"Dive Into OCR" is a textbook that combines OCR theory and practice, written by the PaddleOCR team, Chen Zhineng, a Pre-tenure Professor at Fudan University, Huang Wenhui, a senior expert in the field of vision at China Mobile Research Institute, and other industry-university-research colleagues, as well as OCR developers. The main features are as follows:
"Dive Into OCR" is a textbook that combines OCR theory and practice, written by the PaddleOCR community. The main features are as follows:
- OCR full-stack technology covering text detection, recognition and document analysis
- Closely integrate theory and practice, cross the code implementation gap, and supporting instructional videos
- The first part is the preliminary knowledge of the book, including the knowledge index and resource links needed in the process of positioning and using the book content of the book
- The second part is chapters 4-8 of the book, which introduce the concepts, applications, and industry practices related to the detection and identification capabilities of the OCR engine. In the "Introduction to OCR Technology", the application scenarios and challenges of OCR, the basic concepts of technology, and the pain points in industrial applications are comprehensively explained. Then, in the two chapters of "Text Detection" and "Text Recognition", the two basic tasks of OCR are introduced. In each chapter, an algorithm is accompanied by a detailed explanation of the code and practical exercises. Chapters 6 and 7 are a detailed introduction to the PP-OCR series model, PP-OCR is a set of OCR systems for industrial applications, on the basis of the basic detection and identification model, after a series of optimization strategies to achieve the general field of industrial SOTA model, while opening up a variety of predictive deployment solutions, enabling enterprises to quickly land OCR applications.
| det_db_thresh | Binarization threshold value of DB output map | 0.3 |
| det_db_box_thresh | The threshold value of the DB output box. Boxes score lower than this value will be discarded | 0.5 |
| det_db_unclip_ratio | The expanded ratio of DB output box | 2 |
| det_db_score_mode | The parameter that control how the score of the detection frame is calculated. There are 'fast' and 'slow' options. If the text to be detected is curved, it is recommended to use 'slow' | 'fast' |
| det_east_score_thresh | Binarization threshold value of EAST output map | 0.8 |
| det_east_cover_thresh | The threshold value of the EAST output box. Boxes score lower than this value will be discarded | 0.1 |
| det_east_nms_thresh | The NMS threshold value of EAST model output box | 0.2 |
logger.error("error in loading image:{}".format(image_file))
returnNone
ifisinstance(img,np.ndarray)andlen(img.shape)==2:
img=cv2.cvtColor(img,cv2.COLOR_GRAY2BGR)
returnimg
classPaddleOCR(predict_system.TextSystem):
def__init__(self,**kwargs):
"""
...
...
@@ -482,7 +509,7 @@ class PaddleOCR(predict_system.TextSystem):
rec: use text recognition or not. If false, only det will be exec. Default is True
cls: use angle classifier or not. Default is True. If true, the text with rotation of 180 degrees can be recognized. If no text is rotated by 180 degrees, use cls=False to get better performance. Text with rotation of 90 or 270 degrees can be recognized even if cls=False.
"""
assertisinstance(img,(np.ndarray,list,str))
assertisinstance(img,(np.ndarray,list,str,bytes))
ifisinstance(img,list)anddet==True:
logger.error('When input a list of images, det must be false')
exit(0)
...
...
@@ -491,22 +518,8 @@ class PaddleOCR(predict_system.TextSystem):
'Since the angle classifier is not initialized, the angle classifier will not be uesd during the forward process'
)
ifisinstance(img,str):
# download net image
ifimg.startswith('http'):
download_with_progressbar(img,'tmp.jpg')
img='tmp.jpg'
image_file=img
img,flag,_=check_and_read(image_file)
ifnotflag:
withopen(image_file,'rb')asf:
np_arr=np.frombuffer(f.read(),dtype=np.uint8)
img=cv2.imdecode(np_arr,cv2.IMREAD_COLOR)
ifimgisNone:
logger.error("error in loading image:{}".format(image_file))
-[6.2 Test layout analysis results](#62-Test-layout-analysis-results)
-[7 Model export and inference](#7-Model-export-and-inference)
-[7. Model export and inference](#7-Model-export-and-inference)
-[7.1 Model export](#71-Model-export)
-[7.2 Model inference](#72-Model-inference)
...
...
@@ -249,7 +249,7 @@ After starting training normally, you will see the following log output:
**Note that the configuration file for prediction / evaluation must be consistent with the training.**
### 5.2. FGD Distillation Training
### 5.2. FGD Distillation Training
PaddleDetection supports FGD-based [Focal and Global Knowledge Distillation for Detectors](https://arxiv.org/abs/2111.11837v1) The training process of the target detection model of distillation, FGD distillation is divided into two parts `Focal` and `Global`. `Focal` Distillation separates the foreground and background of the image, allowing the student model to focus on the key pixels of the foreground and background features of the teacher model respectively;` Global`Distillation section reconstructs the relationships between different pixels and transfers them from the teacher to the student to compensate for the global information lost in `Focal`Distillation.
