CN108446699A - Identity card pictorial information identifying system under a kind of complex scene - Google Patents
Identity card pictorial information identifying system under a kind of complex scene Download PDFInfo
- Publication number
- CN108446699A CN108446699A CN201810127310.8A CN201810127310A CN108446699A CN 108446699 A CN108446699 A CN 108446699A CN 201810127310 A CN201810127310 A CN 201810127310A CN 108446699 A CN108446699 A CN 108446699A
- Authority
- CN
- China
- Prior art keywords
- identity card
- image
- complex scene
- module
- identification
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- 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
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- 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
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to identity card pictorial information identifying system under a kind of complex scene, including image uploading module, image rotation module, identification card number identification module and identity card face extraction module, described image uploading module is uploaded for identity card picture；Described image rotary module is rotated for identity card picture character；The identification card number identification module is used for the extraction of identification card number position, identification under complex scene；The identity card face extraction module from picture for extracting face.The present invention can improve OCR discriminations under complicated shooting environmental.
Description
Technical field
The present invention relates to identity card identification technical fields, know more particularly to identity card pictorial information under a kind of complex scene
Other system.
Background technology
The concept of OCR (Optical Character Recognition, optical character identification) earlier than nineteen twenty generation just by
It proposes, is always research direction important in area of pattern recognition.
In recent years, with the quick update iteration of mobile device and the fast development of mobile Internet so that OCR has
It is more widely applied scene, from the character recognition of previous scanning file, is applied to picture character in natural scene till now
Identification, as identified the word in identity card, bank card, doorplate, bill and disparate networks picture.
Steps are as follows for OCR technique：
String localization first is then corrected into line tilt text, after being partitioned into individual character later, and is identified to individual character, finally
Semantic error correction is carried out based on statistical model (such as hidden Markov chain, HMM).It can be divided into three phases by processing mode：Pre- place
Reason stage, cognitive phase and post-processing stages.Wherein key is that pretreatment stage, the quality of pretreatment stage directly determine
Final recognition effect, therefore lower pretreatment stage detailed herein.
Three steps are contained in pretreatment stage：
(1) character area in picture is positioned, and the method that text detection is based primarily upon connected domain analysis, main thought are
By text color, brightness, marginal information clustered in the way of come quick separating character area and non-legible region, more flow
Two capable algorithms are respectively：Maximum extreme value stability region (MSER) algorithm and stroke width convert (SWT) algorithm, and in nature
Because being interfered by intensity of illumination, picture shooting quality and class character background in scene so that comprising very more in testing result
Non-legible region, and distinguish the main two methods of real character area from candidate region at present, judged with rule or light weight
The neural network model of grade distinguishes；
(2) text filed image flame detection, is based primarily upon rotation transformation and affine transformation；
(3) ranks segmentation extracts individual character, this step using word between ranks there are the feature in gap, pass through binaryzation
And ranks cut-point is found out in the projected.
Invention content
Technical problem to be solved by the invention is to provide identity card pictorial information identifying system, energy under a kind of complex scene
It is enough to improve OCR discriminations under complicated shooting environmental.
The technical solution adopted by the present invention to solve the technical problems is：Identity card picture under a kind of complex scene is provided to believe
Cease identifying system, including image uploading module, image rotation module, identification card number identification module and identity card face extraction mould
Block；Described image uploading module is uploaded for identity card picture；Described image rotary module is rotated for identity card picture character；
The identification card number identification module is used for the extraction of identification card number position and identification under complex scene；The identity card face extraction mould
Block from picture for extracting face.
Described image rotary module extracts straight line by Hough transform, is calculated separately since straight line apical pixel point more
Distance of the corresponding origin of a angle to straight line；The pixel above-mentioned steps for traversing whole image, find out the most distance of repetition,
The linear equation of the line correspondences is obtained, finally obtains rotation angle.
The identification card number identification module converts complex scene image to binary picture by self-adaption binaryzation first
Picture is removing image noise by mean filter, and then carrying out burn into expansion to image combines zonule different on image
Get up；Finding strip profile, as identification card number position by opencv, by tesseract increase income ocr softwares know
Do not go out corresponding identification card number, text correction finally is carried out to the digital alphabet identified, exports result.
