From 6e57e8884bf4ad1a39c55a225dbaf363e20bc52b Mon Sep 17 00:00:00 2001
From: Prithvi Krishna <krishna.prithvi2001@gmail.com>
Date: Sun, 6 Feb 2022 21:50:52 +0530
Subject: [PATCH] added readme and requirements

---
 .gitignore       |  3 ++-
 README.md        | 32 ++++++++++++++++++++++++++++++++
 requirements.txt |  5 +++++
 3 files changed, 39 insertions(+), 1 deletion(-)
 create mode 100644 README.md
 create mode 100644 requirements.txt

diff --git a/.gitignore b/.gitignore
index f5e96db..c7de1d1 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1 +1,2 @@
-venv
\ No newline at end of file
+venv
+gestures.csv
\ No newline at end of file
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..79e12f8
--- /dev/null
+++ b/README.md
@@ -0,0 +1,32 @@
+# Sign Language Detection
+
+**A Work in Progress**
+
+This project aims to create a Machine Learning model that can translate Indian Sign Language to English text and act as a simple medium of communication for people unfamiliar with sign language.
+
+The hand recognition is done using [MediaPipe Hands solution](https://google.github.io/mediapipe/solutions/hands.html) in Python.
+
+Tutorials that I referred:
+1. [Real-time Hand Gesture Recognition using TensorFlow & OpenCV](https://techvidvan.com/tutorials/hand-gesture-recognition-tensorflow-opencv/)
+2. [Python: Hand landmark estimation with MediaPipe](https://techtutorialsx.com/2021/04/10/python-hand-landmark-estimation/)
+
+Currently, only dataset creation has been implemented ([save_gestures.py](save_gestures.py)) 
+
+**Instructions to create dataset**
+
+1. Create virtual environment using
+   ```virtualenv``` and activate it.
+2. Run: ```pip install -r requirements.txt```
+3. To just play around with the hand detection, run [hand_recognition.py](hand_recognition.py)
+4. To start creating the dataset, run [save_gestures.py](save_gestures.py)
+5. Press 'C' on your keyboard to start capturing the gesture. 
+6. Enter the name of the gesture in the terminal.
+7. Raise your hand in front of the camera while making the gesture and it will automatically start capturing pixel coordinates of the landmarks that are being detected.
+8. After number of datapoints recorded equals ```   TOTAL_DATAPOINTS```, code will stop capturing.
+9. Press 'C' to start recording a new gesture or press 'Q' to terminate the program.
+
+## **To-Do**
+---
+1. Study more about ISL and decide what changes need to be made.
+2. Test out different machine learning models and architectures.
+3. Work on deployment.
\ No newline at end of file
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..ddfe1d6
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,5 @@
+mediapipe==0.8.9.1
+numpy==1.22.2
+opencv_python==4.5.5.62
+pandas==1.4.0
+tensorflow==2.8.0