GA/T 1325-2017Security protection--Face recognition applications--Specifications for acquisition of video and image (English PDF)
安全防范 人脸识别应用 视频图像采集规范
This is a limited preview
Buy now to download the full PDF (15 pages)
Need quotation for your management?
Get a formal quotation for GA/T 1325-2017 in 30 minutes.
Issued by
Ministry of Public Security
Level / Type
National · Recommended
Issue date
October 8, 2017
Implementation date
December 1, 2017
Scope
GA/T 1325-2017 is the English-translated version of 安全防范 人脸识别应用 视频图像采集规范.
GA/T 1325-2017 — This standard specifies the technical requirements and test methods for video or image acquisition for face recognition in security applications.
This standard is applicable to the scheme design, equipment selection, construction and installation of video or image acquisition for face recognition in security applications.
Engineering acceptance. Face recognition application systems in other fields can be used as reference.
Found what you need?
Document preview — GA/T 1325-2017
National Standard of the People's Republic of China
- ICS
- 13.310
- Classification
- A 91
Issued by: Ministry of Public Security
Contents
- 1 Scope
- 2 Normative references
- 3 Terms and definitions
- 4.3 Acquiring images
- 5 Test method
- 5.1 Collection environment
- 5.2 Acquisition equipment
- 5.3 Acquiring images
1 Scope
This standard specifies the technical requirements and test methods for video or image acquisition for face recognition in security applications.
This standard is applicable to the scheme design, equipment selection, construction and installation of video or image acquisition for face recognition in security applications.
Engineering acceptance. Face recognition application systems in other fields can be used as reference.
2 Normative references
The following documents are indispensable for the application of this document. For dated reference documents, only the dated version applies to this article Pieces. For undated references, the latest version (including all amendments) applies to this document.
GB/T 25724-2010 Security and surveillance digital video and audio coding and decoding technical requirements GB 50396-2007 Code for design of entrance and exit control system engineering GA/T 367-2001 Technical requirements for video security monitoring system GA 461-2004 Technical requirements for digital photos used in resident ID card preparation GA/T 706-2007 Technical requirements and collection specifications for digital photographs of suspects GA/T 893-2010 Application terminology of security biometric identification GA/T 922.2-2011 Security Face Recognition Application System Part 2: Face Image Data GA/T 1126-2013 Technical requirements for near-infrared face recognition equipment GA/T 1127-2013 General technical requirements for security video surveillance cameras GA/T 1180-2014 Technical Requirements for Entry and Exit Digital Photos GA/T 1326-2017 Security Protection Face Recognition Application Program Interface Specification
3 Terms and definitions
The following terms and definitions defined in GA/T 893-2010 are suitable for this document.
Face recognition application video image acquisition videoandimageacquisitionforfacerecognitionapplications the process of obtaining videos or images that may contain facial information for face recognition.
Face recognition video image acquisition equipment deviceofvideoandimageacquisitionforfacerecognition Various devices for face recognition video or image capture.
Note. Including facial recognition cameras and cameras.
Acquisitionsubject
A sample of people whose face images meet certain requirements in the field of view.
a) Number of pixels. 1.3 million pixels or more, no less than 1280 pixels horizontally, no less than 720 pixels vertical, the larger the field of view, the image the more prime numbers;
b) Shutter adjustment. the lowest speed is less than 1/100s;
c) Sampling frame rate. the camera is not less than 10 frames/s, and the camera should have continuous shooting function;
d) The camera/camera with face detection should be able to automatically select the best face image between frames, and it should be combined with portrait index face image output Features.
4.2.2 Lens
The lens used for dynamic capture selection should meet the following requirements.
a) The maximum aperture of the auto iris lens is not less than F=1.4;
b) The optional lens makes the field of view space XYZ of the collected object's face area as follows, to meet the requirements of 4.1.1 and GA/T 922.2-2011
4.2.1 Requirements.
---600mm<=X<=2800mm;
---450mm<=Y<=2100mm;
---Z>=800mm.
c) Refer to formula (A.3) for the selection of lens focal length f. See Appendix C for design examples.
4.2.3 Interface
The physical and command interface should meet the following requirements.
a) Physical interface. meet the requirements of 5.1.2 in GA/T 1127-2013;
b) Command interface. meet the interface requirements of face acquisition equipment in 5.1.4 of GA/T 1326-2017.
4.3 Acquiring images
4.3.1 File format
The output file format should meet the following requirements.
a) Video compression coding. H.264, H.265, MPEG4, MJPEG or SVAC;
b) Image file format. BMP, RAW, JPEG or JPEG2000, the compression ratio of JPEG and JPEG2000 files should not be greater than 25 times.
4.3.2 Image quality
The quality of the output face image is determined by 5.1 in GA/T 1344-2016.According to the different face image library deployed, it conforms to GA 461-the frontal photograph requirements of Chapter 4 in 2004, 4.2 in GA/T 1180-2014 and 6.1 in GA/T 706-2007.
a) The distance between the two eyes. the registered face image should meet the 60 pixel requirement of 4.1.1 in GA/T 922.2-2011, and the face image should be recognized Meet the 30 pixel requirements of 4.2.1 in GA/T 922.2-2011;
b) Face pitch angle. The registered face image should meet the requirements of GA/T 922.2-2011 4.1.3 not greater than ±10°, and recognize the face the image should meet the requirements of GA/T 922.2-2011 in 4.2.2 not greater than ±20°, and there should be auxiliary measures to ensure that the face angle meets the requirements Claim;
c) Distortion rate eta. not more than 1%;
d) Grayscale. the dynamic grayscale range is not less than 180 levels;
e) Clarity. The face is clear, without obvious tailing, jitter and other motion blur;
f) Noise. The image has no obvious noise;
g) Others. Other requirements specified in Chapter 4 of GA/T 922.2-2011.
