EasyOCR | use OCR with 80+ supported languages | Computer Vision library

 by   JaidedAI Python Version: v1.7.0 License: Apache-2.0

kandi X-RAY | EasyOCR Summary

kandi X-RAY | EasyOCR Summary

EasyOCR is a Python library typically used in Artificial Intelligence, Computer Vision, Deep Learning applications. EasyOCR has no bugs, it has no vulnerabilities, it has build file available, it has a Permissive License and it has medium support. You can install using 'pip install EasyOCR' or download it from GitHub, PyPI.

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
Support
    Quality
      Security
        License
          Reuse

            kandi-support Support

              EasyOCR has a medium active ecosystem.
              It has 18347 star(s) with 2611 fork(s). There are 289 watchers for this library.
              There were 1 major release(s) in the last 12 months.
              There are 229 open issues and 569 have been closed. On average issues are closed in 124 days. There are 14 open pull requests and 0 closed requests.
              It has a neutral sentiment in the developer community.
              The latest version of EasyOCR is v1.7.0

            kandi-Quality Quality

              EasyOCR has 0 bugs and 0 code smells.

            kandi-Security Security

              EasyOCR has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.
              EasyOCR code analysis shows 0 unresolved vulnerabilities.
              There are 0 security hotspots that need review.

            kandi-License License

              EasyOCR is licensed under the Apache-2.0 License. This license is Permissive.
              Permissive licenses have the least restrictions, and you can use them in most projects.

            kandi-Reuse Reuse

              EasyOCR releases are available to install and integrate.
              Deployable package is available in PyPI.
              Build file is available. You can build the component from source.
              Installation instructions, examples and code snippets are available.
              EasyOCR saves you 774 person hours of effort in developing the same functionality from scratch.
              It has 2291 lines of code, 97 functions and 16 files.
              It has high code complexity. Code complexity directly impacts maintainability of the code.

            Top functions reviewed by kandi - BETA

            kandi has reviewed EasyOCR and discovered the below as its top functions. This is intended to give you an instant insight into EasyOCR implemented functionality, and help decide if they suit your requirements.
            • Train the supervised model
            • Evaluate the image
            • Adjust learning rate based on gamma
            • Get load parameter
            • Create a custom dataset
            • Recognize the image
            • Given a list of boxes and a list of boxes
            • Get a paragraph from raw results
            • Get text from given image
            • Train the model
            • Generate a hierarchical dataset
            • Add two NumPy arrays together
            • Returns balanced batch of images
            • Reads text language language
            • Group a list of polygons into a text box
            • Performs a batched read on the given image
            • Recognize an image
            • Saves the output of each image
            • Compute the loss of the image
            • Convolutional transformation
            • Make a confidence score for the given index
            • Get a single text image from an image
            • Define concatenation
            • Create a DBNet from a trained model
            • Generate a list of images given a list of boxes
            • Parse command line arguments
            • Evaluate an image
            • Group a list of polygons
            • Export a detector
            • Returns a list of text boxes contained in the given image
            • Wrapper for inference
            • Get a paragraph from raw data
            Get all kandi verified functions for this library.

            EasyOCR Key Features

            No Key Features are available at this moment for EasyOCR.

            EasyOCR Examples and Code Snippets

            easyocr_ros,Setup,Workspace build
            Pythondot img1Lines of Code : 28dot img1License : Permissive (BSD-2-Clause)
            copy iconCopy
            pip3 install --user opencv-python
            source /opt/ros/kinetic/setup.bash
            mkdir -p ~/easyocr_ws/src
            cd ~/easyocr_ws/src
            git clone https://github.com/knorth55/easyocr_ros.git
            wstool init
            wstool merge easyocr_ros/fc.rosinstall
            wstool merge easyocr_ros/fc.ro  
            copy iconCopy
            // This is a comment. The bot will ignore this line.
            # This is also a comment.
            
