不同的标注工具，产生和保存的标签文件也是不同的。比如：
- labelImg保存的是xml文件
- labelme保存的是json文件
不同的任务，对标签的需求也不同。比如：
- 分类任务，就是one hot形式即可
- 目标检测任务，给出矩形框即可，x,y,w,h等等形式
- 对于分割任务，则需要给出polygon，由一个个坐标点构成
与此同时，在公开数据集中，不同的数据集的存储形式也不近相同。比如：
- voc的数据格式
- coco的数据格式
所以，对于标注数据进行处理，格式之间的转换，就成了工程师常常需要操作的事情。这里记录下来，重复的工作快速完成。
一、polygon2bbox
任务描述：
采用labelme标注的图像是多边形Polygon，转为矩形标注BBox xmin,ymin,xmax,ymax读取数据是json文件import osimport jsonimport numpy as npimport PIL.Imageimport PIL.ImageDrawimport base64from PIL import Imageimport ioimport cv2import matplotlib.pyplot as pltdef polygons_to_mask(img_shape, polygons): mask = np.zeros(img_shape, dtype=np.uint8) mask = PIL.Image.fromarray(mask) xy = list(map(tuple, polygons)) PIL.ImageDraw.Draw(mask).polygon(xy=xy, outline=1, fill=1) mask = np.array(mask, dtype=bool) return maskdef mask2box(mask): # [x1,y1,w,h] '''从mask反算出其边框 mask：[h,w] 0、1组成的图片 1对应对象，只需计算1对应的行列号（左上角行列号，右下角行列号，就可以算出其边框） ''' index = np.argwhere(mask == 1) rows = index[:, 0] clos = index[:, 1] # 解析左上角行列号 left_top_r = np.min(rows) # y left_top_c = np.min(clos) # x # 解析右下角行列号 right_bottom_r = np.max(rows) right_bottom_c = np.max(clos) # return [(left_top_r,left_top_c),(right_bottom_r,right_bottom_c)] # return [(left_top_c, left_top_r), (right_bottom_c, right_bottom_r)] return [left_top_c, left_top_r, right_bottom_c, right_bottom_r] # [x1,y1,x2,y2]def getbbox(points): # 多边形变矩形框bbox # img = np.zeros([self.height,self.width],np.uint8) # cv2.polylines(img, [np.asarray(points)], True, 1, lineType=cv2.LINE_AA) # 画边界线 # cv2.fillPoly(img, [np.asarray(points)], 1) # 画多边形 内部像素值为1 polygons = points mask = polygons_to_mask([1024, 1024], polygons) return mask2box(mask) # [x1,y1,w,h]# 构建COCO的annotation字段def annotation(points): bbox = list(map(float, getbbox(points))) return bbox# 法一def data_transfer(json_path): bbox_list = [] with open(json_path, 'r') as fp: #print(json_path) data = json.load(fp) # 加载json文件 for shapes in data['shapes']: points = shapes['points'] points.append([points[0][0], points[1][1]]) points.append([points[1][0], points[0][1]]) bbox = annotation(points) bbox_list.append(bbox) return bbox_listdef contour_label(json_path, image): with open(json_path, 'r') as fp: #print(json_path) data = json.load(fp) # 加载json文件 for shapes in data['shapes']: points = shapes['points'] contour = np.array([points]) contour = np.trunc(contour).astype(int) #print(contour, type(contour)) #print("***") cv2.drawContours(image, [contour], 0, (0, 0, 255), 2) # cv2.FILLED填充 return image# 法二：def simple_label(json_path, image): with open(json_path, 'r') as fp: #print(json_path) data = json.load(fp) # 加载json文件 for shapes in data['shapes']: points = np.array(shapes['points']) y, x, y2, x2 = np.min(points[:, 1]), np.min(points[:, 0]), np.max(points[:, 1]), np.max(points[:, 0]) print(y, x, y2, x2) cv2.rectangle(image, (int(x), int(y)), (int(x2), int(y2)), (0, 0, 255), thickness=2) return imageif __name__=="__main__": labelme_json = r"E:\temp\label" png_json = r"E:\temp\image" for (path, dirs, files) in os.walk(labelme_json): for filename in files: