Face Vector API with Image Quality | Post Request


Face Vector API is the base API used in all of the FaceX facial recognition applications. The basic function of the FaceVector API is to convert the provided face into a 128-Vector Matrix template which can be used for recognition.

But Facial Recognition accuracy depends on the quality of the image being used for recognition¬† (Please refer to the article “Image Quality for Facial Recognition“), FaceX offers a post request for Face Vector API using which you would be able to determine if the image being used matches the minimum requirement for facial recognition.

Three attributes are analysed by this API before providing a response: Face Size, Lighting, Pose.

Image Requirement

  1. We recommend an image resolution no higher than 1024x, since it could slow down the request process. Supported image formats are JPEG/PNG format.

Request URL


Note:  The API will require a greater response time than the normal face vector post request





quality String





user_id String Your valid User ID

(as shown in your user portal when you log in)

content-type multipart/form-data (if using image file)

application/json (if using Base64/URL)

Note: Your User ID will be valid for Face Vector API only if you have an active FaceAPI plan





img file or String An image file, supported files jpeg, png or Base64 or Image URL


If the image quality matches all the required quality threshold’s, the output provided by the FaceVector API is a 128-Vector Matrix which can be used as the face template for the face provided.

If the image quality does not match the required threshold then one of the three errors will be returned by the API


Error Received

Required Threshold

Image Size “Face too Small” The size of the Face provided to the Vector API should be minimum 60×60
Lighting “Low Illumination” Illumination of the image should be a minimum of 70
Pose “Incorrect Pose” The threshold for FaceAPI is 50 yaw

Performing Facial Recognition Using Face Vector

There are different ways you can use the Face Vector API to do facial recognition, read the following articles to get started

Related Articles
Post a Comment