@smcgann/node-red-face-vectorization-plus

A Node-RED node that vectorizes facial images using AI.

You can use the output of this node with 🔗 @smcgann/node-red-cosine-similarity-plus as part of a face recognition flow.

This node is based on 🔗 @good-i-deer/node-red-contrib-face-vectorization

Key Changes

✔ Added Typed Input for incoming msg property.
✔ Improved performance.
✔ Updated dependencies.
✔ Removed unnecessary dependencies.
✔ Easier integration into Node-RED flows.

Installation

Either use the Edit Menu - Manage Palette option to install, or run the following command in your Node-RED user directory - typically ~/.node-red

cd ~/.node-red
npm install @smcgann/node-red-face-vectorization-plus

Restart your Node-RED instance

Input Properties

👤 Single Image

• The input can be one of the following:
  • Buffer: A Buffer containing the image data.
  • File Path: A string representing the file path to the image.

👥 Image Array

• The input should be an array of Buffers, each containing the image data for one face.

Node Properties

🏷️ Name

• The name displayed in the Node-RED editor.

⚙️ Property

• Incomming msg property to use ( Default msg.payload )

📥 Input Type

• You can choose whether to input a single image or multiple images.
  • Single Image: Insert one image buffer, file path, or URL.
  • Multiple Images: Insert multiple image buffers in the form of an array.

📤 Return Type

• You can choose how to receive the vector result:
  • Array of Arrays: Receive the vector result as an array.
  • Text File: Save the vector result as a file. The data will be saved as an array of vector arrays of faces. When this option is selected, the Path and Method properties are activated. It is recommended to save the data as a text file.

📂 Path

• Specify the desired file path, including the file name and extension, when saving the vector data as a text file. If an absolute path is not specified, it will be determined based on the execution space.

🔧 Method

• When saving a file, you can choose whether to:
  • Overwrite: Overwrite the existing file.
  • Add: Append to the existing file.
  If the file does not already exist, it will be created.

📤 Output Properties

Array of Arrays

• Vectors for faces are output in the form of an array to msg.payload.

Text File

• Save vector data in file format. Depending on the method, overwrite or add to the file.

✍️ Authors

S.McGann → Modified Version.

GOOD-I-DEER in SSAFY(Samsung Software Academy for Youth) 9th

• Kim Jaea
• Yi Jong Min
• Lee Deok Yong
• Lee Che Lim
• Lee Hyo sik
• Jung Gyu Sung

📜 Copyright and license

S.McGann → Modified Version
Copyright Samsung Automation Studio Team under the Apache 2.0 license

Reference

• Node-RED Creating Nodes
• SamsungAutomationStudio Github Repository
• FaceNet: A Unified Embedding for Face Recognition and Clustering
• VGGFace2
• inception_resnet_v1