint trace detection method is a method for detecting a fingerprint trace on an image to be detected after deep learning of a fingerprint trace image, and target detection algorithms adopted by the method mainly include the following two categories:
one is a Two stage method, which is mainly divided into Two steps, the first step is to generate a candidate frame on an image to be measured, and the second step is to identify an object in the candidate frame, such as an R-CNN (Region-CNN, i.e., a convolutional network method based on regional recommendation) algorithm, a Fast R-CNN (Fast-Region-CNN, i.e., a Fast convolutional network method based on regional recommendation), a Fast R-CNN (Fast-Region-CNN, more Fast convolutional network method based on regional recommendation), and the like.
The other is a method of One stage, which unifies the whole process and directly gives the detection result, mainly comprising SSD, YOLO and the like.
In the two methods, because of the large calculation amount, in practical application, the image size of the image to be detected is often reduced first, and then fingerprint trace detection calculation is performed.
However, in the related art, for the fingerprint trace, if the size of the image to be detected is reduced too much, the fingerprint trace will be pasted into a block and cannot be distinguished, so that the fingerprint trace detection definition is low; if the size is not reduced enough, the operation speed is greatly reduced, so that the detection speed is low and the requirement of real-time detection is not met.
Therefore, there is a need to provide a new fingerprint trace detection method, a fingerprint detection device and a computer readable storage medium to solve the above-mentioned technical problems.
[ summary of the invention ]
The invention aims to provide a fingerprint trace detection method, a fingerprint detection device and a computer readable storage medium, which solve the problems of low fingerprint trace detection definition, low detection speed and insufficient requirement for real-time detection.
In order to achieve the above object, the present invention provides a fingerprint trace detection method, which comprises the following steps:
step S1, acquiring an image to be detected in real time;
step S2, carrying out contrast ratio limiting adaptive histogram equalization processing on the image to be detected;
step S3, the width and the height of the image to be measured are reduced, and the number of channels of the image to be measured is enlarged to obtain a characteristic image;
step S4, according to the characteristic image, according to the characteristic convolution neural network, calculating and analyzing to obtain the characteristic fingerprint information of the characteristic image; the characteristic fingerprint information comprises at least one of the position and the confidence of a fingerprint trace on the characteristic image, and the acquisition method of the characteristic convolution neural network comprises the following steps:
step S1a, acquiring a plurality of original training images;
step S2a, respectively carrying out contrast ratio limiting adaptive histogram equalization processing on a plurality of original training images;
step S3a, reducing the widths and heights of the original training images, and increasing the number of channels of the original training images to obtain feature training images; the original training images and the feature training images are arranged in a one-to-one correspondence mode;
s4a, respectively carrying out image preprocessing on each feature training image, and obtaining an image set to be trained; the image preprocessing comprises at least one of image processing modes such as Gaussian blur, rotation, contrast, brightness and the like; the image set to be trained comprises a plurality of images to be trained, and at least two images to be trained are generated after one characteristic training image is subjected to image preprocessing;
and S5a, training the image set to be trained through a preset convolutional neural network to obtain the characteristic convolutional neural network.
Preferably, in step S1a, the original training image includes a first training image and/or a second training image, where the first training image is an image of fingerprint traces acquired under various scenes, and the second training image is a random image without fingerprint traces.
Preferably, in the step 3a, the method includes reducing the width of the original training image to one fourth of the original width thereof, reducing the height of the original training image to one fourth of the original height thereof, and expanding the number of channels of the original training image to sixteen times of the number of original channels thereof; in the step 3, the method includes reducing the width of the image to be measured to one fourth of the original width, reducing the height of the image to be measured to one fourth of the original height, and expanding the number of channels of the image to be measured to sixteen times of the number of original channels.
Preferably, the original training image and/or the image to be measured are/is acquired by means of ultraviolet imaging.
