1st Edition officialy released — Grab your copy now!

I lead a large team here at GE, and I gotta say, your books are awesome. I've been able to considerably strengthen my knowledge about deep learning and machine vision, which in turn has enabled me to steer the team in entirely new directions. We're working on some really cool things thanks to what your literature has taught me.”

Magnus AkessonCIO and VP at General Electric

Take a sneak peek at what's inside...

Practical, real-world projects.

The chapters in this book cover real-world use cases, including aligning and OCR'ing invoices, Automatic License/Number Plate Recognition, OCR'ing and translating text, and handwriting recognition, just to name a few. What you learn in this book will directly translate to your own OCR projects.

Clear, easy-to-follow tutorials.

This book won't bury you under a pile of theory or pages and pages of complex equations. Instead, you'll learn through intuitive chapters that are super practical and present solutions to actual real-world OCR problems. By the end of this book you'll be able to successfully apply OCR to your own projects.

Expert advice.

Inevitability, when working on your projects you'll have a question. Questions are a good thing — they mean you're pushing the boundaries of your current knowledge, and are looking to expand your understanding. With our unparalleled support you know your question won't get left unanswered.

Hands-on coding.

In this book you will learn by doing. You'll roll up your sleeves and get your hands dirty with code. Each and every chapter starts with an empty directory. We then design the project and write the code from scratch. Along the way I explain what every line of code is doing, ensuring you not only understand we are doing but we are doing it.

Unparalleled support.

I hold myself and PyImageSearch to an incredibly high standard. When you buy a book or course from me, you're not just getting the content itself — you're also getting access to me and the PyImageSearch team. We are committed to helping you not only learn OCR, but successfully apply OCR to your projects as well. I'm ready to order my copy now

As a computer scientist who had no previous experience with ML (and forgot everything I learned in my math courses) the book was easy to follow/understand and at the same time covered almost all the important details. It helped me "catch up" very quickly to the point I feel like I can start building projects! In other words.. worth every penny!”

Andy HinSoftware Developer

Phenomenal. The concepts on deep learning are so well explained that I will be recommending this book to anybody not just involved in computer vision but AI in general.”

Dr. Zig ZdziarskiPhD in CV and ML

Optical Character Recognition (OCR) is a simple concept but is hard in practice.

The goal of OCR is to Create a piece of software that accepts an input image, automatically recognize the text in the image, and then convert it to machine encoded text (i.e., a "string" data type).

For example, if I were to present the following image to my OCR algorithm, I would expect it to detect the text, recognize the text, and then encode the text as a string variable.

But despite being such an intuitive concept, OCR is incredibly hard. The field of computer vision has existed for over 50 years (with mechanical OCR machines dating back over 100 years), but we still have not "solved" OCR and created an off-the-shelf OCR system that works in nearly any situation.

And worse, trying to code custom software that can perform OCR is even harder:

Open source OCR packages like Tesseract can be difficult to use if you are new to the world of OCR.
Computer vision and image processing libraries such as OpenCV and scikit- image can help you preprocess your images to improve OCR accuracy... but which algorithms and techniques do you use?
Obtaining high accuracy with Tesseract typically requires that you know which options, parameters, and configurations to use — and unfortunately there aren't many high-quality Tesseract tutorials or books online.
Deep learning is responsible for unprecedented accuracy in nearly every area of computer science. Which deep learning models, layer types, and loss functions should you be using for OCR?

If you've ever found yourself struggling to apply OCR to a project, or if you're simply interested in learning OCR, this book is for you.

I'm ready to order my copy now

My brand new book, OCR with OpenCV, Tesseract, and Python, is for developers, students, researchers, and hobbyists just like you who want to learn how to successfully apply Optical Character Recognition to your work, research, and projects.

Regardless of your current experience level with computer vision and OCR, after reading this book you will be armed with the knowledge necessary to tackle your own OCR projects.

Regardless of your experience level, you'll find tremendous value inside OCR with OpenCV, Tesseract, and Python, I guarantee it.

