Python通过YOLO格式TXT标签文件在图像中画框

使用场景

1. 检测数据集标注是否有误： 在目标检测算法中需要标注自己的数据集，为了更加方便的检查数据集标注是否有误，可以使用该工具将标注结果绘制在图像中并查看。
2. 美化识别结果中的检测框： 在一些目标检测场景中，YOLO检测算法原始的检测框绘制会导致重叠、颜色冲突、字体过大等问题。可以使用该工具进行修改。

代码

import os
import cv2

class check_label:
    def __init__(self, classes:list, label_path:str, img_path:str, result_path:str):
        self.classes = classes
        self.line_width = 5 #线宽
        self.rec_color = (0, 0, 255) #颜色
        self.font_color = (255, 255, 255) #字体颜色
        self.font = cv2.FONT_HERSHEY_SIMPLEX
        self.font_size = 5 #字体大小
        self.font_thickness = 4
        self.font_x_offset = 0#字体x坐标偏移
        self.font_y_offset = -15#字体y坐标偏移

        self.isDrawFontRec = False#是否绘制字体矩形框
        self.isShowFont = False#是否绘制字体
        self.isShowConfidence = False#是否绘制置信度

        self.label_path =  label_path # 数据集标注结果文件(yolo格式)
        self.img_path = img_path  # 图像文件
        self.result_path = result_path  # 在图像上画好标注框文件

        self.label_files = os.listdir(label_path)
        self.img_files = os.listdir(img_path)
        self.label_files.sort(key=lambda x: int(x[:-4]))
        self.img_files.sort(key=lambda x: int(x[:-4]))

    def paint(self, imgName, pos):
        img = cv2.imread(self.img_path + "/" + imgName)
        size = img.shape
        imgW = size[1]
        imgH = size[0]
        # print("pos:", len(pos))
        for pos_i in pos:
            # a, x, y, w, h, b = "orange", pos_i[1], pos_i[2], pos_i[3], pos_i[4], pos_i[4]
            pos_i = pos_i.split(' ')
            x_center = float(pos_i[1]) * imgW + 1
            y_center = float(pos_i[2]) * imgH + 1
            x_min = int(x_center - 0.5 * float(pos_i[3]) * imgW)
            y_min = int(y_center - 0.5 * float(pos_i[4]) * imgH)
            x_max = int(x_center + 0.5 * float(pos_i[3]) * imgW)
            y_max = int(y_center + 0.5 * float(pos_i[4]) * imgH)
            x = x_min
            y = y_min
            w = x_max - x_min
            h = y_max - y_min
            # rotate90(imgW, imgH, x_min, y_min, w, h, x_center, y_center)
            # rotate180(imgW, imgH, x_min, y_min, w, h, x_center, y_center)
            # rotate270(imgW, imgH, x_min, y_min, w, h, x_center, y_center)
            # b = float(pos_i[5])
            b = 0.5
            if self.isShowConfidence:
                a = self.classes[int(pos_i[0])]
            else:
                a = ""
            cv2.rectangle(img, (x, y), (x + w, y + h), self.rec_color, self.line_width)
            if self.isDrawFontRec:
                cv2.rectangle(img, (x + self.font_x_offset, y + self.font_y_offset), (x + w, y + abs(self.font_y_offset)), self.rec_color,
                              -1)
            if self.isShowFont:
                cv2.putText(img, '{} {:.3f}'.format(a, b), (x + self.font_x_offset, y + self.font_y_offset), self.font, self.font_size,
                            self.font_color, self.font_thickness)
        cv2.imwrite(self.result_path + "/" + imgName, img)

    def process(self):
        for label_file, img_file in zip(self.label_files, self.img_files):
            print(img_file, label_file)
            if not os.path.isdir(label_file):
                f = open(self.label_path + "/" + label_file, "r", encoding='utf-8')
                result = f.read().splitlines()
                # print(result)
                self.paint(img_file, result)
                f.close()

原文地址：https://blog.csdn.net/weixin_44223883/article/details/142377203

免责声明：本站文章内容转载自网络资源，如本站内容侵犯了原著者的合法权益，可联系本站删除。更多内容请关注自学内容网（zxcms.com）！