Computer Vision और OpenCV Basics

pip install opencv-python matplotlib

import cv2
from sklearn.datasets import load_sample_image

rgb = load_sample_image("flower.jpg")          # NumPy array in RGB order
img = cv2.cvtColor(rgb, cv2.COLOR_RGB2BGR)     # OpenCV works in BGR order
cv2.imwrite("flower.jpg", img)                 # save it like any photo

img = cv2.imread("flower.jpg")                 # how you load your own photo
print("type :", type(img).__name__, img.dtype)
print("shape:", img.shape, "→ height, width, channels")
print("pixel at row 100, col 200 (B, G, R):", img[100, 200])
print("brightest value:", img.max(), "| darkest:", img.min())

import cv2
import matplotlib.pyplot as plt
from sklearn.datasets import load_sample_image

img = cv2.cvtColor(load_sample_image("flower.jpg"), cv2.COLOR_RGB2BGR)

small = cv2.resize(img, (320, 214))                        # (width, height)
crop = img[100:330, 180:480]                               # rows, columns – plain NumPy slicing
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(img, (21, 21), 0)                  # kernel size must be odd

print("small:", small.shape, "| crop:", crop.shape, "| gray:", gray.shape)

show = [("original", img), ("crop", crop), ("grayscale", gray), ("blur", blur)]
fig, axes = plt.subplots(1, 4, figsize=(12, 2.8), dpi=100)
for ax, (title, im) in zip(axes, show):
    ax.imshow(im if im.ndim == 2 else cv2.cvtColor(im, cv2.COLOR_BGR2RGB), cmap="gray")
    ax.set_title(title); ax.axis("off")
fig.tight_layout(); fig.savefig("basics.png")

import cv2
import matplotlib.pyplot as plt
from sklearn.datasets import load_sample_image

gray = cv2.cvtColor(load_sample_image("china.jpg"), cv2.COLOR_RGB2GRAY)

edges = cv2.Canny(gray, 100, 200)                                   # strong intensity changes
_, binary = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)   # Otsu picks the cut-off
print("edge pixels:", int((edges > 0).sum()), "of", edges.size)

fig, axes = plt.subplots(1, 3, figsize=(12, 3.2), dpi=100)
for ax, (t, im) in zip(axes, [("grayscale", gray), ("Canny edges", edges), ("Otsu threshold", binary)]):
    ax.imshow(im, cmap="gray"); ax.set_title(t); ax.axis("off")
fig.tight_layout(); fig.savefig("edges.png")

import cv2
import numpy as np

rng = np.random.default_rng(3)
tray = np.full((300, 500, 3), (60, 90, 40), np.uint8)               # green tray (BGR)
coins = [(70, 70, 32), (180, 90, 26), (300, 70, 36), (420, 100, 30),
         (100, 210, 28), (240, 210, 40), (390, 220, 25)]
for x, y, r in coins:
    cv2.circle(tray, (x, y), r, (40, 180, 220), -1)                  # golden coins
tray = cv2.add(tray, rng.integers(0, 25, tray.shape, dtype=np.uint8))  # camera noise

gray = cv2.cvtColor(tray, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (5, 5), 0)
_, mask = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
contours, _ = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = [c for c in contours if cv2.contourArea(c) > 200]         # ignore tiny specks

print("coins found:", len(contours), "| actual:", len(coins))
for c in sorted(contours, key=cv2.contourArea, reverse=True)[:3]:
    (x, y), r = cv2.minEnclosingCircle(c)
    print(f"  coin at ({x:.0f}, {y:.0f}) radius ≈ {r:.0f}px")

out = tray.copy()
cv2.drawContours(out, contours, -1, (0, 0, 255), 3)
cv2.putText(out, f"{len(contours)} coins", (10, 290), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (255, 255, 255), 2)
cv2.imwrite("counted.png", out)

import cv2

detector = cv2.CascadeClassifier(cv2.data.haarcascades + "haarcascade_frontalface_default.xml")
img = cv2.imread("class.jpg")
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = detector.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=5, minSize=(40, 40))
print("faces found:", len(faces))
for (x, y, w, h) in faces:
    cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 2)
cv2.imwrite("class_faces.jpg", img)

import cv2

cap = cv2.VideoCapture(0)                  # 0 = default webcam
while True:
    ok, frame = cap.read()
    if not ok:
        break
    edges = cv2.Canny(cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY), 80, 160)
    cv2.imshow("edges – press q to quit", edges)
    if cv2.waitKey(1) & 0xFF == ord("q"):
        break
cap.release()
cv2.destroyAllWindows()