From 0b5bf2102fb09eeda7890e9973a1fa9f5e92b372 Mon Sep 17 00:00:00 2001
From: TechGirl007 <chippinginnz@gmail.com>
Date: Tue, 15 Oct 2024 09:34:31 +0800
Subject: [PATCH 1/2] Create haar_classifier.py

This is the 'beginner's guide' to implementing a haar cascading classifier to detect a fact in an image.
---
 computer_vision/haar_classifier.py | 68 ++++++++++++++++++++++++++++++
 1 file changed, 68 insertions(+)
 create mode 100644 computer_vision/haar_classifier.py

diff --git a/computer_vision/haar_classifier.py b/computer_vision/haar_classifier.py
new file mode 100644
index 000000000000..19575dd4b8a9
--- /dev/null
+++ b/computer_vision/haar_classifier.py
@@ -0,0 +1,68 @@
+"""
+Haar Cascading Classifiers
+
+Objective : Detect Object (Face)
+
+Resources Haar Classifiers :
+https://www.analyticsvidhya.com/blog/2022/04/object-detection-using-haar-cascade-opencv/#:~:text=Haar%20cascade%20is%20an%20algorithm,%2C%20buildings%2C%20fruits%2C%20etc
+https://machinelearningmastery.com/using-haar-cascade-for-object-detection/
+Resource for Haar classifiers: https://github.com/opencv/opencv/tree/master/data/haarcascades
+
+Download photo from :
+https://unsplash.com/
+
+1. Open Colab and create new notebook.
+2. Download a free to download photo from unsplash or use one of your own.
+3. Upload the photo in the model
+4.  Use haar classifier to detect face in image
+"""
+
+from google.colab.patches import cv2_imshow  #to assist with image processing and showing
+import cv2
+import numpy as np
+
+
+# Defining the list of image URLs from Unsplash
+foto = [
+    "https://spash.com/[chosen photo URL]"
+    "https://splash.com/[chosen photo URL]"
+]
+
+def load_image_from_url(url):
+    resp = urlopen(url)
+    image = np.asarray(bytearray(resp.read()), dtype="uint8")
+    image = cv2.imdecode(image, cv2.IMREAD_COLOR)
+    return image
+
+for i, image_url in enumerate(foto):
+    img = load_image_from_url(image_url)
+    print(f"Displaying image {i+1}")
+    cv2_imshow(img)
+#The above code should be in one cell and display the photo you chose.
+
+###########next cell##############
+
+# Loading the pre-trained Haar cascade for face detection
+face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml') #you can use others but this one is used the most.  Resource link above.
+
+#detecting the face and covert to grayscale
+def detect_faces(image):
+    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+    faces = face_cascade.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=20, minSize=(20,20)) #Setting general parameters.  Resouces above to understand more.
+    for (x, y, w, h) in faces:
+        cv2.rectangle(image, (x, y), (x+w, y+h), (255, 0, 0), 2) #blue colour bounding box
+    return image
+
+
+# Processing each loaded and resized image with Haar cascade
+for i, url in enumerate(foto, start=1):
+    img=load_image_from_url(url)
+    img_with_faces = detect_faces(img.copy())
+    print(f"Detecting Face {i}")
+    cv2_imshow(img_with_faces) #face
+
+#this should display the image with a blue bounding box.
+
+
+
+

From 3abe01b3f1f584e60c18561fe92eb128f90a8b42 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Tue, 15 Oct 2024 01:36:12 +0000
Subject: [PATCH 2/2] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 computer_vision/haar_classifier.py | 40 ++++++++++++++++--------------
 1 file changed, 22 insertions(+), 18 deletions(-)

diff --git a/computer_vision/haar_classifier.py b/computer_vision/haar_classifier.py
index 19575dd4b8a9..8b9764ddbf10 100644
--- a/computer_vision/haar_classifier.py
+++ b/computer_vision/haar_classifier.py
@@ -17,16 +17,16 @@
 4.  Use haar classifier to detect face in image
 """
 
-from google.colab.patches import cv2_imshow  #to assist with image processing and showing
+from google.colab.patches import (
+    cv2_imshow,
+)  # to assist with image processing and showing
 import cv2
 import numpy as np
 
 
 # Defining the list of image URLs from Unsplash
-foto = [
-    "https://spash.com/[chosen photo URL]"
-    "https://splash.com/[chosen photo URL]"
-]
+foto = ["https://spash.com/[chosen photo URL]" "https://splash.com/[chosen photo URL]"]
+
 
 def load_image_from_url(url):
     resp = urlopen(url)
@@ -34,35 +34,39 @@ def load_image_from_url(url):
     image = cv2.imdecode(image, cv2.IMREAD_COLOR)
     return image
 
+
 for i, image_url in enumerate(foto):
     img = load_image_from_url(image_url)
     print(f"Displaying image {i+1}")
     cv2_imshow(img)
-#The above code should be in one cell and display the photo you chose.
+# The above code should be in one cell and display the photo you chose.
 
 ###########next cell##############
 
 # Loading the pre-trained Haar cascade for face detection
-face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml') #you can use others but this one is used the most.  Resource link above.
+face_cascade = cv2.CascadeClassifier(
+    cv2.data.haarcascades + "haarcascade_frontalface_default.xml"
+)  # you can use others but this one is used the most.  Resource link above.
 
-#detecting the face and covert to grayscale
+
+# detecting the face and covert to grayscale
 def detect_faces(image):
     gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
-    faces = face_cascade.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=20, minSize=(20,20)) #Setting general parameters.  Resouces above to understand more.
-    for (x, y, w, h) in faces:
-        cv2.rectangle(image, (x, y), (x+w, y+h), (255, 0, 0), 2) #blue colour bounding box
+    faces = face_cascade.detectMultiScale(
+        gray, scaleFactor=1.1, minNeighbors=20, minSize=(20, 20)
+    )  # Setting general parameters.  Resouces above to understand more.
+    for x, y, w, h in faces:
+        cv2.rectangle(
+            image, (x, y), (x + w, y + h), (255, 0, 0), 2
+        )  # blue colour bounding box
     return image
 
 
 # Processing each loaded and resized image with Haar cascade
 for i, url in enumerate(foto, start=1):
-    img=load_image_from_url(url)
+    img = load_image_from_url(url)
     img_with_faces = detect_faces(img.copy())
     print(f"Detecting Face {i}")
-    cv2_imshow(img_with_faces) #face
-
-#this should display the image with a blue bounding box.
-
-
-
+    cv2_imshow(img_with_faces)  # face
 
+# this should display the image with a blue bounding box.