Project Files committed

PROJECT_README.md

@@ -0,0 +1,18 @@
+# Sign Language Letters detection
+
+Detects the different letters represented by actions of hand in sign language
+
+
+🚀Trained on **YOLOv8 Nano** model achieving **mAP:50 - 0.94** & **mAP:50-95 - 0.89**
+
+🤗 Hugging Face APP Link: https://huggingface.co/spaces/Harsh72AI/Sign-Language-Letters-detection/
+
+* 🦹‍♂️ Dataset used: https://universe.roboflow.com/david-lee-d0rhs/american-sign-language-letters/
+
+**Requirements for projects**
+```
+ultralytics
+torch
+numpy
+streamlit
+```

Sign-language-detection-results-20240115T023838Z-001.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a28ad8479a18cb4b03c88b3ce9b0ad4deb7539968dfb0b6ca01ffe577db45952
+size 19253170

app.py

@@ -0,0 +1,33 @@
+import streamlit as st
+from pipeline import detectPipeline
+
+
+st.title('Sign Language Letters detection')
+st.write('Detects Sign language Alphabets in an image \nPowered by YOLOv8 Nano model')
+
+st.write('')
+
+detect_pipeline = detectPipeline()
+
+st.info('Sign Language Letters detection model loaded successfully!')
+
+uploaded_file = st.file_uploader("Upload an image", type=["jpg", "png", "jpeg"])
+
+if uploaded_file is not None:
+    
+    with st.container():
+        col1, col2 = st.columns([3, 3])
+        
+        col1.header('Input Image')
+        col1.image(uploaded_file, caption='Uploaded Image', use_column_width=True)
+
+        col1.text('')
+        col1.text('')
+
+        if st.button('Detect'):
+            detections = detect_pipeline.detect_signs(img_path=uploaded_file)
+            detections_img = detect_pipeline.drawDetections2Image(img_path=uploaded_file, detections=detections)
+
+            col2.header('Detections')
+            col2.image(detections_img, caption='Predictions by model', use_column_width=True)
+

pipeline.py

@@ -0,0 +1,35 @@
+from ultralytics import YOLO
+from PIL import Image
+import numpy as np
+import cv2 as cv
+
+
+class detectPipeline():
+    def __init__(self) -> None:
+        self.model = YOLO('yolo_v8_nano_model.pt')
+        self.class_names = {i: chr(65 + i) for i in range(26)}
+
+
+    def detect_signs(self, img_path: str):
+        # Data Preprocessing
+        img = Image.open(img_path).convert('RGB')
+        img_array = np.array(img)
+
+        # Making detections using YOLOv8 Nano
+        detections = self.model(img_array)[0]
+        sign_detections = []
+        for sign in detections.boxes.data.tolist():
+            x1, y1, x2, y2, score, class_id = sign
+            sign_detections.append([int(x1), int(y1), int(x2), int(y2), score, int(class_id)])
+        return sign_detections
+
+    def drawDetections2Image(self, img_path, detections):
+        img = Image.open(img_path).convert('RGB')
+        img = np.array(img)
+        for bbox in detections:
+            x1, y1, x2, y2, score, class_id = bbox
+            cv.rectangle(img, pt1=(x1, y1), pt2=(x2, y2), color=(0, 255, 0), thickness=25)
+            cv.putText(img, text=f'{self.class_names[class_id]} ({round(score*100, 2)}%)', org=(x1, y1-20), fontFace=cv.FONT_HERSHEY_SIMPLEX, fontScale=3.5,
+                        color=(0, 0, 255), lineType=cv.LINE_AA, thickness=10)
+        img_detections = np.array(img)
+        return img_detections

requirements.txt

@@ -0,0 +1,4 @@
+ultralytics
+torch
+numpy
+streamlit

yolo_v8_nano_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59653c5ebdc82c93372189910d73e64701a83e817ce496aa130121dc2af6a66a
+size 6246041