Image Segmentation for Object Recognition

Technical Description:

1. Project Overview:

2. Technologies Used:

3. Workflow:

a. YOLO Model:

b. Flask Front End:

c. Image Segmentation:

d. Result Visualization:

import cv2

import numpy as np



# Load YOLO

net = cv2.dnn.readNet("yolov3.weights", "yolov3.cfg")

classes = []

with open("coco.names", "r") as f:

    classes = [line.strip() for line in f.readlines()]



# Function for YOLO Inference

def perform_yolo_inference(image_path):

    image = cv2.imread(image_path)

    height, width, _ = image.shape



    # YOLO blob

    blob = cv2.dnn.blobFromImage(image, 0.00392, (416, 416), (0, 0, 0), True, crop=False)

    net.setInput(blob)

    output_layers = net.getUnconnectedOutLayersNames()

    detections = net.forward(output_layers)



    class_ids = []

    confidences = []

    boxes = []



    # Process detections

    for out in detections:

        for detection in out:

            scores = detection[5:]

            class_id = np.argmax(scores)

            confidence = scores[class_id]



            if confidence > 0.5:  # Confidence threshold

                center_x = int(detection[0] * width)

                center_y = int(detection[1] * height)

                w = int(detection[2] * width)

                h = int(detection[3] * height)



                # Rectangle coordinates

                x = int(center_x - w / 2)

                y = int(center_y - h / 2)



                boxes.append([x, y, w, h])

                confidences.append(float(confidence))

                class_ids.append(class_id)



    return boxes, confidences, class_ids