CN110110623A - A kind of face identification system and design method based on Android platform - Google Patents
A kind of face identification system and design method based on Android platform Download PDFInfo
- Publication number
- CN110110623A CN110110623A CN201910331068.0A CN201910331068A CN110110623A CN 110110623 A CN110110623 A CN 110110623A CN 201910331068 A CN201910331068 A CN 201910331068A CN 110110623 A CN110110623 A CN 110110623A
- Authority
- CN
- China
- Prior art keywords
- face
- android platform
- identification system
- design method
- method based
- 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.)
- Withdrawn
Links
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
-
- 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
-
- 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
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Collating Specific Patterns (AREA)
Abstract
The present invention relates to a kind of face identification system and design method based on Android platform, this system detects face using the algorithm based on Adaboost, Eigenface based on LDP realizes feature extraction and feature identification, it selects OpenCV computer vision library to realize Face datection and recognition of face, passes through the face identification system that JNI calls local OpenCV code to realize Android platform.
Description
Technical field
The present invention relates to informatizations, and in particular to a kind of face identification system and design based on Android platform
Method.
Background technique
Information security is increasingly paid close attention to by people, and authentication and identification technology become remarkable focus, biology
Feature identification technique and artificial intelligence technology constantly update development, wherein face recognition technology is because with concurrency, non-contact
Property, it is non-imposed, easy to operate the features such as, applied in every field more and more widely.Android system is to move at present
One of the mainstream operation system of dynamic equipment, occupies leading position in the Mobile operating system market share.As people are moving
The raising of dynamic realm information awareness of safety, carrying out recognition of face on a mobile platform has vast potential for future development, while also face
Face lot of challenges.The characteristics of present invention combination Android mobile terminal, studies the reality of the face identification system based on Android
It is existing, preferably meet the market demand in terms of mobile field information security.
Patent of invention content
A kind of face identification system and design method based on Android platform, which is characterized in that this system is used and is based on
The algorithm of Adaboost detects face, and the Eigenface based on LDP realizes feature extraction and feature identification, selects OpenCV meter
Face datection and recognition of face are realized in calculation machine vision library, pass through JNI and call local OpenCV code realization Android platform
Face identification system.
Specific embodiment
A kind of face identification system and design method based on Android platform, which is characterized in that this system is used and is based on
The algorithm of Adaboost detects face, and the Eigenface based on LDP realizes feature extraction and feature identification, selects OpenCV meter
Face datection and recognition of face are realized in calculation machine vision library, pass through JNI and call local OpenCV code realization Android platform
Face identification system.
Further, face recognition technology is a kind of identification technology based on physiological characteristic, extracts face by computer
Feature, and according to a kind of technology of these features progress authentication.The face recognition process of broad sense includes man face image acquiring
And pretreatment, Face datection and feature extraction and the comparison of face and identification three parts.
Further, Eigenface of this system selection based on LDP is realized that face characteristic is extracted and is identified with feature.
Further, image preprocessing, first positioning human eye.In order to improve location efficiency, first determine human eye in face figure
Position Approximate as in, is then based on this rough range, is mutually tied using gray-level projection with grey scale difference integral projection
The method of conjunction is accurately positioned human eye: M(y)=kphori(y)-Dhori(y), wherein k is coefficient, K phori(y) it is gray scale product
Divide projection, Dhori(y) it is grey scale difference integral projection.It followed by the geometric transformation of face image and cuts out, according to detected
Position of human eye, by image rotation, the means such as cut out, scale, so that human eye is alignment and does not include back in face image
Scape, forehead, ear and chin, and face image zooms to 70 × 70 fixed sizes by treated.It is separate histogram again
Equilibrium, this process enable to each face image contrast having the same and brightness.It is finally image smoothing,
Image smoothing can efficiently reduce the noise of image.