Curious about what you’ll learn?

OCR with Tesseract, OpenCV, and Python will teach you how to successfully apply Optical Character Recognition to your work, projects, and research. You will learn via practical, hands-on projects (with lots of code) so you can not only develop your own OCR Projects, but feel confident while doing so.

Inside the book we will focus on:

  • Getting started with OCR
  • Learning the basics of the Tesseract OCR engine
  • Discovering how to improve OCR accuracy using Tesseract options and configurations
  • Interfacing with Tesseract via the Python programming language
  • Localizing and detecting text in images using both OpenCV and Tesseract
  • Using OpenCV and image processing techniques to improve OCR accuracy
  • Using machine learning to denoise our images for better OCR accuracy
  • Image/document registration and alignment to build an invoice scanning project
  • Training our own custom deep learning OCR models with Keras and TensorFlow
  • Solving Sudoku puzzles with OCR, OpenCV, and Keras/TensorFlow
  • Automatic License/Number Plate Recognition (ANPR)
  • Handwriting recognition
  • Performing OCR in real-time video streams
  • Utilizing GPUs for faster OCR inference
  • Using OCR engines in the cloud (i.e., Google Vision API, Amazon Rekognition, etc.)
  • Tips, suggestions, and best practices when performing OCR

Experienced OCR practitioner?

This book isn't just for beginners — there's advanced concepts, algorithms, and techniques covered here as well:

  • You'll learn how to train custom Keras / TensorFlow OCR models.
  • You'll build an Automatic License/Number Plate Recognition (ANPR) system.
  • You'll learn how to apply OCR to real-time video streams using GPUs for inference.
  • You'll train and fine-tune Tesseract models on your own custom OCR datasets.
  • And you'll learn how to use OCR APIs in the cloud, including Amazon Rekognition, Microsoft Cognitive Services, and Google Vision.

Best of all, the algorithms, walkthroughs, and code can be directly applied to your current job and research.

Libraries and Packages

The primary focus of this book is around Tesseract, which is the world's most popular open source OCR engine. Simply put — if you're interested in learning how to apply OCR to your own projects, you need to learn how to operate the Tesesract OCR engine.

We'll be utilizing the Python programming language in this book. Python is an extremely easy language. It also has easy-to-use libraries and packages that allow us to seamlessly interact with our computer vision, deep learning, and OCR APIs.

When we interact with Tesseract via Python, we'll use PyTesseract. The PyTesseract package interfaces Tesseract, making it easy to OCR images using Python.

For computer vision and image processing, we'll be using OpenCV, the de facto standard library for image processing. You'll find OpenCV easy to use, especially with the hands-on projects covered in the text.

When training our own custom deep learning OCR models, we'll be using Keras and TensorFlow 2. Using Keras and TensorFlow 2 is the fastest, easiest way to go from idea, to experimentation, to result.

You'll also learn how to use cloud-based OCR APIs, including Amazon Rekognition, Microsoft Cognitive Services, and the Google Vision API.

I'm ready to order my copy now

This is one of the best books (if not the BEST) I've found in this subject. Easy to read and easy to understand, with many practical examples. A good combination between theory and hands-on problems. I would recommend it to any person interested in Deep Learning and Computer Vision. Adrian, you are a great teacher!”

Sebastian Adolfo Prieto SanchezProfessor at University of Alcalá

You're probably wondering...
“Is this book right for me?”

This book is for developers, students, researchers, and hobbyists who want to learn how to successfully code Optical Character Recognition project (and have at least some programming/scripting experience).

If any of these descriptions fit you... you're the target student. I am writing this book for you.

  • You are a computer vision developer who needs to learn how to apply OCR to a work project.
  • You write code at your day job and are motivated to stand out from your coworkers by learning OCR.
  • You are an undergrad student doing your final project and want to utilize OCR (and you need to complete the project in order to successfully graduate).
  • You are a MSc or PhD student working on your thesis/dissertation and need a practical, hands-on education to compliment what you are learning in textbooks and research papers.
  • You are a computer science teacher who wants to teach your students how to apply OCR.
  • You are a computer vision researcher who has read OCR papers but are struggling to translate theory into code.
  • You are an entrepreneur in the computer vision/deep learning space and see a gap in the market that OCR could help solve.
  • You are a "computer vision hobbyist" who hacks around with OpenCV and now wants to learn OCR.