The present invention provides a fingerprint detection device, including:
the image acquisition module is used for acquiring a plurality of original training images and images to be detected;
the image processing module is used for respectively carrying out contrast ratio limiting adaptive histogram equalization processing on a plurality of original training images and the image to be detected; the system comprises a plurality of original training images or images to be detected, a plurality of feature training images or feature images, a plurality of image acquisition units and a plurality of image acquisition units, wherein the original training images or the images to be detected are used for reducing the width and the height of the original training images or the images to be detected and expanding the number of channels of the original training images or the images to be detected so as to obtain the feature training images or the feature images; the image preprocessing module is used for performing image preprocessing on each characteristic training image and obtaining an image set to be trained;
the image training module is used for training the image set to be trained through a preset convolutional neural network to obtain a characteristic convolutional neural network; and the number of the first and second groups,
the image analysis module is used for calculating and analyzing the characteristic fingerprint information of the characteristic image according to the characteristic convolution neural network and the characteristic image; wherein the feature fingerprint information comprises at least one of a location and a confidence of a fingerprint trace on the feature image.
Preferably, the image processing module is configured to reduce the width of the original training image to one fourth of the original width thereof, reduce the height of the original training image to one fourth of the original height thereof, and expand the number of channels of the original training image to sixteen times of the number of original channels thereof; the method is also used for reducing the width of the image to be detected to be one fourth of the original width of the image to be detected, reducing the height of the image to be detected to be one fourth of the original height of the image to be detected, and expanding the number of channels of the image to be detected to be sixteen times of the number of original channels of the image to be detected.
The invention provides a fingerprint detection device, which comprises a processor and a memory, wherein a control program of a fingerprint trace detection method is stored in the memory, and the control program realizes the steps of the fingerprint trace detection method when being executed by the processor.
The present invention provides a computer-readable storage medium storing a computer program; which when being executed by a processor performs the steps of the fingerprint trace detection method according to the invention.
The present invention provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of the fingerprint trace detection method according to the present invention.
Compared with the related art, the fingerprint trace detection method comprises the following steps: acquiring an original training image or an image to be detected; carrying out contrast ratio limiting adaptive histogram equalization processing on the original training image or the image to be detected; reducing the width and height of the processed original training image or the image to be detected, and expanding the number of channels of the processed original training image or the image to be detected to obtain a characteristic training image or a characteristic image; respectively carrying out image preprocessing on each characteristic training image, and obtaining an image set to be trained; training an image set to be trained through a preset convolutional neural network to obtain a characteristic convolutional neural network; and calculating and analyzing to obtain the characteristic fingerprint information of the characteristic image according to the characteristic convolution neural network. In the method, the characteristic convolution neural network is constructed in advance, and the fingerprint trace on the object to be detected is detected in real time through the characteristic convolution neural network, so that the real-time detection of the fingerprint trace is realized, the obtained image is subjected to contrast-limited adaptive histogram equalization processing, so that the fingerprint trace of the image is clear and obvious, the definition of the fingerprint trace detection of the image is effectively improved, in addition, the calculated amount of the fingerprint trace of the image identified through the characteristic convolution neural network is greatly reduced due to the image reduction processing, the fingerprint trace detection speed of the image is effectively improved, and meanwhile, the identification rate of the fingerprint trace of the image (namely, the detection rate is high) and the detection accuracy is high due to the strong identification capability of the characteristic convolution neural network on the fingerprint trace of the image.
[ description of the drawings ]
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without inventive efforts, wherein:
FIG. 1 is a schematic flow chart of a fingerprint trace detection method according to the present invention;
FIG. 2 is a schematic flow chart of another fingerprint trace detection method according to the present invention;
FIG. 3 is a schematic diagram of a fingerprint detection device according to the present invention;
FIG. 4 is a schematic diagram of an image before and after adjusting data arrangement according to the present invention.
[ detailed description ] embodiments
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 3, the present invention further provides a fingerprint detection apparatus 100, which includes an image acquisition module 1, an image processing module 2, an image training module 3, and an image analysis module 4.