            Turn 1:
                // On Turn 1, the following commands will be executed in order:
                // 6th Summon is invoked, character 1 uses Skill 2 and then Skill 4,
                // and finally ch  
            Architecture
            Pythondot img3Lines of Code : 15dot img3License : Permissive (MIT)
            copy iconCopy
            {
              "file_index_to_read": 1,
              "images": {
                "1": "true-soule.jpg",
                "2": "Eskillstuna.jpg",
                "3": "mistitles.jpg",
                "4": "UNLABELED_1.jpg",
                "5": "coochampion.jpg",
                "6": "UNLABELED_2.jpg",
                "7": "UNLABELED_3.jpg",
                "8": "enno  

            Community Discussions

            QUESTION

            easyocr installation error when install pillow
            Asked 2022-Apr-03 at 14:42

            I'm trying to install the easyocr library, but every time it comes time to install the Pillow library it gives an error.

            I've already tried to install pillow alone and install pytorch first, but it keeps giving the same error, if anyone can help me, I'd really appreciate it.

            Here's the error below:

            ...

            ANSWER

            Answered 2022-Apr-03 at 14:42

            I think that i ommit the line of error, but seeing on others foruns the error was caused because i was using the version 3.10 of python when the library Pillow, that was causing the installation error, is only supported for 3.9.12 of olders versions, so to resolve the problem we have to uninstall the actual python version and install the correct python version or create a virtual enviroment with the correct python version (the venv is a hint mine).

            Thanks for everyones help and i hope that help others people with similary problem.

            Source https://stackoverflow.com/questions/71700531

            QUESTION

            Unknown OpenCV exception while using EasyOcr
            Asked 2022-Feb-22 at 09:04

            Code:

            ...

            ANSWER

            Answered 2022-Jan-09 at 10:19

            The new version of OpenCV has some issues. Uninstall the newer version of OpenCV and install the older one using:

            Source https://stackoverflow.com/questions/70573780

            QUESTION

            How to read text from an image and save it to a text file
            Asked 2022-Feb-07 at 13:55

            I used

            ...

            ANSWER

            Answered 2022-Jan-07 at 05:50

            QUESTION

            I can't read long distance text with pytesseract
            Asked 2022-Jan-31 at 17:02

            I have this image and I want to read the text on it but pytesseract returns blank

            ...

            ANSWER

            Answered 2022-Jan-31 at 10:33

            I was able successfully to read this image with tesseract by doing the following:

            • cropping out the pink border
            • reducing to grayscale (binarising)
            • running tesseract with --psm 8 (see this question )

            I don't know if the cropping is necessary, but I couldn't get any output at all with any page segregation mode before binarising.

            I did the processing manually here, but you will likely want to automate it. A good trick for setting thresholds is to look at the standard deviation of the image in question and use that to scale your thresholds, rather than picking some absolute value and having it fail on you.

            Here's the image I got working:

            And the run:

            Source https://stackoverflow.com/questions/70923335

            QUESTION

            Working with TIFF in Python using EasyOCR
            Asked 2022-Jan-31 at 12:01

            I use a Python Module EasyOCR for extracting text from image. This Method works for PNG Format but in TIFF Situation give me a error

            Code look like this:

            ...

            ANSWER

            Answered 2022-Jan-31 at 12:01

            You are not reading the image. Please use opencv to read the image. Ensure that the image is in the current directory or provide the absolute path of the image.

            Source https://stackoverflow.com/questions/70925304

            QUESTION

            Trying to read these plates using OCR but they are blurry. Where do I start?
            Asked 2022-Jan-10 at 13:28

            Hi I am a student doing research in my university. This is my first time using computer vision (openCV) and I am fairly new to image preprocessing. I have these images of License Plates and I would like to use easyOCR/pytesseract to read the plates. Currently all I have done is convert the image to grayscale, rotate it by a few degrees, but the reading results are very inconsistent. How do I improve that?

            I have tried using kernels to sharpen the images but they seem to be fairly inconsistent too.

            Here are some images I have to give you a general idea of what the images are like:

            ...