zhong_json_path = os.path.join(path, filename) img = cv2.imread(os.path.join(png_json, filename.replace(".json", ".jpg"))) img_bbox = img.copy() img_contour = img.copy() img_simple_bbox = img.copy() zhong_contour_image = contour_label(zhong_json_path, img_contour) zhong_bbox_list = data_transfer(zhong_json_path) plt.figure(figsize=[15, 5]) plt.subplot(131) plt.title("contour") plt.imshow(zhong_contour_image) for box in zhong_bbox_list: x, y, x2, y2 = box cv2.rectangle(img_bbox, (int(x), int(y)), (int(x2), int(y2)), (0, 0, 255), thickness=2) plt.subplot(132) plt.title("Method 1:mask2box") plt.imshow(img_bbox) simple_image = simple_label(zhong_json_path, img_simple_bbox) plt.subplot(133) plt.title("Method 2:np.min[:, 1], np.max(points[:, 0])") plt.imshow(img_bbox) plt.show()
方法1和方法2都在上面了。这里吧简单点的方法单独抽出来做展示：
def data_transfer(json_path): bbox_list = [] with open(json_path, 'r') as fp: #print(json_path) data = json.load(fp) # 加载json文件 for shapes in data['shapes']: points = np.array(shapes['points']) bbox = [np.min(points[:, 1]), np.min(points[:, 0]), np.max(points[:, 1]), np.max(points[:, 0])] #print(bbox) bbox_list.append(bbox) return bbox_list二、mask2json
有时候没法直接获取标注的json文件，只有黑白色的mask图像。 这里需要将mask，转为labelme标注的json文件
import osimport cv2import jsondef mask2json(): mask_path = r"Z:\mult_DR\onLine_zhong_labeled\results\mask_pd_qlj" save_json_path = r"Z:\mult_DR\onLine_zhong_labeled\results\label/" label = "TB" for (path, dirs, files) in os.walk(mask_path): for filename in files: A = dict() listbigoption=[] prefile_path = os.path.join(path, filename) print(prefile_path) pred_seged = cv2.imread(prefile_path, 0) try: _, contours, _ = cv2.findContours(pred_seged, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE) except: contours, _ = cv2.findContours(pred_seged, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE) print(len(contours)) if len(contours) != 0: for contour in contours: if len(contour)>=3: listobject = dict() listxy = [] for e in contour: listxy.append(e[0].tolist()) #print(e,e[0][0],e[0][1]) #x, y = e[0][0], e[0][1] print(listxy) listobject['points'] = listxy listobject['line_color'] = 'null' listobject['label'] = label listobject['fill_color'] = 'null' listbigoption.append(listobject) A['lineColor'] = [0, 255, 0, 128] A['imageData'] = 'imageData' A['fillColor'] = [255, 0, 0, 128] A['imagePath'] = filename A['shapes'] = listbigoption A['flags'] = {} with open(save_json_path + filename.replace(".png", ".json"), 'w') as f: json.dump(A, f)if __name__=="__main__": mask2json()三、保存四边形矩形框bbox标注信息
任意四边形坐标标记格式：tl_x,tl_y,tr_x,tr_y,br_x,br_y,bl_x,bl_y。从左上点开始顺时针旋转的四个顶点的坐标，如下图所示：
将TXT文档中标注信息，存储到labelme标注的json文件内，代码如下：