The image acquisition module 1 is used for acquiring images; for example, in the present embodiment, the image acquisition module 1 is an ultraviolet imager, and the image acquisition module 1 acquires image data of an object by means of ultraviolet imaging.
The image processing module 2 is configured to perform Contrast-Limited Adaptive Histogram equalization (CLAHE) on the image, so that fingerprint traces in the processed image become more obvious, the problem that the fingerprint traces cannot be identified in a subsequent process due to inaccurate focusing or weak fingerprint traces is solved, and the detection rate and the detection accuracy of the fingerprint traces in the subsequent process are effectively improved; the image processing module 2 is further configured to adjust an arrangement mode of image data, that is, reduce the width and height of an image, and expand the number of channels of the image to obtain a feature training image for deep learning training or a feature image of a fingerprint trace to be detected, where the arrangement reduces the amount of calculation in image training by the image training module 3 or the amount of calculation in image recognition analysis by the image analysis module 4 by more than one order of magnitude on the premise of not losing the fingerprint trace on the image, so that the image training speed of the image training module 3 or the image recognition analysis speed of the image analysis module 4 can be greatly increased, and it is ensured that a feature convolutional neural network obtained by training has strong recognition capability (that is, high detection rate) on the fingerprint trace and has high accuracy rate of detection; the image processing module 2 is configured to perform image preprocessing on each feature training image and obtain an image set to be trained, where the image preprocessing includes at least one of image processing manners such as gaussian blur, rotation, contrast, and brightness, after the image preprocessing, the image set to be trained includes a plurality of images to be trained, and one feature training image generates at least two images to be trained after the image preprocessing.
The image training module 3 is configured to train an image set to be trained through a preset Convolutional Neural Network (CNN) to obtain a characteristic Convolutional Neural network. The image is subjected to contrast-limited adaptive histogram equalization processing, so that the display of the fingerprint trace by the image data in the image set to be trained is clearer and more obvious, the subsequent recognition capability of the fingerprint trace by the characteristic convolution neural network obtained after the image set to be trained is ensured, and the detection accuracy of the fingerprint trace by the characteristic convolution neural network is effectively improved.
The image analysis module 4 is used for calculating and analyzing the characteristic fingerprint information of the characteristic image according to the characteristic image and the characteristic convolution neural network; wherein the feature fingerprint information includes at least one of a location and a confidence of a fingerprint trace on the feature image. The characteristic convolution neural network has strong identification capability on the fingerprint trace, and the characteristic image can clearly display the fingerprint trace, so that the image analysis module 4 can quickly and accurately identify the fingerprint trace on the characteristic image.
Referring to fig. 1-3, the present invention provides a fingerprint trace detection method applied to the fingerprint detection apparatus 100, which is described in detail below with reference to the specific structure of the fingerprint detection apparatus 100:
the first step, obtaining a characteristic convolution neural network, which comprises the following substeps:
step S1a, acquiring an original training image by means of ultraviolet imaging using the image acquiring apparatus 1.
Specifically, in step S1a, the original training image includes a first training image and/or a second training image, where the first training image is an image of fingerprint traces acquired under various scenes, and the second training image is a random image without fingerprint traces.
Further, in order to ensure the detection accuracy, it is often necessary to set a negative sample to be input to the convolutional neural network for training, and improve the recognition capability of the trained convolutional neural network on the fingerprint traces in the image, therefore, in this embodiment, preferably, the original training image includes a first training image and a second training image, and in practical application, a large number of random photographs (second training images) are often used as negative samples to be added to the image set to be trained, so as to expand the training data of the image set to be trained, effectively improve the recognition capability of the fingerprint detection apparatus 100 on the image without the fingerprint traces, and effectively reduce the false rate of fingerprint trace recognition.
Step S2a, the image processing module 2 is used to perform contrast-limited adaptive histogram equalization on each of the plurality of original training images.
Step S3a, utilizing the image processing module 2 to reduce the width and height of a plurality of original training images and expand the number of channels of the plurality of original training images to obtain a plurality of characteristic training images; specifically, in step S3a, the original training images and the feature training images are arranged in a one-to-one correspondence.