Download Free Sample Chapters
and Table of Contents

You're ready to learn OCR, but you're not sure where to start. That's where my new book, OCR with Tesseract, OpenCV, and Python comes in.

I am a firm believer that everything can be explained to anybody with the right words. Adrian Rosebrock excels in this art, and solves complex problems in only a few lines of code, going straight to the point and making it so clear. He makes deep learning so accessible and so exciting!"”

Aline Gendrin BrokmannData Scientist at AstraZeneca

Great material, great courses, great support. Thanks, Adrian.”

Greg ChapmanPrincipal Engineer with Microsoft Game Studios

More than just a book — it's your complete training guide to mastering Optical Character Recognition.

Whether you're brand new to OCR, or have been working with OCR for years, this book will help you reach OCR mastery.

Each bundle includes:

The eBook files in PDF, .mobi, and .epub format.
Access to the OCR with OpenCV, Tesseract, and Python companion website so you can further your knowledge, even when you're done reading the book
High quality, well documented source code
Pre-configured Virtual Machine with all the necessary computer vision, deep learning, and OCR packages pre-configured and pre-installed

The "OCR Expert" Bundle includes a Certificate of Completion.

To receive the certificate, you will need to complete all lessons and quizzes associated with the text.

After successfully completing all lessons/quizzes, you will receive your certificate and be able to embed it directly on your LinkedIn profile, thereby demonstrating your Optical Character Recognition skills.

Regardless of your experience level, you'll find tremendous value inside OCR with OpenCV, Tesseract, and Python, I guarantee it.

Trusted by members of top machine learning companies and schools. Join them in computer vision and OCR mastery.

Hardcopy Bundle
$245
Learn the basics of OCR

No Risk 100% Money Back Guarantee!

Master Optical Character Recognition with OpenCV and Tesseract.

The "OCR Expert" Bundle includes a hardcopy edition of both volumes of OCR with OpenCV, Tesseract, and Python mailed to your doorstep.

This bundle also includes access to my private community forums, a Certificate of Completion, and all bonus chapters included in the text.

Read More...

When it comes to studying Optical Character Recognition, you can't beat this bundle!

  • An exclusive hardcopy edition of both OCR with OpenCV, Tesseract, and Python volumes mailed to your doorstep (this is the only bundle that includes a physical, printed edition of the book).
  • Access to my private community forums for additional help and support. You'll get faster, more detailed answers to your questions, and you'll be able to better connect with myself and other OCR readers.
  • A Certificate of Completion after successfully completing all lessons and quizzes associated with the text. You'll be able to embed the certificate on your LinkedIn profile, demonstrating your OCR skills.
  • High quality, well documented source code so you can run the examples in the book out-of-the-box.
  • A downloadable, pre-configured Ubuntu VirtualBox virtual machine with all the necessary computer vision, deep learning, and OCR packages pre-configured and pre-installed.
  • FREE updates as the book is revised and updated.

No Risk 100% Money Back Guarantee!

PyImageSearch University Bundle
$524 Perfect for you to learn Computer Vision in-depth!

No Risk 100% Money Back Guarantee!

345/year. (subscription) and $179 set-up fee

Take your education to the next level. Access the entire Computer Vision Arduino course, and get access to all 86 inside PyImageSearch University.