import jsonimport base64from PIL import Imageimport ioimport osimport cv2import numpy as npdef generate_json(file_dir, file_name): str_json = {} shapes = [] # 读取坐标 fr = open(os.path.join(file_dir, file_name)) for line in fr.readlines(): # 逐行读取，滤除空格等 print(line.strip()) print(type(line.strip())) lineArr = line.strip().split(',') print("lineArr:", lineArr) points = [] points.append([float(lineArr[0]), float(lineArr[1])]) points.append([float(lineArr[2]), float(lineArr[3])]) points.append([float(lineArr[4]), float(lineArr[5])]) points.append([float(lineArr[6]), float(lineArr[7])]) print(points) # 从左上点开始顺时针旋转的四个顶点的坐标 shape = {} shape["label"] = "plate_1" shape["points"] = points shape["line_color"] = [] shape["fill_color"] = [] shape["flags"] = {} shapes.append(shape) str_json["version"] = "3.14.1" str_json["flags"] = {} str_json["shapes"] = shapes str_json["lineColor"] = [0, 255, 0, 128] str_json["fillColor"] = [255, 0, 0, 128] picture_basename = file_name.replace('.txt', '.png') str_json["imagePath"] = picture_basename img = cv2.imread(os.path.join(file_dir, picture_basename)) str_json["imageHeight"] = img.shape[0] str_json["imageWidth"] = img.shape[1] str_json["imageData"] = base64encode_img(os.path.join(file_dir, picture_basename)) return str_jsondef base64encode_img(image_path): src_image = Image.open(image_path) output_buffer = io.BytesIO() src_image.save(output_buffer, format='JPEG') byte_data = output_buffer.getvalue() base64_str = base64.b64encode(byte_data).decode('utf-8') return base64_strif __name__=="__main__": """ txt文件和图像（png）文件，均存储在下面这个文件夹下 生成的json文件，也保存到这个文件夹下 """ file_dir = r"E:\temp" file_name_list = [file_name for file_name in os.listdir(file_dir) \ if file_name.lower().endswith('txt')] for file_name in file_name_list: str_json = generate_json(file_dir, file_name) json_data = json.dumps(str_json, indent=2, ensure_ascii=False) jsonfile_name = file_name.replace(".txt", ".json") f = open(os.path.join(file_dir, jsonfile_name), 'w') f.write(json_data) f.close()检验下生成的json，是否成功。用labelme打开，查看标注结果，进行检验：
四、保存不规则边框polygon标注信息
这里与bbox的区别就在于：
- bbox只有四个坐标点，按顺时针一次排布；
- polygon是大于2个点都可以的，坐标的排序也是按照顺时针进行排布的。
所以，在poly中坐标点的数量是不固定的。在读取时候，依次将坐标点存储进来就行
import jsonimport base64from PIL import Imageimport ioimport osimport cv2import numpy as npdef generate_json(file_dir, file_name): str_json = {} shapes = [] # 读取坐标 fr = open(os.path.join(file_dir, file_name)) for line in fr.readlines(): # 逐行读取，滤除空格等 print(line.strip()) print(type(line.strip())) lineArr = line.strip().split(',') print("lineArr:", lineArr) points = [] for i in range(0, len(lineArr), 2): points.append([float(lineArr[i]), float(lineArr[i+1])]) print(points) # 从左上点开始顺时针旋转的四个顶点的坐标 shape = {} shape["label"] = "plate_1" shape["points"] = points shape["line_color"] = [] shape["fill_color"] = [] shape["flags"] = {} shapes.append(shape) str_json["version"] = "3.14.1" str_json["flags"] = {} str_json["shapes"] = shapes str_json["lineColor"] = [0, 255, 0, 128] str_json["fillColor"] = [255, 0, 0, 128] picture_basename = file_name.replace('.txt', '.png') str_json["imagePath"] = picture_basename img = cv2.imread(os.path.join(file_dir, picture_basename)) str_json["imageHeight"] = img.shape[0] str_json["imageWidth"] = img.shape[1] str_json["imageData"] = base64encode_img(os.path.join(file_dir, picture_basename)) return str_jsondef base64encode_img(image_path): src_image = Image.open(image_path) output_buffer = io.BytesIO() src_image.save(output_buffer, format='JPEG') byte_data = output_buffer.getvalue() base64_str = base64.b64encode(byte_data).decode('utf-8') return base64_strif __name__=="__main__": """ txt文件和图像（png）文件，均存储在下面这个文件夹下 生成的json文件，也保存到这个文件夹下 """ file_dir = r"E:\temp\polygon" file_name_list = [file_name for file_name in os.listdir(file_dir) \ if file_name.lower().endswith('txt')] for file_name in file_name_list: str_json = generate_json(file_dir, file_name) json_data = json.dumps(str_json, indent=2, ensure_ascii=False) jsonfile_name = file_name.replace(".txt", ".json") with open(os.path.join(file_dir, jsonfile_name), 'w') as f: f.write(json_data)同样，labelme打开，查看标注结果：
参考链接：任意四边形坐标标记格式txt文件转labelme标记的json格式文件_skye_95的博客-CSDN博客
五、将labelImg标注的xml BBox文件转成json文件
labelImg只能标注矩形框标签，比较的单一。但是labelme就比较的丰富，能够标注不规则图形。将labelImg标注的BBox标签文件xml，转为labelme格式的json文件
from xml.etree import ElementTree as etimport jsonimport globimport osdef readxml_et(xml_file, save_json_path): tree = et.ElementTree(file=xml_path) root = tree.getroot() A = dict() listbigoption = [] for child_root in root: if child_root.tag == 'filename': imagePath = child_root.text if child_root.tag == 'object': listobject = dict() for xylabel in child_root: if xylabel.tag == 'name': label = xylabel.text if xylabel.tag == 'bndbox': xmin = int(xylabel.find('xmin').text) ymin = int(xylabel.find('ymin').text) xmax = int(xylabel.find('xmax').text) ymax = int(xylabel.find('ymax').text) listxy=[[xmin,ymin],[xmax,ymin],[xmax,ymax],[xmin,ymax]] listobject['points'] = listxy listobject['line_color'] = 'null' listobject['label'] = label listobject['fill_color'] = 'null' listbigoption.append(listobject) # print(listbigoption) A['lineColor'] = [0, 255, 0, 128] A['imageData'] = 'imageData' A['fillColor'] = [255, 0, 0, 128] A['imagePath'] = imagePath A['shapes'] = listbigoption A['flags'] = {} with open(save_json_path + imagePath.replace(".png", ".json"), 'w') as f: json.dump(A, f)if __name__=='__main__': labelme_xml_path = r'F:\xml_labels' save_json_path = r"F:\labels/" for root, dirs, files in os.walk(labelme_xml_path): for filename in files: # 遍历所有文件 xml_path = os.path.join(root, filename) print(xml_path) readxml_et(xml_path, save_json_path)六、voc中txt格式的，也转为json格式
存储标注好的数据方式多种多样，有直接存储到txt文件的，还有XML文件、json文件、Excel文件等等。各种格式数据间的转换，也是常会用到的。
from xml.etree import ElementTree as etimport jsonimport globimport osdef readxml_et(file_path, save_json_path): A = dict() listbigoption = [] with open(file_path, "r") as f: for line in f.readlines(): listobject = dict() line = line.strip('\n') # 去掉列表中每一个元素的换行符 x_center = int(float(line.split(" ")[1]) * 512) y_center = int(float(line.split(" ")[2]) * 512) x_shift = int(float(line.split(" ")[3]) * 512) y_shift = int(float(line.split(" ")[4]) * 512) xmin = x_center - x_shift xmax = x_center + x_shift ymin = y_center - y_shift ymax = y_center + y_shift listxy=[[xmin,ymin],[xmax,ymin],[xmax,ymax],[xmin,ymax]] listobject['points'] = listxy listobject['line_color'] = 'null' listobject['label'] = "jie_jie" listobject['fill_color'] = 