I WANT TO TRAIN CUSTOM OCR . CAN I GET HELP REGARDING THIS. I PREFER TO USE LOCAL SYSTEM FOR TRAINING.

Hi @"dhunjoshi"#p396 , So there are two parts to our OCR system: 1. Text detection. We used EAST, as it allows text to be oriented at odd angles/etc. I am pinging our engineer on this on if he did retraining. Anyway, [here](https://github.com/argman/EAST) is one example of retraining it in TensorFlow, which then should be compatible with our platform, as OpenVINO supports TensorFlow. 2. OCR. This takes the region found from the text detection, and runs the actual OCR on it. For this network, we use the OCR model from Intel: [https://docs.openvinotoolkit.org/2019_R1/_text_recognition_0012_description_text_recognition_0012.html](https://docs.openvinotoolkit.org/2019_R1/_text_recognition_0012_description_text_recognition_0012.html) I do not at this time know if Intel gives a reference on how to retrain that. For some of their networks, they do give retraining. Looking quickly. Not immediately seeing it. From the notes on it, "VGG16-like backbone and bidirectional LSTM encoder-decoder". So likely any network that is similar to this could be used instead, as long as it is on a similar backbone (or one of [these](https://docs.luxonis.com/en/latest/pages/faq/#what-network-backbones-are-supported-on-depthai)), or uses neural operations supported by OpenVINO for the VPU (OAK-D is the VPU in this context), see [here](https://docs.luxonis.com/en/latest/pages/faq/#if-i-train-my-own-network-which-neural-operations-are-supported-by-depthai).

[URL=https://i.imgur.com/Lx90Rdb.jpg][IMG]https://i.imgur.com/Lx90Rdb.jpg[/IMG][/URL] Can OCR will work in attached image. i have to retrain with new images?

i tried [EAST](https://github.com/argman/EAST) and result as shown. EAST was suggested by @"Brandon"#p405 [URL=https://i.imgur.com/e1u9Blp.png][IMG]https://i.imgur.com/e1u9Blp.png[/IMG][/URL] By the way @"Brandon"#p405 is there any OCR examples ?

Thanks @"demoacct01"#92 . To your question @"demoacct01"#p430 , we do have an in-progress example but it is crashing on some of the warp/re-shape when taking the EAST bounding boxes and feeding them through WARP/deWARP on the Myriad X. We just fixed the crash (got the message that it was fixed just now, actually). So the last step is the OCR output decoding. But the whole pipeline is actually now running. Here's the Github issue: https://github.com/luxonis/depthai/issues/124 And here's the WIP PR for the whole demo flow: https://github.com/luxonis/depthai-experiments/pull/26 We will likely update the PR shortly with the whole flow working, excepting the host-side decoding of the OCR. We're discussing internally the timing on that. Thoughts? Thanks again, Brandon

Hi @"Brandon"#p437, git checkout the branch gen2_ocr and gave it a test run. It runs slow ... :-( I tried to move the paper (with text on it) I was holding in front of the camera. Was like it never went past the first few frame or something. The output screen just freeze with the bounding box on some texts on the paper I was holding. When I did pip install -r requirements.txt, I got this error. ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. depthai-gui 1.0.7 requires depthai==0.0.2.1+d436ec6b629c09b92c58d869e80aac52367a3aa9, but you have depthai 0.0.2.1+9430403bc960388da512c6c8936c27f8d1fa8b2d which is incompatible. Could this cause the "freeze" ?

Hi @"demoacct01"#p445 , Sorry about the trouble. The OCR is likely the slow part. The detection itself is a lot faster: https://youtu.be/sEWFQP9kdTM This example is still a work in progress. Luxonis-Alex is finishing it up now. We actually lost the engineer who was working on this (another one to Amazon!) so it got delayed as a result. This PR is what will allow for the flow to be on DepthAI/OAK directly: https://github.com/luxonis/depthai-shared/pull/16 It's what took a lot of time/debugging here. So now that this is out of the way, hopefully we will have the whole flow working well soon. Thanks and sorry about the delay. -Brandon

No problem @"Brandon"#p446 ... I am working on some OCR project at the moment. So was eager to see a working sample from your end. I hope I didn't misunderstood your response. Are you trying to say that if I "git checkout gen2_ocr" and run main.py I should see a speedup improvement? I tested it and it was slightly faster but not as fast as what was shown in the youtube. I realised the youtube was a last year video. So I am a bit confused now whether the fix is completed or not.

