工业缺陷检测基于python检测和C++部署检测实现PCB板缺陷检测

import cv2
import numpy as np

# 加载YOLO模型
net = cv2.dnn.readNetFromDarknet(yolo_config_path, yolo_weights_path)

# 获取模型输出层信息
layer_names = net.getLayerNames()
output_layers = [layer_names[i[0] - 1] for i in net.getUnconnectedOutLayers()]

# 加载图像
image = cv2.imread(image_path)
height, width, channels = image.shape

# 对图像进行预处理
blob = cv2.dnn.blobFromImage(image, 0.00392, (416, 416), (0, 0, 0), True, crop=False)
net.setInput(blob)

# 进行前向传播
outs = net.forward(output_layers)

# 解析输出结果
class_ids = []
confidences = []
boxes = []
for out in outs:
    for detection in out:
        scores = detection[5:]
        class_id = np.argmax(scores)
        confidence = scores[class_id]
        if confidence > 0.5:
            # 获取目标框的位置信息
            center_x = int(detection[0] * width)
            center_y = int(detection[1] * height)
            w = int(detection[2] * width)
            h = int(detection[3] * height)
            # 计算目标框的坐标
            x = int(center_x - w / 2)
            y = int(center_y - h / 2)
            # 保存目标框的相关信息
            class_ids.append(class_id)
            confidences.append(float(confidence))
            boxes.append([x, y, w, h])

# NMS非极大值抑制
nms_threshold = 0.4
nms_indices = cv2.dnn.NMSBoxes(boxes, confidences, 0.5, nms_threshold)

# 在图像上绘制检测结果
for i in range(len(boxes)):
    if i in nms_indices:
        x, y, w, h = boxes[i]
        label = class_ids[i]
        confidence = confidences[i]
        cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 2)
        cv2.putText(image, label, (x, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)

# 显示结果图像
cv2.imshow("Detection Result", image)
cv2.waitKey(0)
cv2.destroyAllWindows()