'null' listbigoption.append(listobject) A['lineColor'] = [0, 255, 0, 128] A['imageData'] = 'imageData' A['fillColor'] = [255, 0, 0, 128] A['imagePath'] = os.path.basename(file_path).replace(".txt", ".png") A['shapes'] = listbigoption A['flags'] = {} with open(save_json_path + os.path.basename(file_path).replace(".txt", ".json"), 'w') as f: json.dump(A, f)if __name__=='__main__': labelme_xml_path = r'F:\txt_label' save_json_path = r"F:\labels/" for root, dirs, files in os.walk(labelme_xml_path): for filename in files: # 遍历所有文件 xml_path = os.path.join(root, filename) print(xml_path) readxml_et(xml_path, save_json_path)七、labelme标注的json文件，打印到原图image上
每次看label me标注好的信息，都需要用这个标注软件再次打开，就显得很麻烦。能不能把标注的信息，打印到原始图像上，这样发给别人对照或者展示的时候，就可以直接查看标注的位置和类别了。
import numpy as npimport cv2import osimport jsondef loadFont(path): with open(path, 'r', encoding='utf8')as fp: json_data = json.load(fp) return json_datadef genarete_mask_label(label_info, filename): shapes = label_info['shapes'] mask_temp = np.zeros((512, 512)) for i in range(len(shapes)): points = shapes[i]["points"] contour = np.array([points]) contour = np.trunc(contour).astype(int) print(contour, type(contour)) print("***") cv2.drawContours(mask_temp, [contour], 0, (255, 255, 255), cv2.FILLED) # 填充 print(r"G:\NCP_ResUNet\V_TEST\data\2_1\mask/" + filename.replace(".json",".png")) cv2.imwrite(r"G:\NCP_ResUNet\V_TEST\data\2_1\mask/" + filename.replace(".json",".png"), mask_temp)def draw_mask_image(label_info, filepath): shapes = label_info['shapes'] raw_PATH = filepath.replace(".json", ".png").replace("labels", "images") print(raw_PATH) raw_temp = cv2.imread(raw_PATH) for i in range(len(shapes)): points = shapes[i]["points"] contour = np.array([points]) contour = np.trunc(contour).astype(int) print(contour, type(contour)) print("***") cv2.drawContours(raw_temp, [contour], 0, (0, 0, 255), 1) # 勾勒边界 print(filepath.replace(".json", ".png").replace("labels", "label_png")) cv2.imwrite(filepath.replace(".json", ".png").replace("labels", "label_png"), raw_temp)if __name__ == '__main__': # 路径中不要有中文字符 raw_path = r"F:\labels" for root, dirs, files in os.walk(raw_path): for filename in files: # 遍历所有文件 filepath=os.path.join(root,filename) if filename[len(filename) - 4:len(filename)] == 'json': label_info = loadFont(filepath) print(label_info) draw_mask_image(label_info, filepath)八、labelme的json数据转换成coco数据读取所需的json文件
普通的由labelme标注生成的文件，一个json对应一个标注图。单coco数据集要求将训练集和验证集的所有标签汇集在一个json文件内
import argparseimport jsonimport matplotlib.pyplot as pltimport skimage.io as ioimport cv2from labelme import utilsimport numpy as npimport globimport PIL.Imageimport osclass MyEncoder(json.JSONEncoder): def default(self, obj): if isinstance(obj, np.integer): return int(obj) elif isinstance(obj, np.floating): return float(obj) elif isinstance(obj, np.ndarray): return obj.tolist() else: return super(MyEncoder, self).default(obj)class labelme2coco(object): def __init__(self, labelme_json=[], save_json_path='./tran.json'): ''' :param labelme_json: 