It is described when converting complex scene image to binary image by self-adaption binaryzation on pixel (x, y) point periphery
The region for choosing a b × b, calculates the weighted average W (x, y) in this region b × b, and weighted mean W (x, y) and one are fixed
Parameter subtracts each other to obtain threshold value T (x, y).
The mean filter removes image noise：One template, the template are selected to pending current pixel
For its neighbouring several pixels composition, the value of original pixel is substituted with the mean value of template.
It is described that image progress burn into expansion is combined zonule different on image specially：In the small of artwork
It takes local minimum to carry out corrosion treatment in region, local maximum is taken to carry out expansion process in the zonule of artwork, use
First expand the processing mode corroded again, wherein the number of expansion process is 15, and the number of corrosion treatment is 1.
It is described strip profile is found by opencv to be specially：Length-width ratio, breadth length ratio are found in the profile extracted
Less than 1.3 and area is less than 10000 profile.
The identity card face extraction module is loaded trained first by the Face datection of Haar features in opencv
Harr files input corresponding identity card picture, after its gray processing, call the position of Harr files output facial image.
Advantageous effect
Due to the adoption of the above technical solution, compared with prior art, the present invention having the following advantages that and actively imitating
Fruit：Invention increases to (such as uneven illumination has sundries) identification card number abstraction function under complicated photographed scene.The present invention operates
Simply, facilitate deployment；This system can be applied to security, financial field, can improve ID card information under complicated photographed scene
Extraction, can greatly improve discrimination.
Description of the drawings
Fig. 1 is the system block diagram of the present invention；
Fig. 2A -2B are the internal structure charts of the present invention.
Specific implementation mode
Present invention will be further explained below with reference to specific examples.It should be understood that these embodiments are merely to illustrate the present invention
Rather than it limits the scope of the invention.In addition, it should also be understood that, after reading the content taught by the present invention, people in the art
Member can make various changes or modifications the present invention, and such equivalent forms equally fall within the application the appended claims and limited
Range.
Embodiments of the present invention are related to identity card pictorial information identifying system under a kind of complex scene, as shown in Figure 1, packet
Image uploading module, image rotation module, identification card number identification module and identity card face extraction module are included, described image uploads
Module is uploaded for identity card picture；Described image rotary module is rotated for identity card picture character；The identification card number is known
Other module is used for the extraction of identification card number position, identification under complex scene；The identity card face extraction module is used for from picture
Extract face.
As shown in Figure 2 A, present embodiment be subject to user upload identity card picture and portrait photo's (certificate photo) be
Standard identifies identification card number above.Since the picture that client uploads is likely to be inclination or reversing, for the ease of knowing below
Not, spin step is increased, the picture after rotating through obtains field above by ocr.
It is to tilt, or upside down that image rotation, which is directed to have some pictures in the picture of user's upload,.This implementation
Image rotation module in mode is corrected picture in such a way that opencv rotates and adjusts angle.
What present embodiment was mainly used is the method for opencv lines detections, then finds out the angle of inclination of straight line, at this
In the method for lines detection be Hough transform.
Any point O (x, y) in rectangular coordinate system, any one straight line by O can all meet Y=kX+b (except vertical
The straight line of straight X-axis).Due to this special circumstances, so coordinate system is converted to polar coordinate system to meet this case.
In polar coordinate system, arbitrary straight line can be indicated with ρ=xCos θ+ySin θ.
Assuming that having straight line in the image of a width 10*10, angle is calculated separately since graph line apical pixel point
The degree distance of corresponding origin to straight line when being 180 °, 135 °, 90 °, 45 °, 0 °.It is repeated in the pixel of traversal whole image rigid
The step of, finds out the most distance of repetition, has just obtained corresponding linear equation, and obtain angle.
When a width figure finds out a plurality of straight line, take the highest angle of angular frequency as the rotation angle of image.
What present embodiment was mainly used is the method for opencv self-adaption binaryzations, and this method is for handling different illumination
Under image binaryzation problem.
