Every day, we are visited by numerous people at our homes. Some are familiar faces, while others are strangers. At times, these strangers can become intruders, especially when the residents are elderly. Due to their inability to respond swiftly, elderly individuals may find themselves at a disadvantage, allowing strangers to intrude into their homes for theft or other malicious purposes. This situation can be avoided by verifying who the visitor is before opening the door to interact with them.

To address such challenges, a visitor verification system can be built using the MAX78000 Feather Board, utilizing a Siamese Convolutional Neural Network (Siamese CNN) for face recognition and verification. The MAX78000 features an ARM Cortex-M4F processor, which benefits from a large community and extensive documentation support. These resources help developers maximize the use of available tools and solve any issues they encounter. The MAX78000FTHR has a CNN accelerator and can include a camera interface and TFT display, making it suitable for image processing applications.

Since visitors arrive throughout the day, their identification and verification must be performed continuously. Developing deep learning models typically requires thousands of labeled samples per class, which makes data collection costly and time-consuming. To overcome this challenge, we employ one-shot learning methods using Siamese CNNs, where only a single picture of a person is sufficient to train the model, making it ideal for this application.

In addition to its effectiveness, power consumption and cost are crucial factors in this system. Given these considerations and the model chosen for the project, the MAX78000 is the ideal board. Apart from facial recognition tasks, the project can also integrate audio-based tasks, and possibly include an RTOS for scheduling jobs such as data transactions.

References:
1. N. I. Ahmad Sabri and S. Setumin, "One-Shot Learning for Facial Sketch Recognition using the Siamese Convolutional Neural Network," 2021 IEEE 11th IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE), Penang, Malaysia, 2021, pp. 307-312, doi: 10.1109/ISCAIE51753.2021.9431773.
2. Analog devices application notes
3. Maxim Integrated notes