所有labelme的json文件路径组成的列表 :param save_json_path: json保存位置 ''' self.labelme_json = labelme_json self.save_json_path = save_json_path self.images = [] self.categories = [] self.annotations = [] # self.data_coco = {} self.label = [] self.annID = 1 self.height = 0 self.width = 0 self.save_json() # 由json文件构建COCO def data_transfer(self): for num, json_file in enumerate(self.labelme_json): print(json_file) with open(json_file, 'r') as fp: data = json.load(fp) # 加载json文件 self.images.append(self.image(json_file, data, num)) for shapes in data['shapes']: label = shapes['label'] if label not in self.label: self.categories.append(self.categorie(label)) self.label.append(label) points = shapes['points'] points.append([points[0][0],points[1][1]]) points.append([points[1][0],points[0][1]]) self.annotations.append(self.annotation(points, label, num)) self.annID += 1 # 构建COCO的image字段 def image(self, json_file, data, num): """ { "height": 1024, "width": 1024, "id": 1, "file_name": "1.2.156.112536.2.560.7050106199066.1346626203150.42_2519_3027_0.140_0.140.png" }, """ image = {} #img = utils.img_b64_to_arr(data['imageData']) # 解析原图片数据 #print(data['imagePath']) #img=io.imread(os.path.join(r"F:\lingjun2019\detectron2\Dataset_DR\database\images",data['imagePath'])) # 通过图片路径打开图片 img = io.imread(os.path.join(r"F:\DR-TB\iter2\database\images", os.path.basename(json_file).replace(".json", ".png"))) #img = cv2.imread(data['imagePath'], 0) height, width = img.shape[:2] #print(height,width) #height, width = data['imageHeight'], data['imageWidth'] img = None image['height'] = height image['width'] = width image['id'] = num + 1 #image['file_name'] = data['imagePath'].split('/')[-1] image['file_name'] = os.path.basename(json_file).replace(".json", ".png") self.height = height self.width = width return image # 构建类别 def categorie(self, label): """ "categories": [ { "supercategory": "component", "id": 1, "name": "TB" } ], """ categorie = {} categorie['supercategory'] = 'component' categorie['id'] = len(self.label) + 1 # 0 默认为背景 categorie['name'] = label return categorie # 构建COCO的annotation字段 def annotation(self, points, label, num): """ { "segmentation": [ ], "iscrowd": 0, "image_id": 5, "bbox": [ ], "area": 37101.0, "category_id": 1, "id": 1 }, """ annotation = {} annotation['segmentation'] = [list(np.asarray(points).flatten())] annotation['iscrowd'] = 0 annotation['image_id'] = num + 1 # annotation['bbox'] = str(self.getbbox(points)) # 使用list保存json文件时报错（不知道为什么） # list(map(int,a[1:-1].split(','))) a=annotation['bbox'] 使用该方式转成list annotation['bbox'] = list(map(float, self.getbbox(points))) annotation['area'] = annotation['bbox'][2] * annotation['bbox'][3] annotation['category_id'] = self.getcatid(label) #annotation['category_id'] = 1 annotation['id'] = self.annID return annotation def getcatid(self, label): for categorie in self.categories: if label == categorie['name']: return categorie['id'] return 1 def getbbox(self, points): # img = np.zeros([self.height,self.width],np.uint8) # cv2.polylines(img, [np.asarray(points)], True, 