You will get:

  • Everything in the OCR Hardcopy package
  • Lifetime access to PyImageSearch University
  • Brand new courses released every month, ensuring you can keep up with state-of-the-art techniques
  • 115 hours of on-demand video
  • 86 courses on essential computer vision, deep learning and OpenCV topics
  • 94 Certificates of Completion
  • 540 tutorials and downloadable resources
  • Pre-configured Jupyter Notebooks in Google Colab for 338 PyImageSearch tutorials
  • Run all code examples in your web browser - works on Windows, macOS, and Linux (no dev environment configuration required!)
  • Access to centralized code repos for all 348 tutorials on PyImageSearch
  • Easy one click downloads for code, datasets, pre-trained models, etc.
  • Access on mobile, laptop, desktop

No Risk 100% Money Back Guarantee!

At the age of 58, learning ML, Computer Vision and Python all in parallel with no prior programming background was a steep learning curve and without PyImageSearch this could not have been possible. PyImageSearch brought it all nicely together.”

Sam RanadeIT Professional

Just wanted to thank you [Adrian] for the great work you are doing with PyImageSearch blog. The site has often been our main go-to place for solving Computer Vision problems for image and video analysis. I particularly appreciate the code samples you provide which are easy to understand.”

Dattaraj RaoChief Architect at GE

Enjoy a 100% money back guarantee.

After taking this curriculum, if you haven't learned any of the aforementioned courses, then we don't want your money. That's why we offer a 100% Money-Back Guarantee. Simply send us an email and ask for a refund- up to 30 days after your purchase. With all the copies we've sold, we can count the number of refunds on the one hand. Our readers are satisfied, and we're sure you will be too. For subscription products, please cancel before your renewal date. You can cancel at any time, so refunds will not be processed for renewals. Reach out to our team if you are considering canceling, as we'll be happy to generate a custom learning path or point you in the best direction for your current learning. For our complete Terms of Use, please visit: pyimagesearch.com/terms-of-use/

Questions?

Why this book?

OCR with OpenCV, Tesseract, and Python is the most in-depth, comprehensive, and hands-on guide to learning Optical Character Recognition with OpenCV and Tesseract. You cannot find any other book or course online that includes this level of intuitive explanations and thoroughly documented code.

What bundle should I buy?

Each bundle builds on top of the others and includes all content from lower volumes. You should choose a bundle based on (1) how in depth you want to study Optical Character Recognition, OpenCV, and Tesseract and (2) your particular budget. Use the "Here's the full breakdown of what you'll learn inside OCR with OpenCV, Tesseract, and Python" section above to help you decide which topics you want to learn, then pick a bundle based on your choices.

What happens after I purchase?

After you purchase your copy of OCR with OpenCV, Tesseract, and Python you will (1) receive an email receipt for your purchase and (2) you will be able to download your books, code, datasets, etc. immediately.

What is your money back guarantee policy?

I offer a 30 day Money Back Guarantee on all orders. If you haven't learned the fundamentals of Optical Character Recognition after reading my book, then I don't want your money. Simply send me an email and ask for a refund, up to 30 days after your purchase. With all the copies I've sold, I count the number of refunds on one hand. My readers are satisfied and I'm sure you will be too.

Are the hardcopy editions shipping?

Yep, the hardcopies are indeed shipping! The "OCR Expert" Bundle is the only bundle that includes a hardcopy edition. After you purchase, you will receive an email with a link to enter your shipping information. Once I have your shipping address I can get your hardcopy edition in the mail, normally within 48 hours.

Why are we using the Python programming language?

Python is an extremely easy language to learn and has huge number of powerful packages. Python is the best way to apply Optical Character Recognition to your own projects.

Does this book cover OCR with Tesseract?

Yes, this book covers Tesseract for Optical Character Recognition extensively. You'll start by learning the basics of the Tesseract OCR engine, including how to utilize the Tesseract binary from the command line. From there, you'll interface with Tesseract via the Python programming language, learn how to OCR images with Python and Tesseract, and even train and fine-tune Tesseract models on your own custom datasets!.

Will this book show me how to apply OCR with OpenCV?

The OpenCV library is a collection of functions, modules, and tools that allow you to perform image processing and computer vision. OpenCV includes functions that let you perform OCR, but the library is actually much more powerful than just OCR. Inside this book you'll not only learn how to perform OCR with OpenCV, but also use OpenCV's functions to help you obtain higher OCR accuracy.