Further, under the condition that other conditions are not changed, the inference time of the deep learning Convolutional Neural Network (CNN) is generally proportional to the size of the area of the input image, so in step S3a, by reducing and adjusting the overall size of the original training image, the area of the characteristic training image (as the input image) is reduced, and the training speed of the preset convolutional neural network on the image set to be trained is effectively improved; it should be noted that the specific reduction or expansion factor can be specifically set according to the actual use situation, and in the present embodiment, the step S3a includes:
the image processing module 2 is used for reducing the width of the original training image to be one fourth of the original width of the original training image, reducing the height of the original training image to be one fourth of the original height of the original training image, and expanding the number of channels of the original training image to be sixteen times of the number of original channels of the original training image.
And S4a, respectively carrying out image preprocessing on each characteristic training image by using the image processing module 2, and obtaining an image set to be trained.
Specifically, in step S4a, the image preprocessing includes at least one of image processing manners such as gaussian blur, rotation, contrast, and brightness, the image set to be trained includes a plurality of images to be trained, and one feature training image is subjected to image preprocessing to generate at least two images to be trained.
And step S5a, training the image set to be trained by the image training module 3 through a preset Convolutional Neural Network (CNN), so as to obtain a characteristic convolutional neural network.
Secondly, detecting fingerprint traces in the image in real time according to the characteristic convolution neural network, and the method comprises the following substeps:
step S1, acquiring an image to be detected in real time by using the image acquiring apparatus 1, and more specifically, acquiring image information of the object to be detected in real time by using the image acquiring apparatus 1 in an ultraviolet imaging manner as the image to be detected.
In step S2, the image to be measured is subjected to contrast-limited adaptive histogram equalization processing by the image processing module 2.
Step S3, the image processing module 2 is used to reduce the width and height of the processed image to be measured, and expand the number of channels of the processed image to be measured, so as to obtain a feature image.
Specifically, step S3 corresponds to step S3a, and therefore, in the present embodiment, step S3 includes:
the image processing module 2 is used for reducing the width of the image to be detected to be one fourth of the original width of the image to be detected, reducing the height of the image to be detected to be one fourth of the original height of the image to be detected, and expanding the number of channels of the image to be detected to be sixteen times of the number of original channels of the image to be detected.
Referring to fig. 4, (a) is a schematic diagram before arrangement of the image adjustment data, and (b) is a schematic diagram after arrangement of the image adjustment data, and referring to the following formula:
Iinput(i，j，c)；
Ioutput(i′，j′，c′)＝Iinput(c′/4+i/4，c′％4+j/4，1)；
i∈[1，h]，j∈[1，w]，c＝1；i′∈[1，h/4]，j′∈[1，w/4]，c′∈[i，16]；
in the formula IinputThe image is expressed before the data arrangement is adjusted, wherein i represents the longitudinal coordinate of the image, j represents the transverse coordinate of the image, and c represents the channel of the image; h represents IinputHeight of the image, w denotes IinputThe width of the image; i isinputThe number of channels is 1;
Ioutputrepresenting the image after the arrangement of the adjustment data, wherein i ' represents the longitudinal coordinate of the image, j ' represents the transverse coordinate of the image, and c ' represents the channel of the image; i isoutputWidth and height of the image are respectively IinputOne quarter of the width and height of the image; i isoutputThe number of channels is 16;
in the formula, "/" represents an integer division operation, and "%" represents a remainder operation.
Step S24, calculating and analyzing by using the image analysis module 4 according to the characteristic image and the characteristic convolution neural network to obtain characteristic fingerprint information of the characteristic image; wherein the feature fingerprint information includes at least one of a location and a confidence of a fingerprint trace on the feature image.
The invention provides a fingerprint detection device, which comprises a processor and a memory, wherein a control program of a fingerprint trace detection method is stored in the memory, and the control program realizes the steps of the fingerprint trace detection method when being executed by the processor.