1, lineType=cv2.LINE_AA) # 画边界线 # cv2.fillPoly(img, [np.asarray(points)], 1) # 画多边形 内部像素值为1 polygons = points mask = self.polygons_to_mask([self.height, self.width], polygons) return self.mask2box(mask) def mask2box(self, mask): # [x1,y1,w,h] '''从mask反算出其边框 mask：[h,w] 0、1组成的图片 1对应对象，只需计算1对应的行列号（左上角行列号，右下角行列号，就可以算出其边框） ''' # np.where(mask==1) index = np.argwhere(mask == 1) rows = index[:, 0] clos = index[:, 1] # 解析左上角行列号 left_top_r = np.min(rows) # y left_top_c = np.min(clos) # x # 解析右下角行列号 right_bottom_r = np.max(rows) right_bottom_c = np.max(clos) # return [(left_top_r,left_top_c),(right_bottom_r,right_bottom_c)] # return [(left_top_c, left_top_r), (right_bottom_c, right_bottom_r)] # return [left_top_c, left_top_r, right_bottom_c, right_bottom_r] # [x1,y1,x2,y2] return [left_top_c, left_top_r, right_bottom_c - left_top_c, right_bottom_r - left_top_r] # [x1,y1,w,h] 对应COCO的bbox格式 def polygons_to_mask(self, img_shape, polygons): mask = np.zeros(img_shape, dtype=np.uint8) mask = PIL.Image.fromarray(mask) xy = list(map(tuple, polygons)) PIL.ImageDraw.Draw(mask).polygon(xy=xy, outline=1, fill=1) mask = np.array(mask, dtype=bool) return mask def data2coco(self): data_coco = {} data_coco['images'] = self.images # 构建COCO的image字段 data_coco['categories'] = self.categories # 构建COCO的categories字段(标注类别数量和类别name信息) data_coco['annotations'] = self.annotations # 构建COCO的annotations字段 return data_coco def save_json(self): self.data_transfer() self.data_coco = self.data2coco() # 保存json文件 json.dump(self.data_coco, open(self.save_json_path, 'w'), indent=4, cls=MyEncoder) # indent=4 更加美观显示labelme_json = glob.glob(r'F:\database\label/*.json')labelme2coco(labelme_json, r'F:\database\annotations/train_label.json')九、python opencv minAreaRect 生成最小外接矩形
画一个任意四边形（任意多边形都可以）的最小外接矩形，那么点集cnt 存放的就是该四边形的4个顶点坐标（点集里面有4个点）
cnt = np.array([[x1,y1],[x2,y2],[x3,y3],[x4,y4]]) # 必须是array数组的形式rect = cv2.minAreaRect(cnt) # 得到最小外接矩形的（中心(x,y), (宽,高), 旋转角度）box = cv2.cv.BoxPoints(rect) # 获取最小外接矩形的4个顶点坐标(ps: cv2.boxPoints(rect) for OpenCV 3.x)box = np.int0(box)# 画出来cv2.drawContours(img, [box], 0, (255, 0, 0), 1)cv2.imwrite('contours.png', img)函数 cv2.minAreaRect() 返回一个Box2D结构rect：（最小外接矩形的中心（x，y），（宽度，高度），旋转角度），但是要绘制这个矩形，我们需要矩形的4个顶点坐标box, 通过函数 cv2.cv.BoxPoints() 获得，返回形式[ [x0,y0], [x1,y1], [x2,y2], [x3,y3] ]。
得到的最小外接矩形的4个顶点顺序：中心坐标、宽度、高度、旋转角度（是度数形式，不是弧度数）的对应关系如下：
注意：
旋转角度θ是水平轴（x轴）逆时针旋转，直到碰到矩形的第一条边停住，此时该边与水平轴的夹角。并且这个边的边长是width，另一条边边长是height。也就是说，在这里，width与height不是按照长短来定义的。
在opencv中，坐标系原点在左上角，相对于x轴，逆时针旋转角度为负，顺时针旋转角度为正。所以，θ∈（-90度，0]。
原文链接：https://blog.csdn.net/lanyuelvyun/article/details/76614872
十、自动化修改labelme标注保存好的json文件
labelme标注好后，会自动的生成一个json文件。但是如果需要对标记好的文件内的字段进行批量修改，那么一个个点开再保存，那效率太低了。这里利用python，先获取json存储的信息，修改后，再保存下来。
这里以改变json文件内的label为例。如果你想要修改其他的参数，比如说坐标值、甚至是base64的图像，都可以。