Adaptive binary conversion treatment is different from the processing of fixed threshold, and the threshold value of each pixel depends on its neighbouring picture
Plain gray scale, the threshold value T (x, y) that (x, y) is put in order to obtain, it would be desirable to carry out following processing.
(1)：The region of a b × b is chosen on this pixel periphery, wherein b is that user specifies.
(2)：Calculate the weighted average in this region b × b.OpenCV provides two methods and calculates this weighted mean, and one
Kind it is arithmetic mean method, another kind is Gauss weighted mean method, and the nearlyr weight in distance areas center is more when the latter will calculate mean value
Greatly.Obtained weighted mean is calculated as W (x, y) by us.
(3)：Subtract each other above-mentioned weighted mean and a preset parameter to obtain threshold value T (x, y), this preset parameter is set as
Param1, the then threshold value that (x, y) is put can be calculated with following formula：
T (x, y)=W (x, y)-param1
B is 35, param1 35 in present embodiment.
What present embodiment was mainly used is the method for opencv mean filters, and this method is for removing image noise.
Mean filter：To pending current pixel, it is its several neighbouring pixel groups to select a template, the template
At the method for substituting the value of original pixel with the mean value of template.
In above formula, M represents template size, and f (x, y) represents original image pixel, and g (x, y) represents image slices after mean filter
Element.Such as the neighborhood pixels that a following formula left side 1~8 is (x, y), the formula right side is weight coefficient matrix template.
Then corresponding export is：
G=(f (x-1, y-1)+f (x, y-1)+f (x+1, y-1)+f (x-1, y)+f (x, y)+f (x+1, y)+f (x-1, y+
1)+f(x,y+1)+f(x+1,y+1))/9
What present embodiment was mainly used is the method for opencv Image erosions expansion, and the purpose of this method will scatter
Image accumulates one piece convenient for extraction profile.
The effect of corrosion is that picture " is reduced ", and principle is to take local minimum for example with b in the zonule of artwork
× b matrixes are unit.Because being binary picture, only 0 and 255, so in zonule there are one be 0 pixel just be 0；Phase
The anti-effect expanded is that picture " is become fat ", only need to take local maximum in the zonule of artwork.
Present embodiment first expands post-etching, and according to 3 × 3 sizes of acquiescence, it is secondary to expand 15 times, corrode 1 for zonule.
The method that present embodiment mainly uses opencv extraction profiles, the purpose of this method is to find out identification card number position
It sets.Length-width ratio, breadth length ratio are found in the profile extracted less than 1.3 and profile of the area less than 10000 is exactly identification card number
Position.
Present embodiment mainly uses tesseract and increases income ocr softwares to identify identification card number.
Compared to other expensive business ocr engines, tesseract can be compatible with more multilingual character recognition,
Therefore also without providing very detailed character repertoire for each language.But it is that it provides a character repertoire training method, it can
With allow it is user-defined go training needed for language character, it is highly effective for the text identification of the language there are many font,
Recognition correct rate can be greatly improved.
Pass through subprocess call instructions in python:Tesseract filename file, wherein filename
File is picture name.
As shown in Fig. 2, what present embodiment mainly used is Face datection based on haar features in opencv, this method
Position for obtaining face in ID Card Image.
Used herein is cv2.CascadeClassifier, this is the Cascade for initializing opencv
Classification, its effect are exactly to generate a detector, and the foundation of detection is all stored in that representated by parameter
In a xml document, this xml document can obtain in opencv-github, official provide also have eyes, tree etc. other
The identification data of object, these data be exactly one by one image train come.
After classifier training is complete, so that it may with (identical with training sample applied to the area-of-interest in input picture
Size) detection.Detect that target area grader output is 1, otherwise output is 0.In order to detect whole sub-picture, can scheme
The mobile search window as in, detects each position to determine possible target.In order to search for different size of target object, point
Class device is designed to carry out size change, more more effective than changing the size of image to be checked in this way.So in order to
Detect the target object of unknown size in image, scanner program usually require with the search window of different proportion size to picture into
Row scans several times.