The present invention provides a computer-readable storage medium storing a computer program; which when being executed by a processor performs the steps of the fingerprint trace detection method according to the invention.
Compared with the related art, the fingerprint trace detection method comprises the following steps: acquiring an original training image or an image to be detected; carrying out contrast ratio limiting adaptive histogram equalization processing on the original training image or the image to be detected; reducing the width and height of the processed original training image or the image to be detected, and expanding the number of channels of the processed original training image or the image to be detected to obtain a characteristic training image or a characteristic image; respectively carrying out image preprocessing on each characteristic training image, and obtaining an image set to be trained; training an image set to be trained through a preset convolutional neural network to obtain a characteristic convolutional neural network; and calculating and analyzing to obtain the characteristic fingerprint information of the characteristic image according to the characteristic convolution neural network. In the method, the characteristic convolution neural network is constructed in advance, and the fingerprint trace on the object to be detected is detected in real time through the characteristic convolution neural network, so that the real-time detection of the fingerprint trace is realized, the obtained image is subjected to contrast-limited adaptive histogram equalization processing, so that the fingerprint trace of the image is clear and obvious, the definition of the fingerprint trace detection of the image is effectively improved, in addition, the calculated amount of the fingerprint trace of the image identified through the characteristic convolution neural network is greatly reduced due to the image reduction processing, the fingerprint trace detection speed of the image is effectively improved, and meanwhile, the identification rate of the fingerprint trace of the image (namely, the detection rate is high) and the detection accuracy is high due to the strong identification capability of the characteristic convolution neural network on the fingerprint trace of the image.
While the foregoing is directed to embodiments of the present invention, it will be understood by those skilled in the art that various changes may be made without departing from the spirit and scope of the invention.
Claims (8)
1. A fingerprint trace detection method, characterized in that the method comprises the steps of:
step S1, acquiring an image to be detected in real time;
step S2, carrying out contrast ratio limiting adaptive histogram equalization processing on the image to be detected;
step S3, the width and the height of the image to be measured are reduced, and the number of channels of the image to be measured is enlarged to obtain a characteristic image;
step S4, according to the characteristic image, according to the characteristic convolution neural network, calculating and analyzing to obtain the characteristic fingerprint information of the characteristic image; the characteristic fingerprint information comprises at least one of the position and the confidence of a fingerprint trace on the characteristic image, and the acquisition method of the characteristic convolution neural network comprises the following steps:
step S1a, acquiring a plurality of original training images;
step S2a, respectively carrying out contrast ratio limiting adaptive histogram equalization processing on a plurality of original training images;
step S3a, reducing the widths and heights of the original training images, and increasing the number of channels of the original training images to obtain feature training images; the original training images and the feature training images are arranged in a one-to-one correspondence mode;
s4a, respectively carrying out image preprocessing on each feature training image, and obtaining an image set to be trained; the image preprocessing comprises at least one of image processing modes such as Gaussian blur, rotation, contrast, brightness and the like; the image set to be trained comprises a plurality of images to be trained, and at least two images to be trained are generated after one characteristic training image is subjected to image preprocessing;
and S5a, training the image set to be trained through a preset convolutional neural network to obtain the characteristic convolutional neural network.
2. The method for detecting fingerprint traces according to claim 1, wherein in the step S1a, the original training image includes a first training image and/or a second training image, the first training image is an image of fingerprint traces acquired under various scenes, and the second training image is a random image without fingerprint traces.
3. The fingerprint trace detection method according to claim 1, wherein in the step 3a, the method comprises reducing the width of the original training image to one fourth of the original width and reducing the height of the original training image to one fourth of the original height, and expanding the number of channels of the original training image to sixteen times of the number of original channels; in the step 3, the method includes reducing the width of the image to be measured to one fourth of the original width, reducing the height of the image to be measured to one fourth of the original height, and expanding the number of channels of the image to be measured to sixteen times of the number of original channels.
