该方案针对2021广东工业智造创新大赛瓷砖瑕疵检测任务，基于Paddle2.2及PaddleDetection套件的FasterRCNN模型实现。处理初赛白板瓷砖数据（含15230张训练图、1762张测试图），将标注转为COCO格式，划分训练集与验证集，经训练、评估后，生成符合竞赛要求的预测提交文件，以实现瓷砖瑕疵的定位与分类。
☞☞☞AI 智能聊天, 问答助手, AI 智能搜索, 免费无限量使用 DeepSeek R1 模型☜☜☜
佛山作为国内最大的瓷砖生产制造基地之一，拥有众多瓷砖厂家和品牌。经前期调研，瓷砖生产环节一般（不同类型砖工艺不一样，这里以抛釉砖为例）经过原材料混合研磨、脱水、压胚、喷墨印花、淋釉、烧制、抛光，最后进行质量检测和包装。得益于产业自动化的发展，目前生产环节已基本实现无人化。而质量检测环节仍大量依赖人工完成。一般来说，一条产线需要配2～6名质检工，长时间在高光下观察瓷砖表面寻找瑕疵。这样导致质检效率低下、质检质量层次不齐且成本居高不下。瓷砖表检是瓷砖行业生产和质量管理的重要环节，也是困扰行业多年的技术瓶颈。
本赛场聚焦瓷砖表面瑕疵智能检测，要求选手开发出高效可靠的计算机视觉算法，提升瓷砖表面瑕疵质检的效果和效率，降低对大量人工的依赖。要求算法尽可能快与准确的给出瓷砖疵点具体的位置和类别，主要考察疵点的定位和分类能力。
赛题数据说明： 大赛深入到佛山瓷砖知名企业，在产线上架设专业拍摄设备，实地采集生产过程真实数据，解决企业真实的痛点需求。大赛数据覆盖到了瓷砖产线所有常见瑕疵，包括粉团、角裂、滴釉、断墨、滴墨、B孔、落脏、边裂、缺角、砖渣、白边等。实拍图示例如下：
针对某些缺陷在特定视角下的才能拍摄到，每块砖拍摄了三张图，包括低角度光照黑白图、高角度光照黑白图、彩色图，示例如下：
数据主要分为两种：
初赛数据集： 白板数据包含有瑕疵图片、无瑕疵图片和标注数据。标注数据标注瑕疵位置和类别信息。训练集共15230张，测试集A共1762张
└── dataset
├── Readme.md
├── train_annos.json
└── train_imgs!pip install scikit-image
#安装至全局，如果重启项目，这几个依赖和库需要重新安装%cd /home/aistudio/cocoapi/PythonAPI !make install %cd ../..
#解压paddle的目标检测套件源码!unzip /home/aistudio/data/data113827/PaddleDetection-release-2.2_tile.zip -d work/
#安装依赖%cd /home/aistudio/work/PaddleDetection-release-2.2!pip install -r requirements.txt !python setup.py install
#解压数据集，训练集先放work路径下，后面划分验证集时候在弄到paddledetection下，测试集直接放过去# 该过程需要3mins多钟!unzip /home/aistudio/data/data66771/tile_round1_train_20201231.zip -d /home/aistudio/work/dataset !unzip /home/aistudio/data/data66771/tile_round1_testA_20201231.zip -d /home/aistudio/work/PaddleDetection-release-2.2/dataset/coco
#注意路径要正确，大部分已经改成绝对路径%cd ..