It is not difficult to find that invention increases extracted to (such as uneven illumination has sundries) identification card number under complicated photographed scene
Function.The present invention is easy to operate, facilitates deployment；This system can be applied to security, financial field, can improve complicated shooting field
Identity card information extraction under scape can greatly improve discrimination.
Claims (8)
1. identity card pictorial information identifying system under a kind of complex scene, which is characterized in that revolved including image uploading module, image
Revolving die block, identification card number identification module and identity card face extraction module；Described image uploading module is used for identity card picture
It passes；Described image rotary module is rotated for identity card picture character；The identification card number identification module is used under complex scene
Identification card number position is extracted and identification；The identity card face extraction module from picture for extracting face.
2. identity card pictorial information identifying system under complex scene according to claim 1, which is characterized in that described image
Rotary module extracts straight line by Hough transform, and the corresponding origin of multiple angles is calculated separately since straight line apical pixel point
To the distance of straight line；The pixel above-mentioned steps for traversing whole image, find out the most distance of repetition, obtain the line correspondences
Linear equation finally obtains rotation angle.
3. identity card pictorial information identifying system under complex scene according to claim 1, which is characterized in that the identity
Card identification module converts complex scene image to binary image by self-adaption binaryzation first, is passing through mean filter
Image noise is removed, then carrying out burn into expansion to image combines zonule different on image；Passing through opencv
Strip profile, as identification card number position are found, corresponding identity card is being identified by tesseract ocr softwares of increasing income
Number, text correction finally is carried out to the digital alphabet identified, exports result.
4. identity card pictorial information identifying system under complex scene according to claim 3, which is characterized in that described to pass through
When self-adaption binaryzation converts complex scene image to binary image the area of a b × b is chosen on pixel (x, y) point periphery
Domain calculates the weighted average W (x, y) in this region b × b, subtracts each other weighted mean W (x, y) and a preset parameter to obtain threshold value T
(x,y)。
5. identity card pictorial information identifying system under complex scene according to claim 3, which is characterized in that the mean value
Filtering removes image noise：One template selected to pending current pixel, which is its neighbouring several
Pixel forms, and the value of original pixel is substituted with the mean value of template.
6. identity card pictorial information identifying system under complex scene according to claim 3, which is characterized in that described pair of figure
Zonule different on image is combined specially as carrying out burn into expansion：Local Minimum is taken in the zonule of artwork
Value carries out corrosion treatment, takes local maximum to carry out expansion process in the zonule of artwork, using first expanding the place corroded again
Reason mode, wherein the number of expansion process is 15, and the number of corrosion treatment is 1.
7. identity card pictorial information identifying system under complex scene according to claim 3, which is characterized in that described to pass through
Opencv finds strip profile：Length-width ratio is found in the profile extracted, breadth length ratio is less than less than 1.3 with area
10000 profile.
8. identity card pictorial information identifying system under complex scene according to claim 1, which is characterized in that the identity
Witness's face extraction module loads trained Harr files, input pair first by the Face datection of Haar features in opencv