4. The fingerprint trace detection method according to claim 1, wherein the original training image and/or the image to be detected is obtained by means of ultraviolet imaging.
5. A fingerprint detection apparatus, comprising:
the image acquisition module is used for acquiring a plurality of original training images and images to be detected;
the image processing module is used for respectively carrying out contrast ratio limiting adaptive histogram equalization processing on a plurality of original training images and the image to be detected; the system comprises a plurality of original training images or images to be detected, a plurality of feature training images or feature images, a plurality of image acquisition units and a plurality of image acquisition units, wherein the original training images or the images to be detected are used for reducing the width and the height of the original training images or the images to be detected and expanding the number of channels of the original training images or the images to be detected so as to obtain the feature training images or the feature images; the image preprocessing module is used for performing image preprocessing on each characteristic training image and obtaining an image set to be trained;
the image training module is used for training the image set to be trained through a preset convolutional neural network to obtain a characteristic convolutional neural network; and the number of the first and second groups,
the image analysis module is used for calculating and analyzing the characteristic fingerprint information of the characteristic image according to the characteristic convolution neural network and the characteristic image; wherein the feature fingerprint information comprises at least one of a location and a confidence of a fingerprint trace on the feature image.
6. The fingerprint detection device according to claim 5, wherein the image processing module is configured to reduce the width of the original training image to one fourth of the original width, reduce the height of the original training image to one fourth of the original height, and expand the number of channels of the original training image to sixteen times the number of original channels; the method is also used for reducing the width of the image to be detected to be one fourth of the original width of the image to be detected, reducing the height of the image to be detected to be one fourth of the original height of the image to be detected, and expanding the number of channels of the image to be detected to be sixteen times of the number of original channels of the image to be detected.
7. A fingerprint detection apparatus comprising a processor and a memory, the memory having stored therein a control program for a fingerprint trace detection method, wherein the control program when executed by the processor implements the steps of the fingerprint trace detection method according to any one of claims 1 to 6.
8. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the fingerprint trace detection method according to any one of the preceding claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011080076.1A CN112287772B (en) | 2020-10-10 | 2020-10-10 | Fingerprint trace detection method, fingerprint detection device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011080076.1A CN112287772B (en) | 2020-10-10 | 2020-10-10 | Fingerprint trace detection method, fingerprint detection device and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112287772A true CN112287772A (en) | 2021-01-29 |
| CN112287772B CN112287772B (en) | 2023-02-10 |
Family
ID=74421877
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011080076.1A Active CN112287772B (en) | 2020-10-10 | 2020-10-10 | Fingerprint trace detection method, fingerprint detection device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112287772B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106647758A (en) * | 2016-12-27 | 2017-05-10 | 深圳市盛世智能装备有限公司 | Target object detection method and device and automatic guiding vehicle following method |
| CN108073933A (en) * | 2016-11-08 | 2018-05-25 | 杭州海康威视数字技术股份有限公司 | A kind of object detection method and device |
| CN108230257A (en) * | 2017-11-15 | 2018-06-29 | 北京市商汤科技开发有限公司 | Image processing method, device, electronic equipment and storage medium |
| CN109002846A (en) * | 2018-07-04 | 2018-12-14 | 腾讯科技（深圳）有限公司 | A kind of image-recognizing method, device and storage medium |
| WO2019128508A1 (en) * | 2017-12-28 | 2019-07-04 | Oppo广东移动通信有限公司 | Method and apparatus for processing image, storage medium, and electronic device |