            ANSWER

            Answered 2022-Jan-10 at 12:42

            I would start with image enhancement. It's hard to tell what exactly is applicable but here are some possible manuevers:

            1. As usual recognition algorithms are not invariant to rotation. And every image seems to be geometically distorted similarly. You can try to normalize the geometry by warpPerspective function from Opencv with appropriate transformation matrix. Rotation is a subset of all possible transformations covered by perspective transform.
            2. You can try to use advanced deblurring techniques like wiener filter or deeplearning. It seems like point spread function is different from image to image that complecates the recovery.
            3. There is some periodic signal in your images (vertical blue-white-blue stripes). That can possibly can be enhanced by doing FFT -> removing components of the specific wavelength -> iFFT.

            Anyway looking on your images, I am not sure if it will be easy to achieve the desired result without diving into the OCR pipeline.

            Source https://stackoverflow.com/questions/70651951

            QUESTION

            EasyOCR Segmentation fault (core dumped)
            Asked 2022-Jan-03 at 20:48

            I got this issue

            ...

            ANSWER

            Answered 2022-Jan-03 at 14:37

            Solved downgrading to the nov 2021 version of opencv

            Source https://stackoverflow.com/questions/70567344

            QUESTION

            Loop, extract and save a list within list as a dataframe
            Asked 2021-Nov-20 at 04:25

            pretty new to Python in general, but hopefully my question will make sense.

            I have a list that contains lists with irregular lengths, and I am trying to cover the list into a data frame structure so I can save it as a CSV. I want to also make sure i have a way of combining the lists that are within their family lists by adding IDs so i can combine them later.

            An overview: i ran easyocr on several images which extract texts from images, so i want the imageID so i can find the text and relate it back to the image it was nested within.

            An example of data looks like this:

            ...

            ANSWER

            Answered 2021-Nov-20 at 04:25

            First you could use print() to see what you have in variables - it helps to see what is needed in code.

            Using for-loops (without range()) you get lists, not indexes, so results_[i][j][0] is wrong.

            If you have empty list then you should skip them - ie. if i: .... to run code only when i is not empty.

            Source https://stackoverflow.com/questions/70042088

            QUESTION

            GPU for REST API on AWS?
            Asked 2021-Nov-18 at 01:19

            I have an EasyOCR model that I have trained with personnal data and I need to deploy it and make it available with an API REST. My project is on Github.

            Problem: I have saw that we can't use GPU on AWS LAMBDA so how can we deploy a REST API that can use GPU on AWS ?

            (EasyOCR is really slow when we don't use GPU with CUDA)

            ...

            ANSWER

            Answered 2021-Nov-17 at 13:52

            You can have a look at AWS EC2 Instances with GPU Support. There are 3 or 4 classes available (p3, g3, p4 and g4). They should be sufficient for your usecase. Make sure to use the AWS Deep Learning AMI, to get out of the Box NVIDIA Drivers and CUDA Support.

            Edit: Ref- https://docs.aws.amazon.com/dlami/latest/devguide/gpu.html

            Source https://stackoverflow.com/questions/70005344

            QUESTION

            Save result of easyocr in veriable and print it with all data at same line
            Asked 2021-Oct-20 at 16:06

            I am using easyocr to detect mrz of passport:

            .py code:

            ...

            ANSWER

            Answered 2021-Oct-20 at 16:06

            Use this code to achive the result in single line

            Source https://stackoverflow.com/questions/69649297

            Community Discussions, Code Snippets contain sources that include Stack Exchange Network

            Vulnerabilities

            No vulnerabilities reported

            Install EasyOCR

            Install using pip for stable release,. For latest development release,. Note 1: for Windows, please install torch and torchvision first by following the official instruction here https://pytorch.org. On pytorch website, be sure to select the right CUDA version you have. If you intend to run on CPU mode only, select CUDA = None.

            Support

            Let's advance humanity together by making AI available to everyone!.
            Find more information at:

            Find, review, and download reusable Libraries, Code Snippets, Cloud APIs from over 650 million Knowledge Items

            Find more libraries