OCR with OpenCV, Tesseract, and Python - Intro to OCR

Companion Website......Page 3
Acronyms......Page 11
1 Introduction......Page 15
1.3 Do I Need to Know Deep Learning?......Page 16
1.5 Summary......Page 17
2 What Is Optical Character Recognition?......Page 19
2.2.1 A Brief History of OCR......Page 20
2.2.2 Applications of OCR......Page 21
2.2.4 The Importance of Pre-Processing and Post-Processing......Page 22
2.3 Summary......Page 23
3.2 OCR Tools and Libraries......Page 25
3.2.1 Tesseract......Page 26
3.2.4 OpenCV......Page 27
3.2.5 Keras, TensorFlow, and scikit-learn......Page 28
3.2.6 Cloud OCR APIs......Page 29
3.3 Summary......Page 30
4.2.1 A Note on Install Instructions......Page 31
4.2.2.2 Installing Tesseract on Ubuntu......Page 32
4.2.2.5 Verifying Your Tesseract Install......Page 33
4.2.5 Installing Other Computer Vision, Deep Learning, and Machine Learning Libraries......Page 34
4.3 Summary......Page 35
5 Your First OCR Project with Tesseract......Page 37
5.1 Chapter Learning Objectives......Page 38
5.2.2 Basic OCR with Tesseract......Page 39
5.2.3 Tesseract OCR Results......Page 41
5.3 Summary......Page 43
6 Detecting and OCR'ing Digits with Tesseract......Page 45
6.2.1 What Is Digit Detection and Recognition?......Page 46
6.2.3 OCR'ing Digits with Tesseract and OpenCV......Page 47
6.2.4 Digit OCR Results......Page 49
6.3 Summary......Page 50
7.2.1 What Are Whitelists and Blacklists?......Page 51
7.2.3 Whitelisting and Blacklisting Characters with Tesseract......Page 52
7.2.4 Whitelisting and Blacklisting with Tesseract Results......Page 54
7.3 Summary......Page 57
8.1 Chapter Learning Objectives......Page 59
8.2 What Is Orientation and Script Detection?......Page 60
8.3.2 Implementing Our Text Orientation and Correction Script......Page 61
8.3.3 Text Orientation and Correction Results......Page 63
8.4 Summary......Page 66
9.2 OCR and Language Translation......Page 69
9.2.1 Translating Text to Different Languages with textblob......Page 70
9.2.3 Implementing Our OCR and Language Translation Script......Page 71
9.2.4 OCR Language Translation Results......Page 72
9.3 Summary......Page 73
10.2.1 Configuring Tesseract for Multiple Languages......Page 75
10.2.2 Adding Language Packs to Tesseract......Page 76
10.2.3 The textblob Package's Relation to This Chapter......Page 77
10.2.4 Verifying Tesseract Support for Non-English Languages......Page 78
10.3.2 Implementing Our Tesseract with Non-English Languages Script......Page 79
10.3.3 Tesseract and Non-English Languages Results......Page 81
10.4 Summary......Page 84
11 Improving OCR Results with Tesseract Options......Page 85
11.2.1 What Are Page Segmentation Modes?......Page 86
11.2.2 Project Structure......Page 88
11.2.3 PSM 0. Orientation and Script Detection Only......Page 89
11.2.4 PSM 1. Automatic Page Segmentation with OSD......Page 91
11.2.6 PSM 3. Fully Automatic Page Segmentation, But No OSD......Page 92
11.2.7 PSM 4. Assume a Single Column of Text of Variable Sizes......Page 93
11.2.8 PSM 5. Assume a Single Uniform Block of Vertically Aligned Text......Page 96
11.2.9 PSM 6. Assume a Single Uniform Block of Text......Page 99
11.2.10 PSM 7. Treat the Image as a Single Text Line......Page 101
11.2.11 PSM 8. Treat the Image as a Single Word......Page 102
11.2.12 PSM 9. Treat the Image as a Single Word in a Circle......Page 103
11.2.14 PSM 11. Sparse Text: Find as Much Text as Possible in No Particular Order......Page 104
11.2.16 PSM 13. Raw Line: Treat the Image as a Single Text Line, Bypassing Hacks That Are Tesseract-Specific......Page 107
11.2.17 Tips, Suggestions, and Best Practices for PSM Modes......Page 108
11.3 Summary......Page 109
12.1 Chapter Learning Objectives......Page 111
12.2.2 When Tesseract by Itself Fails to OCR an Image......Page 112
12.2.3 Implementing an Image Processing Pipeline for OCR......Page 114
12.3 Summary......Page 119
13.2 OCR and Spellchecking......Page 121
13.2.2 Implementing Our OCR Spellchecking Script......Page 122
13.2.3 OCR Spellchecking Results......Page 124
13.3 Summary......Page 125
14.1 Chapter Learning Objectives......Page 127
14.2.1 What Is a Machine-Readable Zone?......Page 128
14.2.2 Project Structure......Page 129
14.2.3 Locating MRZs in Passport Images......Page 130
14.2.4 Text Blob Localization Results......Page 136
14.3 Summary......Page 138
15.2 OCR'ing Text via Template Matching......Page 141
15.2.1 The OCR-A, OCR-B, and MICR E-13B Fonts......Page 142
15.2.2 Project Structure......Page 143
15.2.3 Credit Card OCR with Template Matching and OpenCV......Page 144
15.2.4 Credit Card OCR Results......Page 153
15.3 Summary......Page 155
16 OCR'ing Characters with Basic Image Processing......Page 157
16.2.1 The 7-Segment Display......Page 158
16.2.2 Project Structure......Page 159
16.2.3 Implementing Our 7-Segment Visualization Utilities......Page 160
16.2.4 Visualizing Digits on a 7-Segment Display......Page 163
16.2.5 Creating Our 7-Segment Digit Recognizer......Page 164
16.2.6 Digit OCR with Image Processing and OpenCV......Page 166
16.2.7 The 7-Segment Digit OCR Results......Page 169
16.3 Summary......Page 170
17.1 Chapter Learning Objectives......Page 173
17.2.1 What Is Text Localization and Detection?......Page 174
17.2.3 Drawing OCR'd Text with OpenCV......Page 175
17.2.4 Implementing Text Localization and OCR with Tesseract......Page 176
17.2.5 Text Localization and OCR Results......Page 178
17.3 Summary......Page 180
18.1 Chapter Learning Objectives......Page 183
18.2.1 Why Is Natural Scene Text Detection So Challenging?......Page 184
18.2.2 EAST Deep Learning Text Detector......Page 186
18.2.3 Project Structure......Page 187
18.2.4 Creating Our Rotated Text Detector Helper Functions......Page 188
18.2.5 Implementing the EAST Text Detector with OpenCV......Page 191
18.2.6 Rotated Text Bounding Box Results......Page 195
18.3 Summary......Page 197
19 A Complete Text Detection and OCR Pipeline......Page 199
19.2.1 How to Combine Text Detection and OCR with OpenCV......Page 200
19.2.3 Implementing Our Text Detection and OCR Pipeline......Page 201
19.2.4 Text Detection and OCR with OpenCV Results......Page 207
19.3 Summary......Page 209
20 Conclusions......Page 211
Bibliography......Page 213