american sign language recognition with esp32-cam:
I implement a tensorflow lite (tflite) model on the ESP32-cam for American Sign language. The model is a stand-alone model and requires no network connection to run. The projects uses a pcb from pcbway to connect the esp32-can to a tft lcd screen, thus eliminating much of the messy wiring.
The youtube video giving instructions for building this project is here:
https://youtu.be/9ikQ7QFDbh4
This directory contains the Arduino sketch (and supporting files) for doing american sign language recognition on the esp32-cam.
This directory contains my updated version of the person detection sketch for ouputing the camera image on a tft, using the TFT_eSPI library.
This directory contains my pcb design gerber files and fritzing file.
Kaggle dataset:
https://www.kaggle.com/datasets/datamunge/sign-language-mnist
pcbway:
https://pcbway.com/g/QkVak7
person detection training instructions:
https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/person_detection/training_a_model.md
tflite instructions for microcontrollers:
https://www.tensorflow.org/lite/microcontrollers/get_started_low_level
Converting tensorflow to tflite interesting video:
https://www.youtube.com/watch?v=bKLL0tAj3GE&t
I'm using board version 2.02 of the esp32. The higher versions had a bug with the TFT_eSPI library for outputting jpeg files. Although, I didn't end up using the jpeg files.
The pin connections for the esp32 and tft are below. Note: if you are using the TFT_eSPI library, you need to define the pin connections in the User_Setup.h file.
#define TFT_MISO 13
#define TFT_MOSI 12
#define TFT_SCLK 14
#define TFT_CS 15 // Chip select control pin
#define TFT_DC 2 // Data Command control pin
#define TFT_RST 16 // Reset pin (could connect to RST pin)
\\LED pin connected high