Главная
Study mode:
on
1
Intro
2
Business goal
3
Case 2: the Doctor's Consultation Certificate
4
Case 1: the Death Certificate
5
Data pipeline
6
Mining
7
Original image
8
Line segmentation
9
Baseline
10
Training set definition
11
Data quality
12
Data partitioning: split into text lines
13
Deep-Learning Model
14
Ensemble modelling
15
Model Training Performance
16
Model accuracy
17
Prediction confidence levels
18
Confidence plot
19
Examples target population
20
Examples false positives
21
Statistics false positives
22
Examples low confidence
23
Example: type A
24
Language detection
25
Certificate type detection
26
Preprocessing
27
Training data
28
Nomenclature code
29
Date of Consultation
30
Comparison OCR - Neural Network
31
The Grid (5)
32
Some grid examples
33
Approach
34
Examples: 2 lines
35
Training on histogram features
36
Results number of lines prediction
37
Reading the lines
38
Examples: high confidence false predictions
39
Grid summary
40
Second challenge: different patterns
41
Fourth challenge: rotations
42
Fifth challenge: superposition and readability
43
Step 1: find the stamp
44
Intersection over Union
45
Summary stamp reading
46
Application Integration
47
Conclusion
Description:
Explore a deep learning approach to deciphering doctors' handwriting in this 51-minute Devoxx conference talk. Delve into the development of a data-processing pipeline designed to support human data entry of medical information from handwritten documents. Learn about the challenges of digitizing handwritten medical records and how machine learning can improve accuracy and efficiency. Discover the end-to-end process, from data mining and anonymization to image processing and deep learning model construction. Examine real-life examples and statistics demonstrating the model's effectiveness in reducing illegible handwritings by 30%. Gain insights into the application of AI modeling for doctor's handwriting across various use cases, including death certificates and consultation certificates. Follow the speaker's journey through data preprocessing, model training, confidence level calculations, and integration of natural language processing techniques. Understand how this innovative approach compares to traditional OCR methods and addresses challenges such as language detection, certificate type identification, and complex handwriting patterns. Read more

Deciphering Doctor's Handwriting with Deep Learning

Devoxx
Add to list
0:00 / 0:00