Further, Face datection, adaptive enhance (adaptive boosting, AdaBoost) is a kind of to need to supervise
The machine learning algorithm superintended and directed.Feature Selection and feature calculation determine the speed of service of AdaBoost algorithm.Viola et al. is proposed
AdaBoost Face datection algorithm based on Haar feature.Feature extraction is carried out using Haar feature herein.Based on feature
Detection can encode the state of selection area.Rectangular characteristic is to extract feature using rectangle to input picture.Haar
It is characterized in that some features being made of black and white rectangle, some characteristics of face can be easily described with rectangular characteristic, rectangle is special
Value indicative is two different its differences of rectangular area pixel sum.If image feature representation eye color is than the color of cheek upper end
It is deep.It can be with characteristic value come coding characteristic, characteristic value is defined as: V=Sum is black, and-Sum is white, wherein Sum is black, Sum is white respectively indicates
The pixel in black and white rectangular foot-print domain and.Using the concept of Viola et al. integral image proposed, rectangle spy can be accelerated
The calculating speed of sign.And then the characteristic value of Haar feature is calculated, the value in defining integration figure at position (x, y) is testing image
The sum of top and left side all pixels at position (x, y).S(x, y)=s(x, y 1)+i(x, y), C(x, y) and=c(x 1, y)+s
(x, y), wherein c(x, y) be value of the integrogram at (x, y) point, i(x, y) be original image pixel (x, y) at gray value, s
(x, y) indicate the cumulative of a line gray value and.S(x when initial, -1)=0, c(-1, y)=0.Weak Classifier is to positive and negative sample classification
Accuracy rate should be greater than 1/2, such training algorithm is finally restrained.One Weak Classifier h(x, f, p, θ): wherein 1 indicate people
Face, 0 indicates non-face.All sample characteristics at each feature f are calculated, and are ranked up.Then it scans one time and sequences
The characteristic value of sequence, so that it is determined that a last threshold value of feature f, is finally trained to a Weak Classifier.What all iteration obtained
Weak Classifier, and stack up according to-fixed weight, obtain a strong classifier.Multiple strong classifiers are connected, are obtained
To Adaboost cascade classifier.
Further, the human face detection and tracing system in Android platform is mainly by image capture module, face figure
As totally five modules form for preprocessing module, face detection module, face registration module and face recognition module etc..
Further, image capture module: carrying out Image Acquisition using Android platform camera, call the library Opencv,
It realizes and functions, the information of quick obtaining picture frame such as calls camera, the object of shooting is carried out auto-focusing, continuously taken pictures.
Further, illumination compensation, filtering and noise reduction processing facial image preprocessing module: are carried out to acquired image frame
It is handled with the processing of geometrical normalization etc..
Further, face detection module: pretreated image obtains face using Adaboost method for detecting human face,
And the facial image cut out is marked.
Further, face registration module: can input name after training, then can continuously record ten photos,
And extract 10 human face photos according to the step in Face datection and be saved in SD card, face name and number are write in order
Enter in faceN.txt file.
Further, face recognition module: face LDP feature is calculated according to tester's facial image, obtains recognition result.
If the face characteristic of tester is in the threshold value that we are arranged, otherwise the name of output identification face prompts face database
Middle no such person please ajust face cooperation identification.
Further, this system has used Adaboost Face datection algorithm and the recognition of face based on LDP eigenface to calculate
Method is realized in Android platform using OpenCV vision open source library.
The above description is only a preferred embodiment of the patent of the present invention, is not intended to limit the invention patent, all at this
Made any modifications, equivalent replacements, and improvements etc., should be included in the invention patent within the spirit and principle of patent of invention
Protection scope within.
Claims (9)
1. a kind of face identification system and design method based on Android platform, which is characterized in that this system is used and is based on
The algorithm of Adaboost detects face, and the Eigenface based on LDP realizes feature extraction and feature identification, selects OpenCV meter
Face datection and recognition of face are realized in calculation machine vision library, pass through JNI and call local OpenCV code realization Android platform
Face identification system.
2. a kind of face identification system and design method based on Android platform according to claim 1, feature exist
In Eigenface of this system selection based on LDP is realized that face characteristic is extracted and identified with feature.
3. a kind of face identification system and design method based on Android platform according to claim 1, feature exist
In this system is mainly by image capture module, facial image preprocessing module, face detection module, face registration module and people
Totally five modules form face identification module etc..
4. a kind of face identification system and design method based on Android platform according to claim 1, feature exist
In image capture module: carrying out Image Acquisition using Android platform camera, call the library Opencv, realize and call camera shooting
Head such as carries out auto-focusing to the object of shooting, continuously takes pictures at functions, the information of quick obtaining picture frame.