/home/aistudio/work
#调用一些需要的第三方库import numpy as npimport pandas as pdimport shutilimport jsonimport osimport cv2import globfrom PIL import Image
path = "/home/aistudio/work/dataset/tile_round1_train_20201231/train_imgs/220_146_t20201124140430373_CAM1.jpg"img1=cv2.imread(path)print(img1.shape) img2=Image.open(path)print(img2.size)
(6000, 8192, 3) (8192, 6000)
#统计一下类别path = "/home/aistudio/work/dataset/tile_round1_train_20201231/train_annos.json"dict_class = { "0":0, "1":0, "2":0, "3":0, "4":0, "5":0, "6":0}
id_s = 0image_width,image_height = 0,0with open(path,"r") as f:
files = json.load(f) #遍历标注文件
for file_img in files:
id_s += 1
#统计类别
file_class = file_img["category"]
dict_class[str(file_class)] += 1
#统计图片平均像素
image_height += file_img["image_height"]
image_width += file_img["image_width"] if id_s % 1000 is 0: print("处理到第{}个标注".format(id_s))print("类别：",dict_class)print("图片平均高{},图片平均宽{}".format(image_height/id_s,image_width/id_s))class Fabric2COCO:
def __init__(self,
is_mode = "train"
):
self.images = []
self.annotations = []
self.categories = []
self.img_id = 0
self.ann_id = 0
self.is_mode = is_mode if not os.path.exists("/home/aistudio/work/PaddleDetection-release-2.2/dataset/coco/{}".format(self.is_mode)):
os.makedirs("/home/aistudio/work/PaddleDetection-release-2.2/dataset/coco/{}".format(self.is_mode)) def to_coco(self, anno_file,img_dir):
self._init_categories()
anno_result= pd.read_json(open(anno_file,"r"))
if self.is_mode == "train":
anno_result = anno_result.head(int(anno_result['name'].count()*0.9))#取数据集前百分之90
elif self.is_mode == "val":
anno_result = anno_result.tail(int(anno_result['name'].count()*0.1))
name_list=anno_result["name"].unique()#返回唯一图片名字
for img_name in name_list:
img_anno = anno_result[anno_result["name"] == img_name]#取出此图片的所有标注
bboxs = img_anno["bbox"].tolist()#返回list
defect_names = img_anno["category"].tolist() assert img_anno["name"].unique()[0] == img_name
img_path=os.path.join(img_dir,img_name) #img =cv2.imread(img_path)
#h,w,c=img.shape
#这种读取方法更快
img = Image.open(img_path)
w, h = img.size #h,w=6000,8192
self.images.append(self._image(img_path,h, w))
self._cp_img(img_path)#复制文件路径
if self.img_id % 200 is 0: print("处理到第{}张图片".format(self.img_id)) for bbox, label in zip(bboxs, defect_names):
annotation = self._annotation(label, bbox)
self.annotations.append(annotation)
self.ann_id += 1
self.img_id += 1
instance = {}
instance['info'] = 'fabric defect'
instance['license'] = ['none']
instance['images'] = self.images
instance['annotations'] = self.annotations
instance['categories'] = self.categories return instance def _init_categories(self):
#1，2，3，4，5，6个类别
for v in range(1,7): print(v)
category = {}
category['id'] = v
category['name'] = str(v)
category['supercategory'] = 'defect_name'
self.categories.append(category) def _image(self, path,h,w):
image = {}
image['height'] = h
image['width'] = w
image['id'] = self.img_id
image['file_name'] = os.path.basename(path)#返回path最后的文件名
return image def _annotation(self,label,bbox):
area=(bbox[2]-bbox[0])*(bbox[3]-bbox[1])
points=[[bbox[0],bbox[1]],[bbox[2],bbox[1]],[bbox[2],bbox[3]],[bbox[0],bbox[3]]]
annotation = {}
annotation['id'] = self.ann_id
annotation['image_id'] = self.img_id
annotation['category_id'] = label
annotation['segmentation'] = []# np.asarray(points).flatten().tolist()
annotation['bbox'] = self._get_box(points)
annotation['iscrowd'] = 0
annotation["ignore"] = 0
