Table Transformer做表格检测和识别实践(clh锅)

Table Transformer做表格检测和识别实践

推荐整理分享Table Transformer做表格检测和识别实践(clh锅)，希望有所帮助，仅作参考，欢迎阅读内容。

文章相关热门搜索词:clh锅,ambition锅,锅具 wmf,锅mini,wmm锅,sentruth锅,sentruth锅,sentruth锅,内容如对您有帮助，希望把文章链接给更多的朋友！

计算机视觉方面的三大顶级会议：ICCV,CVPR,ECCV.统称ICE CVPR 2022文档图像分析与识别相关论文26篇汇集简介

论文： PubTables-1M: Towards comprehensive table extraction from unstructured documents是发表于CVPR上的一篇论文 作者发布了两个模型，表格检测和表格结构识别。

论文讲解可以参考【论文阅读】PubTables- 1M: Towards comprehensive table extraction from unstructured documents

hugging face Table Transformer 使用文档 hugging face Table DETR 使用文档

检测表格from huggingface_hub import hf_hub_downloadfrom transformers import AutoImageProcessor, TableTransformerForObjectDetectionimport torchfrom PIL import Imagefile_path = hf_hub_download(repo_id="nielsr/example-pdf", repo_type="dataset", filename="example_pdf.png")image = Image.open(file_path).convert("RGB")image_processor = AutoImageProcessor.from_pretrained("microsoft/table-transformer-detection")model = TableTransformerForObjectDetection.from_pretrained("microsoft/table-transformer-detection")inputs = image_processor(images=image, return_tensors="pt")outputs = model(**inputs)# convert outputs (bounding boxes and class logits) to COCO APItarget_sizes = torch.tensor([image.size[::-1]])results = image_processor.post_process_object_detection(outputs, threshold=0.9, target_sizes=target_sizes)[ 0]for score, label, box in zip(results["scores"], results["labels"], results["boxes"]): box = [round(i, 2) for i in box.tolist()] print( f"Detected {model.config.id2label[label.item()]} with confidence " f"{round(score.item(), 3)} at location {box}" ) region = image.crop(box) #检测 region.save('xxx.jpg') #保存# Detected table with confidence 1.0 at location [202.1, 210.59, 1119.22, 385.09]

结果 ：效果不错

表格结构识别

参考：https://github.com/NielsRogge/Transformers-Tutorials/blob/master/Table%20Transformer/Using_Table_Transformer_for_table_detection_and_table_structure_recognition.ipynb

import torchfrom PIL import Imagefrom transformers import DetrFeatureExtractorfrom transformers import AutoImageProcessor, TableTransformerForObjectDetectionfrom huggingface_hub import hf_hub_downloadfeature_extractor = DetrFeatureExtractor()file_path = hf_hub_download(repo_id="nielsr/example-pdf", repo_type="dataset", filename="example_pdf.png")image = Image.open(file_path).convert("RGB")encoding = feature_extractor(image, return_tensors="pt")model = TableTransformerForObjectDetection.from_pretrained("microsoft/table-transformer-structure-recognition")with torch.no_grad(): outputs = model(**encoding)target_sizes = [image.size[::-1]]results = feature_extractor.post_process_object_detection(outputs, threshold=0.6, target_sizes=target_sizes)[0]# plot_results(image, results['scores'], results['labels'], results['boxes'])results

获取列图像:

columns_box_list = [results['boxes'][i].tolist() for i in range(len(results['boxes'])) if results['labels'][i].item()==1]columns_1 = image.crop(columns_box_list[0]) columns_1.save('columns_1.jpg') #保存

可视化：import matplotlib.pyplot as plt# colors for visualizationCOLORS = [[0.000, 0.447, 0.741], [0.850, 0.325, 0.098], [0.929, 0.694, 0.125], [0.494, 0.184, 0.556], [0.466, 0.674, 0.188], [0.301, 0.745, 0.933]]def plot_results(pil_img, scores, labels, boxes): plt.figure(figsize=(16, 10)) plt.imshow(pil_img) ax = plt.gca() colors = COLORS * 100 for score, label, (xmin, ymin, xmax, ymax), c in zip(scores.tolist(), labels.tolist(), boxes.tolist(), colors): ax.add_patch(plt.Rectangle((xmin, ymin), xmax - xmin, ymax - ymin, fill=False, color=c, linewidth=3)) text = f'{model.config.id2label[label]}: {score:0.2f}' ax.text(xmin, ymin, text, fontsize=15, bbox=dict(facecolor='yellow', alpha=0.5)) plt.axis('off') plt.show()post_process_object_detection方法：