5. a kind of face identification system and design method based on Android platform according to claim 1, feature exist
In facial image preprocessing module: carrying out illumination compensation, filtering and noise reduction processing and geometrical normalization to acquired image frame
The processing such as processing.
6. a kind of face identification system and design method based on Android platform according to claim 1, feature exist
In face detection module: pretreated image obtains face using Adaboost method for detecting human face, and to the people cut out
Face image is marked.
7. a kind of face identification system and design method based on Android platform according to claim 1, feature exist
In face registration module: name can be inputted after training, then can continuously record ten photos, and according to Face datection
In step extract 10 human face photos and be saved in SD card, by face name and number write-in faceN.txt text in order
In part.
8. a kind of face identification system and design method based on Android platform according to claim 1, feature exist
In face recognition module: calculating face LDP feature according to tester's facial image, obtain recognition result.
9. a kind of face identification system and design method based on Android platform according to claim 1, feature exist
In this system has used Adaboost Face datection algorithm and the face recognition algorithms based on LDP eigenface, is regarded using OpenCV
Feel that open source library is realized in Android platform.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910331068.0A CN110110623A (en) | 2019-04-24 | 2019-04-24 | A kind of face identification system and design method based on Android platform |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910331068.0A CN110110623A (en) | 2019-04-24 | 2019-04-24 | A kind of face identification system and design method based on Android platform |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110110623A true CN110110623A (en) | 2019-08-09 |
Family
ID=67486433
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910331068.0A Withdrawn CN110110623A (en) | 2019-04-24 | 2019-04-24 | A kind of face identification system and design method based on Android platform |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110110623A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114677744A (en) * | 2022-04-11 | 2022-06-28 | 深圳市领天智杰科技有限公司 | Image algorithm for correcting sitting posture |
-
2019
- 2019-04-24 CN CN201910331068.0A patent/CN110110623A/en not_active Withdrawn
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114677744A (en) * | 2022-04-11 | 2022-06-28 | 深圳市领天智杰科技有限公司 | Image algorithm for correcting sitting posture |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Ahmed et al. | LBPH based improved face recognition at low resolution | |
CN108985134B (en) | Face living body detection and face brushing transaction method and system based on binocular camera | |
CN110838119B (en) | Human face image quality evaluation method, computer device and computer readable storage medium | |
WO2019061658A1 (en) | Method and device for positioning eyeglass, and storage medium | |
CN108898125A (en) | One kind being based on embedded human face identification and management system | |
Anand et al. | An improved local binary patterns histograms techniques for face recognition for real time application | |
KR20170006355A (en) | Method of motion vector and feature vector based fake face detection and apparatus for the same | |
Kalas | Real time face detection and tracking using OpenCV | |
CN104143086A (en) | Application technology of portrait comparison to mobile terminal operating system | |
Suma et al. | Real time face recognition of human faces by using LBPH and Viola Jones algorithm | |
CN111178130A (en) | Face recognition method, system and readable storage medium based on deep learning | |
Hebbale et al. | Real time COVID-19 facemask detection using deep learning | |
Kumar et al. | Face recognition attendance system using local binary pattern algorithm | |
Shrivastava et al. | Conceptual model for proficient automated attendance system based on face recognition and gender classification using Haar-Cascade, LBPH algorithm along with LDA model | |
CN113239739A (en) | Method and device for identifying wearing article | |
Ali et al. | A robust and efficient system to detect human faces based on facial features | |
Monwar et al. | Eigenimage based pain expression recognition | |
CN110110623A (en) | A kind of face identification system and design method based on Android platform | |
KR20080101388A (en) | A face detection algorithm based on a new modified census transform | |
WO2023158408A1 (en) | Face recognition method | |
Sai et al. | Student Attendance Monitoring System Using Face Recognition | |
CN110135362A (en) | A kind of fast face recognition method based under infrared camera | |
El-Sayed et al. | An identification system using eye detection based on wavelets and neural networks | |
CN111723612A (en) | Face recognition and face recognition network training method and device, and storage medium | |
Ribeiro et al. | Access control in the wild using face verification |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190809 |
|
WW01 | Invention patent application withdrawn after publication |