annotation['area'] = area return annotation def _cp_img(self, img_path):
shutil.copy(img_path, os.path.join("/home/aistudio/work/PaddleDetection-release-2.2/dataset/coco/{}".format(self.is_mode), os.path.basename(img_path))) def _get_box(self, points):
min_x = min_y = np.inf
max_x = max_y = 0
for x, y in points:
min_x = min(min_x, x)
min_y = min(min_y, y)
max_x = max(max_x, x)
max_y = max(max_y, y) '''coco,[x,y,w,h]'''
return [min_x, min_y, max_x - min_x, max_y - min_y] def save_coco_json(self, instance, save_path):
import json with open(save_path, 'w') as fp:
json.dump(instance, fp, indent=1, separators=(',', ': '))#缩进设置为1，元素之间用逗号隔开 ， key和内容之间 用冒号隔开'''转换有瑕疵的样本为coco格式'''#训练集,划分90%做为训练集img_dir = "/home/aistudio/work/dataset/tile_round1_train_20201231/train_imgs"anno_dir="/home/aistudio/work/dataset/tile_round1_train_20201231/train_annos.json"fabric2coco = Fabric2COCO()
train_instance = fabric2coco.to_coco(anno_dir,img_dir)if not os.path.exists("/home/aistudio/work/PaddleDetection-release-2.2/dataset/coco/annotations/"):
os.makedirs("/home/aistudio/work/PaddleDetection-release-2.2/dataset/coco/annotations/")
fabric2coco.save_coco_json(train_instance, "/home/aistudio/work/PaddleDetection-release-2.2/dataset/coco/annotations/"+'instances_{}.json'.format("train"))'''转换有瑕疵的样本为coco格式'''#验证集，划分10%做为验证集img_dir = "/home/aistudio/work/dataset/tile_round1_train_20201231/train_imgs"anno_dir="/home/aistudio/work/dataset/tile_round1_train_20201231/train_annos.json"fabric2coco = Fabric2COCO(is_mode = "val")
train_instance = fabric2coco.to_coco(anno_dir,img_dir)if not os.path.exists("/home/aistudio/work/PaddleDetection-release-2.2/dataset/coco/annotations/"):
os.makedirs("/home/aistudio/work/PaddleDetection-release-2.2/dataset/coco/annotations/")
fabric2coco.save_coco_json(train_instance, "/home/aistudio/work/PaddleDetection-release-2.2/dataset/coco/annotations/"+'instances_{}.json'.format("val"))
#开始训练%cd /home/aistudio/work/PaddleDetection-release-2.2/#%env CUDA_VISIBLE_DEVICES=0!python tools/train.py \
-c /home/aistudio/work/faster_rcnn_r50_fpn_2x.yml \
-r /home/aistudio/work/PaddleDetection-release-2.2/output/faster_rcnn_r50_fpn_2x/12.pdparams --eval模型评估需要指定被评估模型，如-o weights=output/faster_rcnn_r50_fpn_2x/best_model.pdparams：
#模型评估%cd /home/aistudio/work/PaddleDetection-release-2.2/
!python tools/eval.py \
-c /home/aistudio/work/faster_rcnn_r50_fpn_2x.yml \
-o weights=/home/aistudio/work/PaddleDetection-release-2.2/output/faster_rcnn_r50_fpn_2x/best_model.pdparams模型预测调用tools/infer.py文件，需要指定模型路径、被预测的图像路径如--infer_img=dataset/coco/val/235_7_t20201127123214965_CAM2.jpg、预测结果输出目录如--output_dir=infer_output/等：
预测结果会直接画在图像上保存在output_dir目录下。
#模型预测%cd /home/aistudio/work/PaddleDetection-release-2.2/
!python -u tools/infer.py \
-c /home/aistudio/work/faster_rcnn_r50_fpn_2x.yml \
--output_dir=infer_output/ \
--save_txt=True \
-o weights=/home/aistudio/work/PaddleDetection-release-2.2/output/faster_rcnn_r50_fpn_2x/best_model.pdparams \
--infer_img=/home/aistudio/work/PaddleDetection-release-2.2/dataset/coco/val/235_7_t20201127123214965_CAM2.jpg将测试集生成标注文件代码如下，生成的测试集标注文件存放在dataset/coco/annotations/instances_test.json：
#生成个test标注文件（无效的）import os, sys, zipfileimport urllib.requestimport shutilimport numpy as npimport skimage.io as ioimport pandasimport matplotlib.pyplot as pltimport pylabimport jsonimport tqdmfrom PIL import Image#generate test def test_from_dir(pic_path):
pics = os.listdir(pic_path)
meta = {}
images = []