# -*- coding=utf-8 -*-import jsonimport numpy as npimport globimport jsondef get_new_json(filepath): flag = False move_flag=False listbigoption = [] A = dict() with open(filepath, 'r', encoding='utf-8') as f: json_data = json.load(f) # if json_data['shapes'] == []: # print(filepath) # print(json_data['shapes']) # print(len(json_data['shapes'])) for shapes in json_data['shapes']: label = shapes['label'] print(label) noduleMalignant = label.split('_')[-1] shapes['label'] = 'nodule_'+noduleMalignant print(shapes['label']) flag = True f.close() return json_data, flag, move_flagclass MyEncoder(json.JSONEncoder): def default(self, obj): if isinstance(obj, np.integer): return int(obj) elif isinstance(obj, np.floating): return float(obj) elif isinstance(obj, np.ndarray): return obj.tolist() else: return super(MyEncoder, self).default(obj)def rewrite_json_file(filepath, json_data): with open(filepath, 'w') as f: json.dump(json_data, f, indent=4, cls=MyEncoder) f.close()import matplotlib.pyplot as pltdef oneDocument(): labelme_json = glob.glob(r'X:\qlj\database\处理前\malignant_1\json/*.json') n=0 label_list = [] for num, json_path in enumerate(labelme_json): # print(json_path) m_json_data, flag, move_flag = get_new_json(json_path) rewrite_json_file(json_path, m_json_data)if __name__ == '__main__': oneDocument()十一、由yolov5学习矩形坐标变换
11.1、xywh2xyxy
def xywh2xyxy(x): print('x:', x) # Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) y[:, 0] = x[:, 0] - x[:, 2] / 2 # top left x y[:, 1] = x[:, 1] - x[:, 3] / 2 # top left y y[:, 2] = x[:, 0] + x[:, 2] / 2 # bottom right x y[:, 3] = x[:, 1] + x[:, 3] / 2 # bottom right y print('y:', y) return y输入和输出的坐标信息如下所示：
x: tensor([[188.29141, 55.49617, 56.29586, 95.01012], [188.17989, 55.49852, 55.87830, 95.67655], [183.24368, 54.52598, 66.56559, 99.71941], [188.91458, 55.26056, 58.75016, 93.95803], [368.82562, 50.15098, 74.95942, 97.38110], ])y: tensor([[160.14348, 7.99111, 216.43935, 103.00124], [160.24074, 7.66025, 216.11903, 103.33680], [149.96089, 4.66628, 216.52647, 104.38568], [159.53951, 8.28154, 218.28966, 102.23957], [331.34592, 1.46043, 406.30533, 98.84154]])11.2、xyxy2xywh
def xyxy2xywh(x): # Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] where xy1=top-left, xy2=bottom-right y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) y[:, 0] = (x[:, 0] + x[:, 2]) / 2 # x center y[:, 1] = (x[:, 1] + x[:, 3]) / 2 # y center y[:, 2] = x[:, 2] - x[:, 0] # width y[:, 3] = x[:, 3] - x[:, 1] # height return y11.3、xywhn2xyxy
从归一化坐标 (x = 0,1) (y = 0,1) 转换到像素坐标 (x = 0, w) (x = 0, h)
def xywhn2xyxy(x, w=640, h=640, padw=0, padh=0): # Convert nx4 boxes from [x, y, w, h] normalized to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) y[:, 0] = w * (x[:, 0] - x[:, 2] / 2) + padw # top left x y[:, 1] = h * (x[:, 1] - x[:, 3] / 2) + padh # top left y y[:, 2] = w * (x[:, 0] + x[:, 2] / 2) + padw # bottom right x y[:, 3] = h * (x[:, 1] + x[:, 3] / 2) + padh # bottom right y return y11.4、xyn2xy
从归一化坐标 (x = 0,1) (y = 0,1) 转换到像素分割坐标 (x = 0, w) (x = 0, h)
def xyn2xy(x, w=640, h=640, padw=0, padh=0): # Convert normalized segments into pixel segments, shape (n,2) y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) y[:, 0] = w * x[:, 0] + padw # top left x y[:, 1] = h * x[:, 1] + padh # top left y return y