computer-visionlisted

# Computer Vision Patterns ## OpenCV Essentials ```python import cv2 import numpy as np img = cv2.imread("image.jpg") # BGR, not RGB img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) # Resize preserving aspect ratio h, w = img.shape[:2] scale = 640 / max(h, w) resized = cv2.resize(img, (int(w * scale), int(h * scale)), interpolation=cv2.INTER_AREA) # Gaussian blur + Canny edges blurred = cv2.GaussianBlur(gray, (5, 5), 0) edges = cv2.Canny(blurred, threshold1=50, threshold2=150) # Draw bounding box x, y, bw, bh = 100, 50, 200, 150 cv2.rectangle(img, (x, y), (x + bw, y + bh), color=(0, 255, 0), thickness=2) cv2.putText(img, "Label 0.92", (x, y - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 0), 2) ``` ## YOLOv8 Training & Inference ```python from ultralytics import YOLO # Training model = YOLO("yolov8n.pt") # nano backbone results = model.train( data="dataset.yaml", epochs=100, imgsz=640, batch=16, device=0, project="runs/detect", name="exp1", patience=20, augment=True, ) # Inference model = YOLO("runs/detect/exp1/weights/best.pt") results = model.predict("test.jpg", conf=0.4, iou=0.5, save=True) for r in results: for box in r.boxes: cls = int(box.cls[0]) conf = float(box.conf[0]) xyxy = box.xyxy[0].tolist() print(f"Class {cls} ({conf:.2f}): {xyxy}") ``` ## YOLOv8 dataset.yaml ```yaml path: /data/my_dataset train: images/train val: images/v