4.3.3 Image processing
The post-processing of the captured image in terms of color and brightness is in accordance with the following requirements.
a) Color adjustment. The color of the image can be adjusted appropriately until the skin color of the face is natural and true. When the image is seriously color cast, it should not be forcibly adjusted its color should be recollected after adjusting the white balance;
b) Brightness and highlight processing. The brightness can be adjusted appropriately until the skin color of the face is natural and true, and the image is seriously underexposed or overexposed at this time, the brightness should not be forcibly adjusted, and the exposure parameters of the equipment should be adjusted and then collected again.
5 Test method
5.1 Collection environment
5.1.1 Installation location
The installation locations of different dynamic acquisition equipment for testing are as follows.
a) Measure the measured distance L, installation height H1 and pitch angle A of the dynamic collection device from the collection object, refer to Table A.2 and Table A.3 and Table A.4, judge whether it meets the requirements of a) and b) in 4.1.1;
b) Observe the installation height H1 of the dynamic acquisition equipment in the entrance and exit control scene from the ground, and judge whether it meets the requirements in 4.1.1 c).
5.1.2 Ambient lighting
Observe the lighting conditions of the area around the collection object and the face area, and use a visible light meter to test the area around the collection object and the face Area light intensity, judge whether it meets the requirements of 4.1.2.
5.2 Acquisition equipment
5.2.1 Video/Camera
View the camera/camera inspection report installed on site for dynamic acquisition, check the consistency of the acquisition equipment model and the inspection report, Verify the number of pixels of the image sensor, shutter adjustment speed, and sampling frame rate indicators, identify the optimal selection of face images between frames and index face images with both portraits Like output function, judge whether it meets the requirements of a), b), c) and d) in 4.2.1.
5.2.2 Lens
View the inspection report of the lens equipped with the dynamic acquisition equipment installed on the site, check the consistency of the lens model and the inspection report, and verify the largest lens Aperture and focal length indicators, to determine whether they meet the requirements of a), b) and c) in 4.2.2.
5.2.3 Interface
Visually inspect the physical interface to determine whether it meets the requirements in 4.2.3 a).
Send the "device initialization function", "device connection function", etc. of the 11 face collection functions of GA/T 1326-2017 to the collection device no less than 3 random functions, check the command interface of the dynamic acquisition device, and judge whether it meets the requirements in 4.2.3 b).
5.3 Acquiring images
5.3.1 File format
Check the output file format as follows.
a) Check the compression encoding type of the face video file under the specified storage path to determine whether it meets the requirements of a) in 4.3.1;
b) Check the output format of the face image file under the specified storage path, and calculate the ratio of the file length before compression to the file length after compression Value, to determine whether it meets the requirements of b) in 4.3.1.
5.3.2 Image quality
Test the image quality as follows.
a) Collect a front view of the object in the field of view space at the actual measurement distance L from the face recognition video image acquisition device.
According to the face image, test the number of pixels between the eyes of the collected object's face image and the pitch angle A to determine whether it meets the requirements in 4.3.2
a) and b) requirements;
b) Collect a standard test card M image, make it fill the high-definition display, calculate according to the formula (B.1) in Appendix B, and judge it to be Whether it meets the requirements of c) in 4.3.2;
c) Collect a standard test card M image, observe the dynamic gray range of the standard test card M image histogram, and judge whether it meets 4.3.2 d) requirements;
d) Visually inspect the sharpness and noise of the collected face image in 5.3.2a), and judge whether it meets the requirements of e), f) and g) in 4.3.2.
5.3.3 Image processing
Visually inspect the color adjustment, brightness and highlight processing effect of the post-processed image to determine whether it meets the requirements of a) and b) in 4.3.3.
......
This preview omits tables, figures, formulas and parts of the technical clauses. The complete document — 15 pages — is available in the English PDF.
Referenced standards
How to Download GA/T 1325-2017
- 1
Add to cart
Click "Download PDF" on this page and choose "Buy this standard". You can add more standards before checkout.
- 2
Checkout
Enter your email and billing details. Payment is processed securely by Stripe (cards or bank transfer). Prefer bank details? Request a quotation (min. order $300).
- 3
Instant delivery (0–9 sec)
Delivery is automatic: within seconds of payment you'll receive an email with a secure download link. The link stays valid for 72 hours.
- 4
Invoice included
A tax invoice is attached to the confirmation email. Need a custom invoice? Contact us.
Related Standards
GB 50396-2007 — Code of design for access control systems engineering
GA/T 2322-2025 — Forensic sciences-Code of practice for latent fingerprint development by superglue of humidity and heat
GA/T 2323-2025 — Forensic sciences-Examination methods for thiosulfate ions in biologicasamples - LC-MS
Secure payment via Stripe
Payments accepted
GA/T 1325-2017
$484.00