The identity card picture answered calls the position of Harr files output facial image after its gray processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810127310.8A CN108446699A (en) | 2018-02-08 | 2018-02-08 | Identity card pictorial information identifying system under a kind of complex scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810127310.8A CN108446699A (en) | 2018-02-08 | 2018-02-08 | Identity card pictorial information identifying system under a kind of complex scene |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108446699A true CN108446699A (en) | 2018-08-24 |
Family
ID=63191869
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810127310.8A Pending CN108446699A (en) | 2018-02-08 | 2018-02-08 | Identity card pictorial information identifying system under a kind of complex scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108446699A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109376735A (en) * | 2018-08-31 | 2019-02-22 | 百度在线网络技术（北京）有限公司 | Identity information extracting method, device, electronic equipment and storage medium |
| CN109697440A (en) * | 2018-12-10 | 2019-04-30 | 浙江工业大学 | A kind of ID card information extracting method |
| CN110263889A (en) * | 2019-06-24 | 2019-09-20 | 合肥盈川信息技术有限公司 | A kind of special trade network monitoring management system |
| CN110348326A (en) * | 2019-06-21 | 2019-10-18 | 安庆师范大学 | The family health care information processing method of the identification of identity-based card and the access of more equipment |
| CN110516665A (en) * | 2019-08-23 | 2019-11-29 | 上海眼控科技股份有限公司 | Identify the neural network model construction method and system of image superposition character area |
| CN111046899A (en) * | 2019-10-09 | 2020-04-21 | 京东数字科技控股有限公司 | Method, device and equipment for identifying authenticity of identity card and storage medium |
| CN112686247A (en) * | 2020-12-10 | 2021-04-20 | 广州广电运通金融电子股份有限公司 | Identification card number detection method and device, readable storage medium and terminal |
| CN112801232A (en) * | 2021-04-09 | 2021-05-14 | 苏州艾隆科技股份有限公司 | Scanning identification method and system applied to prescription entry |
| CN113095329A (en) * | 2021-04-02 | 2021-07-09 | 重庆至道医院管理股份有限公司 | Working method for separating doctor-patient experience abnormal image data through big data platform |
| CN115471919A (en) * | 2022-09-19 | 2022-12-13 | 江苏至真健康科技有限公司 | Filing method and system based on portable mydriasis-free fundus camera |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105528604A (en) * | 2016-01-31 | 2016-04-27 | 华南理工大学 | Bill automatic identification and processing system based on OCR |
| CN105528602A (en) * | 2015-10-30 | 2016-04-27 | 小米科技有限责任公司 | Region identification method and device |
| CN105701488A (en) * | 2016-01-01 | 2016-06-22 | 广州恒巨信息科技有限公司 | Identity card identification method |
| CN106156712A (en) * | 2015-04-23 | 2016-11-23 | 信帧电子技术（北京）有限公司 | A kind of based on the ID (identity number) card No. recognition methods under natural scene and device |
| CN106682629A (en) * | 2016-12-30 | 2017-05-17 | 佳都新太科技股份有限公司 | Identification number identification algorithm in complicated background |
| CN107122775A (en) * | 2017-03-29 | 2017-09-01 | 南京航空航天大学 | A kind of Android mobile phone identity card character identifying method of feature based matching |
-
2018
- 2018-02-08 CN CN201810127310.8A patent/CN108446699A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106156712A (en) * | 2015-04-23 | 2016-11-23 | 信帧电子技术（北京）有限公司 | A kind of based on the ID (identity number) card No. recognition methods under natural scene and device |
| CN105528602A (en) * | 2015-10-30 | 2016-04-27 | 小米科技有限责任公司 | Region identification method and device |
| CN105701488A (en) * | 2016-01-01 | 2016-06-22 | 广州恒巨信息科技有限公司 | Identity card identification method |
| CN105528604A (en) * | 2016-01-31 | 2016-04-27 | 华南理工大学 | Bill automatic identification and processing system based on OCR |
| CN106682629A (en) * | 2016-12-30 | 2017-05-17 | 佳都新太科技股份有限公司 | Identification number identification algorithm in complicated background |
| CN107122775A (en) * | 2017-03-29 | 2017-09-01 | 南京航空航天大学 | A kind of Android mobile phone identity card character identifying method of feature based matching |
Non-Patent Citations (7)
| Title |
|---|
| DEERLUX: "利用python open实现图像自适应二值化", 《HTTPS://BLOG.CSDN.NET/DEERLUX/ARTICLE/DETAILS/48477219》 * |
| OPENCV: "OpenCV形状识别学习总结", 《HTTP://WWW.VOIDN.COM/ARTICLE/P-MXQOSALM-RD.HTML》 * |
| 候纯: "不良图像检测***的设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 孙贺: "***汉信码的识别算法与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 杜刚: "银行票据识别***的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 程育恒: "基于Tesseract开源OCR引擎的证件识别***的设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 钟侠: "基于Hough变换的票据图像倾斜校正", 《常州大学学报（自然科学版）》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109376735A (en) * | 2018-08-31 | 2019-02-22 | 百度在线网络技术（北京）有限公司 | Identity information extracting method, device, electronic equipment and storage medium |