What if I'm a beginner at OCR?

It's okay if you are brand new to Optical Character Recognition! This book makes no assumptions on your prior experience with OCR, computer vision, or deep learning. You'll still be able to follow along with this book, even if you are brand new to the world of OCR.

That said, a little bit of OpenCV experience goes a long way, so if you're new to OpenCV, I highly recommend that you also grab a copy of Practical Python and OpenCV so that you can learn the basics.

What if I'm already experienced in OCR?

This book isn't just for beginners — there are advanced concepts, algorithms, and techniques covered as well:

  • You'll learn how to train custom Keras/TensorFlow OCR models.
  • You'll build an Automatic License/Number Plate Recognition (ANPR) system.
  • You'll learn how to apply OCR to real-time video streams using GPUs for inference.
  • You'll train and fine-tune Tesseract models on your own custom OCR datasets.
  • And you'll learn how to use OCR APIs in the cloud, including Amazon Rekognition, Microsoft Cognitive Services, and Google Vision.

Best of all, the algorithms, walkthroughs, and code can be directly applied to your current job and research.

Do I need any programming experience before reading this book?

This book assumes you have some prior programming experience (e.g. you know what a variable function, loop, etc. are). You should have more skills than a beginner but certainly not an intermediate or advanced developer. As long as you understand basic programming logic-flow, you'll be successful in reading (and understanding) the contents of this book.

Do I need to know OpenCV?

You do not need to know the OpenCV library to be successful when going through this book. We only use OpenCV to facilitate basic image processing operations such as loading an image from disk, displaying it to our screen, along with some basic image processing routines.

That said, a little bit of OpenCV experience goes a long way, so if you're new to OpenCV, I highly recommend that you also grab a copy of Practical Python and OpenCV so that you can learn the basics.

Do I need to know Deep Learning, Keras, TensorFlow, etc.?

The "Intro to OCR" Bundle does not require any knowledge over deep learning. The "OCR Practitioner" Bundle and "OCR Expert" Bundle require a practitioner's knowledge over deep learning, meaning that you understand the basic idea of how a model is trained. If you're new to deep learning or want to level up your skills, make sure you grab a copy of the Deep Learning for Computer Vision with Python book — you can work through this OCR book and the deep learning book in tandem.

Can I upgrade from the lower tier bundle to a higher one? How does the upgrade process work?

Yes, you can always upgrade your bundle to a higher one. For example, you could purchase the "Intro to OCR" Bundle and then upgrade to the "OCR Practitioner" Bundle or "OCR Expert" Bundle at a later date.

The cost to upgrade would simply be the price difference between your current bundle and the bundle you wanted to upgrade to (you would not need to "repurchase" the content you already own). To upgrade your bundle just send me an email and I can get you the upgrade link.

I'm just so busy right now...

Everyone has the same amount of time in a day — we all have 24 hours to work, spend time with our families, sleep, and have fun. If you're interested in studying Optical Character Recognition, I challenge you to make it your goal. Take the time to invest in yourself and your OCR knowledge by grabbing a copy of OCR with OpenCV, Tesseract, and Python.

Ask yourself, how much time are you wasting because:

  • You lack the fundamentals of OpenCV, Computer Vision, and Deep Learning.
  • You don’t understand what knobs and dials to tune to achieve high accuracy results.
  • Your scripts error out, leaving you confused on how to proceed.

OCR with OpenCV, Tesseract, and Python solves these problems so you can stop wasting your time and money following paths that only lead to failure — let me guide you to success!

Where can I learn more about you?

I have authored over 400+ blog posts about computer vision, OpenCV, and deep learning over at PyImageSearch.com. Check out the posts to get a feel for my teaching and writing style (not to mention the quality and depth of the tutorials). I would also highly suggest that you sign up for the (free) Table of Contents and sample chapters I am offering using the form at the bottom-right corner of this page.

I have another question.

If you have any other questions, please send me a message, and I'll get back to you ASAP.