annotations = []
categories=[] for v in range(1,7):
category = {}
category['id'] = v
category['name'] = str(v)
category['supercategory'] = 'defect_name'
categories.append(category)
num = 0
for im in pics:
num += 1
annotation = { "area": 326.1354999999996, "iscrowd": 0, "image_id": num, "bbox": [ 1654.76, 2975, 22, 15
], "category_id": 5, "ignore": 0, "segmentation": [], "id": num
}
img = os.path.join(pic_path,im)
img = Image.open(img)
images_anno = {}
images_anno['file_name'] = im
images_anno['width'] = img.size[0]
images_anno['height'] = img.size[1]
images_anno['id'] = num
images.append(images_anno)
annotations.append(annotation)
meta['images'] = images
meta['categories'] = categories
meta['annotations'] = annotations print(len(annotations))
json.dump(meta,open('/home/aistudio/work/PaddleDetection-release-2.2/dataset/coco/annotations/instances_test.json','w'),indent=4, ensure_ascii=False)#生成测试集标注（伪标注，无效的）pic_path='/home/aistudio/work/PaddleDetection-release-2.2/dataset/coco/tile_round1_testA_20201231/testA_imgs'test_from_dir(pic_path)
1762
运行模型评估，数据集指向测试集。本案例为大家提供了修改完数据配置的配置文件faster_rcnn_r50_fpn_2x_test.yml：
#模型评估（预测），标注在生成的bbox.json文件中，注意要把read配置文件中的eval部分的batch_size改成1，不然会报错，这边已经改好了# 该过程大概需要一个半小时%cd /home/aistudio/work/PaddleDetection-release-2.2!python tools/eval.py \
-c /home/aistudio/work/faster_rcnn_r50_fpn_2x_test.yml \
-o weights=/home/aistudio/work/PaddleDetection-release-2.2/output/faster_rcnn_r50_fpn_2x/best_model.pdparams \
save_prediction_only=True#将评估预测的结果按照我们生成的测试集伪标注格式保存bbox = '/home/aistudio/work/PaddleDetection-release-2.2/bbox.json'test_path = '/home/aistudio/work/PaddleDetection-release-2.2/dataset/coco/annotations/instances_test.json'sub_path = '/home/aistudio/work/PaddleDetection-release-2.2/results.json'def make_submittion(sub_path,bbox,test_path):
meta = {} with open(bbox) as f:
bbox = json.load(f) with open(test_path) as f:
test_ann = json.load(f)
meta['images'] = test_ann['images']
meta['annotations'] = bbox
json.dump(meta,open(sub_path,'w'),indent=4)
make_submittion(sub_path,bbox,test_path)
final_path = '/home/aistudio/work/PaddleDetection-release-2.2/final_results.json'results_path = '/home/aistudio/work/PaddleDetection-release-2.2/results.json'def final_result(final_path, results_path):
with open(results_path,"r") as f:
test_result = json.load(f) #获取图片id对应的图片名字字典
imgs = test_result["images"]
dict_img = {} for img in imgs:
img_name = img["file_name"]
img_id = img["id"]
dict_img[str(img_id)] = img_name #print("*******",dict_img)
#按照提交格式对应字段
final_results = []
annotations = test_result["annotations"] for ann in annotations:
dict_ann = {} #设置图片name
#将图片id对应为name
ann_name_id = str(ann["image_id"])
dict_ann["name"] = dict_img[ann_name_id] #设置类别category
dict_ann["category"] = ann["category_id"] #设置bbox
#之前预测的bbox中格式为【左上角横坐标x，左上角纵坐标y，框的高h，框的宽w】
#提交格式要求的bbox格式为【左上角横坐标，左上角纵坐标，右下角横坐标，右下角纵坐标】
bbox = ann["bbox"]
bbox = [bbox[0],bbox[1],bbox[0]+bbox[2],bbox[1]+bbox[3]]
dict_ann["bbox"] = bbox #设置置信度score
dict_ann["score"] = ann["score"]
final_results.append(dict_ann)
#print(final_results[0])
json.dump(final_results,open(final_path,'w'),indent=4)
final_result(final_path, results_path)通过上面的代码得到了竞赛提交文件final_results.json。
以上就是2021广东工业智造创新大赛-瓷砖瑕疵检测方案的详细内容，更多请关注php中文网其它相关文章！
每个人都需要一台速度更快、更稳定的 PC。随着时间的推移，垃圾文件、旧注册表数据和不必要的后台进程会占用资源并降低性能。幸运的是，许多工具可以让 Windows 保持平稳运行。
Copyright 2014-2025 https://www.php.cn/ All Rights Reserved | php.cn | 湘ICP备2023035733号
863
收藏