OpenCV PIL图像格式互转

参考：https://blog.csdn.net/dcrmg/article/details/78147219

PIL–》OpenCV

cv2.cvtColor(numpy.asarray(image),cv2.COLOR_RGB2BGR)import cv2from PIL import Imageimport numpyimage = Image.open("plane.jpg")image.show()img = cv2.cvtColor(numpy.asarray(image),cv2.COLOR_RGB2BGR)cv2.imshow("OpenCV",img)cv2.waitKey()

OpenCV --》 PIL

Image.fromarray(cv2.cvtColor(img,cv2.COLOR_BGR2RGB))import cv2from PIL import Imageimport numpyimg = cv2.imread("plane.jpg")cv2.imshow("OpenCV",img)image = Image.fromarray(cv2.cvtColor(img,cv2.COLOR_BGR2RGB))image.show()cv2.waitKey()

综上，模型检测列代码如下

# 检测模型import cv2from huggingface_hub import hf_hub_downloadfrom transformers import AutoImageProcessor, TableTransformerForObjectDetectionimport torchfrom PIL import Imageimport torchfrom PIL import Imagefrom transformers import DetrFeatureExtractorfrom transformers import AutoImageProcessor, TableTransformerForObjectDetectionfrom huggingface_hub import hf_hub_downloadimport numpy as npimport matplotlib.pyplot as pltimport cv2def dectect_table(file_path): # file_path = hf_hub_download(repo_id="nielsr/example-pdf", repo_type="dataset", filename="example_pdf.png") image = Image.open(file_path).convert("RGB") # transformers.AutoImageProcessor 是一个通用图像处理器 image_processor = AutoImageProcessor.from_pretrained("microsoft/table-transformer-detection") model = TableTransformerForObjectDetection.from_pretrained("microsoft/table-transformer-detection") inputs = image_processor(images=image, return_tensors="pt") outputs = model(**inputs) # convert outputs (bounding boxes and class logits) to COCO API target_sizes = torch.tensor([image.size[::-1]]) results = image_processor.post_process_object_detection(outputs, threshold=0.9, target_sizes=target_sizes)[ 0 ] box_list = [] for score, label, box in zip(results["scores"], results["labels"], results["boxes"]): box = [round(i, 2) for i in box.tolist()] print( f"Detected {model.config.id2label[label.item()]} with confidence " f"{round(score.item(), 3)} at location {box}" ) box_list.append(box) region = image.crop(box) #检测 # region.save('xxx.jpg') #保存 return region#def plot_results(pil_img, scores, labels, boxes): # colors for visualization COLORS = [[0.000, 0.447, 0.741], [0.850, 0.325, 0.098], [0.929, 0.694, 0.125], [0.494, 0.184, 0.556], [0.466, 0.674, 0.188], [0.301, 0.745, 0.933]] plt.figure(figsize=(16, 10)) plt.imshow(pil_img) ax = plt.gca() colors = COLORS * 100 for score, label, (xmin, ymin, xmax, ymax), c in zip(scores.tolist(), labels.tolist(), boxes.tolist(), colors): if label == 1: ax.add_patch(plt.Rectangle((xmin, ymin), xmax - xmin, ymax - ymin, fill=False, color=c, linewidth=3)) # text = f'{model.config.id2label[label]}: {score:0.2f}' text = f'{score:0.2f}' ax.text(xmin, ymin, text, fontsize=15, bbox=dict(facecolor='yellow', alpha=0.5)) plt.axis('off') plt.show()def cv_show(img): ''' 展示图片 @param img: @param name: @return: ''' cv2.namedWindow('name', cv2.WINDOW_KEEPRATIO) # cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO cv2.imshow('name', img) cv2.waitKey(0) cv2.destroyAllWindows()def dect_col(file_path): ''' 识别列 :param file_path: :return: ''' # example_table= region # width, height = image.size # image.resize((int(width * 0.5), int(height * 0.5))) table = dectect_table(file_path) # 截取左半边 feature_extractor = DetrFeatureExtractor() # file_path = hf_hub_download(repo_id="nielsr/example-pdf", repo_type="dataset", filename="example_table.png") # image = Image.open(file_path).convert("RGB") # image = cv2.imread(file_path) left_table = table.crop((0, 0, table.size[0]//2,table.size[1])) encoding = feature_extractor(left_table, return_tensors="pt") model = TableTransformerForObjectDetection.from_pretrained("microsoft/table-transformer-structure-recognition") with torch.no_grad(): outputs = model(**encoding) target_sizes = [left_table.size[::-1]] results = feature_extractor.post_process_object_detection(outputs, threshold=0.6, target_sizes=target_sizes)[0] plot_results(left_table, results['scores'], results['labels'], results['boxes']) # columns_box_list = [results['boxes'][i].tolist() for i in range(len(results['boxes'])) if results['labels'][i].item()==1] # columns_box_list.sort() # columns_1 = left_table.crop(columns_box_list[0]) # left, upper, right, lower # columns_1.save('columns_1.jpg') #保存 return columns_box_listdect_col(r'xxxx.jpg')