| CN109978036A (en) * | 2019-03-11 | 2019-07-05 | 华瑞新智科技（北京）有限公司 | Target detection deep learning model training method and object detection method |
| CN110033417A (en) * | 2019-04-12 | 2019-07-19 | 江西财经大学 | A kind of image enchancing method based on deep learning |
| CN110276726A (en) * | 2019-05-13 | 2019-09-24 | 南昌大学 | A kind of image deblurring method based on the guidance of multichannel network prior information |
| CN111611907A (en) * | 2020-05-18 | 2020-09-01 | 沈阳理工大学 | Image-enhanced infrared target detection method |
-
2020
- 2020-10-10 CN CN202011080076.1A patent/CN112287772B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108073933A (en) * | 2016-11-08 | 2018-05-25 | 杭州海康威视数字技术股份有限公司 | A kind of object detection method and device |
| CN106647758A (en) * | 2016-12-27 | 2017-05-10 | 深圳市盛世智能装备有限公司 | Target object detection method and device and automatic guiding vehicle following method |
| CN108230257A (en) * | 2017-11-15 | 2018-06-29 | 北京市商汤科技开发有限公司 | Image processing method, device, electronic equipment and storage medium |
| WO2019128508A1 (en) * | 2017-12-28 | 2019-07-04 | Oppo广东移动通信有限公司 | Method and apparatus for processing image, storage medium, and electronic device |
| CN109002846A (en) * | 2018-07-04 | 2018-12-14 | 腾讯科技（深圳）有限公司 | A kind of image-recognizing method, device and storage medium |
| CN109978036A (en) * | 2019-03-11 | 2019-07-05 | 华瑞新智科技（北京）有限公司 | Target detection deep learning model training method and object detection method |
| CN110033417A (en) * | 2019-04-12 | 2019-07-19 | 江西财经大学 | A kind of image enchancing method based on deep learning |
| CN110276726A (en) * | 2019-05-13 | 2019-09-24 | 南昌大学 | A kind of image deblurring method based on the guidance of multichannel network prior information |
| CN111611907A (en) * | 2020-05-18 | 2020-09-01 | 沈阳理工大学 | Image-enhanced infrared target detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112287772B (en) | 2023-02-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106875381B (en) | Mobile phone shell defect detection method based on deep learning | |
| CN109583483B (en) | Target detection method and system based on convolutional neural network | |
| US20160364849A1 (en) | Defect detection method for display panel based on histogram of oriented gradient | |
| CN110348522B (en) | Image detection and identification method and system, electronic equipment, and image classification network optimization method and system | |
| CN111524137A (en) | Cell identification counting method and device based on image identification and computer equipment | |
| CN110826558B (en) | Image classification method, computer device, and storage medium | |
| US20210390282A1 (en) | Training data increment method, electronic apparatus and computer-readable medium | |
| KR20180109658A (en) | Apparatus and method for image processing | |
| CN113034514A (en) | Sky region segmentation method and device, computer equipment and storage medium | |
| CN113706481A (en) | Sperm quality detection method, sperm quality detection device, computer equipment and storage medium | |
| CN110334775B (en) | Unmanned aerial vehicle line fault identification method and device based on width learning | |
| CN112884721B (en) | Abnormality detection method, abnormality detection system and computer-readable storage medium | |
| CN114332942A (en) | Night infrared pedestrian detection method and system based on improved YOLOv3 | |
| CN114092467A (en) | Scratch detection method and system based on lightweight convolutional neural network | |
| CN111914706B (en) | Method and device for detecting and controlling quality of text detection output result | |
| CN110348353B (en) | Image processing method and device | |
| CN115830302B (en) | Multi-scale feature extraction fusion power distribution network equipment positioning identification method | |
| CN112287772B (en) | Fingerprint trace detection method, fingerprint detection device and computer readable storage medium | |
| CN111127400A (en) | Method and device for detecting breast lesions | |
| CN117011222A (en) | Cable buffer layer defect detection method, device, storage medium and equipment | |
| WO2021139447A1 (en) | Abnormal cervical cell detection apparatus and method | |
| CN113111850A (en) | Human body key point detection method, device and system based on region-of-interest transformation | |
| CN108830166B (en) | Real-time bus passenger flow volume statistical method | |
| CN114120423A (en) | Face image detection method and device, electronic equipment and computer readable medium | |
| CN112949494A (en) | Fire extinguisher position detection method, device, equipment and storage medium |
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 |