| CN109697440A (en) * | 2018-12-10 | 2019-04-30 | 浙江工业大学 | A kind of ID card information extracting method |
| CN110348326A (en) * | 2019-06-21 | 2019-10-18 | 安庆师范大学 | The family health care information processing method of the identification of identity-based card and the access of more equipment |
| CN110263889A (en) * | 2019-06-24 | 2019-09-20 | 合肥盈川信息技术有限公司 | A kind of special trade network monitoring management system |
| CN110516665A (en) * | 2019-08-23 | 2019-11-29 | 上海眼控科技股份有限公司 | Identify the neural network model construction method and system of image superposition character area |
| CN111046899A (en) * | 2019-10-09 | 2020-04-21 | 京东数字科技控股有限公司 | Method, device and equipment for identifying authenticity of identity card and storage medium |
| CN111046899B (en) * | 2019-10-09 | 2023-12-08 | 京东科技控股股份有限公司 | Identification card authenticity identification method, device, equipment and storage medium |
| CN112686247A (en) * | 2020-12-10 | 2021-04-20 | 广州广电运通金融电子股份有限公司 | Identification card number detection method and device, readable storage medium and terminal |
| CN113095329A (en) * | 2021-04-02 | 2021-07-09 | 重庆至道医院管理股份有限公司 | Working method for separating doctor-patient experience abnormal image data through big data platform |
| CN112801232A (en) * | 2021-04-09 | 2021-05-14 | 苏州艾隆科技股份有限公司 | Scanning identification method and system applied to prescription entry |
| CN115471919A (en) * | 2022-09-19 | 2022-12-13 | 江苏至真健康科技有限公司 | Filing method and system based on portable mydriasis-free fundus camera |
| CN115471919B (en) * | 2022-09-19 | 2023-09-12 | 江苏至真健康科技有限公司 | Filing method and system based on portable mydriasis-free fundus camera |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108446699A (en) | Identity card pictorial information identifying system under a kind of complex scene | |
| CN111401372B (en) | Method for extracting and identifying image-text information of scanned document | |
| Romero et al. | Unsupervised deep feature extraction for remote sensing image classification | |
| Lukic et al. | Leaf recognition algorithm using support vector machine with Hu moments and local binary patterns | |
| He et al. | Multi-patch convolution neural network for iris liveness detection | |
| Akhtar et al. | A comparative evaluation of local feature descriptors for deepfakes detection | |
| CN108133212A (en) | A kind of quota invoice amount identifying system based on deep learning | |
| Malhotra et al. | Fingerphoto authentication using smartphone camera captured under varying environmental conditions | |
| CN112052831A (en) | Face detection method, device and computer storage medium | |
| CN108960088A (en) | The detection of facial living body characteristics, the recognition methods of specific environment | |
| Elaskily et al. | Comparative study of copy-move forgery detection techniques | |
| Wang et al. | Hand vein recognition based on multi-scale LBP and wavelet | |
| Suryani et al. | Offline signature recognition and verification system using efficient fuzzy kohonen clustering network (EFKCN) algorithm | |
| Wang et al. | Hyperspectral image classification based on PCA network | |
| Bui et al. | Selecting automatically pre-processing methods to improve OCR performances | |
| Liu et al. | Iris recognition in visible spectrum based on multi-layer analogous convolution and collaborative representation | |
| Majumder et al. | A tale of a deep learning approach to image forgery detection | |
| Ren et al. | A new unsupervised convolutional neural network model for Chinese scene text detection | |
| Nanni et al. | RegionBoost learning for 2D+ 3D based face recognition | |
| Diaa | A Deep Learning Model to Inspect Image Forgery on SURF Keypoints of SLIC Segmented Regions | |
| Ovodov | Optical Braille recognition using object detection neural network | |
| CN110795995B (en) | Data processing method, device and computer readable storage medium | |
| Rana et al. | Use of image enhancement techniques for improving real time face recognition efficiency on wearable gadgets | |
| Javidnia et al. | Palmprint as a smartphone biometric | |
| Lin et al. | Face detection based on skin color segmentation and SVM classification |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180824 |