Hi @"demoacct01"#92 , The demo in the Youtube video is only running the text detection (bounding boxes) network, whereas the Gen2 one https://github.com/luxonis/depthai-experiments/pull/26 is running both text detection and text recognition, passing each cropped bounding box to the recognition model. So depending on the number of detections, it may be slower. I'm working now on this Gen2 example, moving the rotated cropping from host (OpenCV warp) to run on device (with the recent rotated cropping/rescale added in ImageManip node), and will add a decoder for the recognition model outputs as well: https://docs.openvinotoolkit.org/2020.1/_models_intel_text_recognition_0012_description_text_recognition_0012.html

Hello! I tried to use gen2-ocr project from GitHub https://github.com/luxonis/depthai-experiments/tree/master/gen2-ocr and got several errors. Using depthai version from requirements caused a warning "DeprecationWarning: setCamId() is deprecated, use setBoardSocket() instead." Switching between depthai versions made other warnings. There are some of them: - Creating depthai.Pipeline() has no Constructor - nn doesn't have function nn.passthrough (line 25) - silent crashes while compiling I use OAK-D with Windows-10. What am I doing wrong?

Hi @"asidsunrise"#p583 , Sorry about the delay (been inundated with Brexit/pandemic shipping/logistics problems in Europe). This is quite odd. So just to confirm, when trying out that example, you ran: `python -m pip install -r requirements.txt` And then: `python3 main.py` And it is still giving those errors? If so, is the installation of requirements throwing errors? As from what you shared, it is seeming that the API being used is not compatible with the example. Thoughts? Thanks, Brandon

CUSTOM OCR TRAINING

Brandon

I can't seem to replicate the version error here. For me it is just running:

So here are the commands I did to get it to run:

cd ~/depthai-experiments/gen2-ocr
git checkout master
git pull
python3 -m pip install -r requirements.txt
python3 main.py

Could you try doing these in sequence? And actually, to make sure that the other version of depthai installed, could you do this sequence:

python3 -m pip uninstall depthai
cd ~/depthai-experiments/gen2-ocr
git checkout master
git pull
python3 -m pip install -r requirements.txt
python3 main.py

I just repeated that whole sequence to be sure, and it works. I'm wondering if something has locked an incorrect version of depthai on the system. If this doesn't work, would it be OK to do a TeamViewer session to debug?

If so, please shoot us an email at support@luxonis.com to coordinate the session.

Thanks - and sorry about the trouble.
-Brandon

asidsunrise

I used all commands you provided in last message and it didn't work for me on both my Windows PC's. I'll try to run it on my Macbok Air and connect via email. Thanks for your support!

Brandon

asidsunrise Thanks. Very strange. Perhaps our CI/CD didn't properly build for Windows for this example. Will be curious to find out.

asidsunrise

Brandon Well, I tried to run it on my Macbook and got the same error. The re-installing depthai version didn't help. If it could help to find a problem it will be OK to use TeamViewer, but I'm not sure it is possible in the next 2-3 days.

Will

Hi, same issue on my iMac under Catalina (macOS 10.15.7)...

Brandon

Thanks and sorry about the delay, both. So could you please send an email to support@luxonis.com to facilitate a teamviewer to see what is happening here?

I'll try this again now on my iMac as well.

Thanks and sorry again about the delay (so far behind on shipping issues in Europe),
Brandon

Brandon

Hi @Will ,

So I was able to replicate this with the version that was checked out on my iMac. Steps:

cd ~/depthai-experiments/gen2-ocr 
python3 -m pip install -r requirements.txt

Which produced:

Looking in indexes: https://pypi.org/simple, https://artifacts.luxonis.com/artifactory/luxonis-python-snapshot-local
Requirement already satisfied: numpy==1.19.5 in /Users/leeroy/Library/Python/3.9/lib/python/site-packages (from -r requirements.txt (line 1)) (1.19.5)
Requirement already satisfied: opencv-python==4.5.1.48 in /Users/leeroy/Library/Python/3.9/lib/python/site-packages (from -r requirements.txt (line 2)) (4.5.1.48)
Collecting depthai==0.0.2.1+e88c98c8a7681dd16cd754a832df1165380ac305
  Using cached https://artifacts.luxonis.com/artifactory/luxonis-python-snapshot-local/depthai/depthai-0.0.2.1%2Be88c98c8a7681dd16cd754a832df1165380ac305-cp39-cp39-macosx_10_9_x86_64.whl (4.3 MB)
Installing collected packages: depthai
  Attempting uninstall: depthai
    Found existing installation: depthai 0.4.1.1
    Uninstalling depthai-0.4.1.1:
      Successfully uninstalled depthai-0.4.1.1
Successfully installed depthai-0.0.2.1+e88c98c8a7681dd16cd754a832df1165380ac305

And then I ran:

python3 main.py

Which resulted in:

/Users/leeroy/depthai-experiments/gen2-ocr/main.py:15: DeprecationWarning: setCamId() is deprecated, use setBoardSocket() instead.
  colorCam.setCamId(0)
libc++abi.dylib: terminating with uncaught exception of type std::runtime_error: XLink write error, error message: X_LINK_ERROR
zsh: abort      python3 main.py

I am now updating the repo with git pull on the master branch to check if this improves it.

Brandon

Same error:

python3 main.py                           
/Users/leeroy/depthai-experiments/gen2-ocr/main.py:15: DeprecationWarning: setCamId() is deprecated, use setBoardSocket() instead.
  colorCam.setCamId(0)
libc++abi.dylib: terminating with uncaught exception of type std::runtime_error: XLink write error, error message: X_LINK_ERROR
zsh: abort      python3 main.py

So I am checking with the team now. The fact that I can reproduce this is good as I think we will now be able to fix it quickly.

Thanks and sorry about the issues here.

-Brandon

king

Dear Brandon:

we are using OAK-1 with EAST with text_recognition_0012 as demo video shown:

and source code below :

So far we are satisfy the

we have a request is we want to add ROI function and combine with source code， then it could judge OCR ok or ng only inside of ROI , of course we can adjust ROI by execute CMD .
Please assist us to realize the above function ,

all the best~~

erik

Hello king , your google drive video/source code can't be accessed (it says that we have to request the access). Regarding the ROI, from my understanding you would like to specify the ROI and run text detection/OCR in that region?

king

Dear erik:

Yes~_you are right
as attached picture content is using text_recognition_0012 results that you couldn't seen by google video:

As we know EAST OCR is 1080p resolution and getting all of text of whole paper.
but our customer want only setting their own ROI and could adjust size of ROI ,finally running OCR inside ROI.

for example like COGNEX OCR (shown red ROI):

We have three ideas:

We would like to use IMREAD_UNCHANGE to cutoff picture ,and imshow
Change the aspect ratio (stretch the image)
Apply letterboxing to the image,
as below:
https://docs.luxonis.com/projects/api/en/latest/tutorials/maximize_fov/
SpatialLocationCalculator
to create ROI and combine with text_recognition
https://docs.luxonis.com/projects/api/en/latest/components/nodes/spatial_location_calculator/

Please assist us which method could be match our goal??

all the best~~

erik

Hello king , let me ask our ML engineer to suggest the best approach for this issue.
Thanks, Erik

Matija

Hey @king , so if I understand correctly, you do not need actual test detection, only test recognition? And you want to set a custom ROI?

If that is so, you could use our ImageManip node, where you can set the ROI to some rectangle by providing the points for ROI and then resize the image so that it has correct shape for input to recognition network. Then you would have to link this ImageManip node to a Neural Network node that performs text recognition as in OCR example.

So you could try editing this part of the code to use custom defined ROI instead of ROI from detections from the whole image. Which means you could skip the first NN node, but keep the rest the same.

Does this make sense?

king

Dear Matija:

Thanks for your suggestion of custom ROI~ our target is not only text recognition but also ROI settings and running inside of ROI.

We will follow your ImageManip ndoe and and compile it with text recognition first . maybe there are good results for us.

all the best~~

king

Dear Matija and erik:

We could create ROI of 256x256 pixels due to east_text_detection_256x256 , but the results will be Influenced in black OCR and it cause incorrect results whc sometimes as below picture red frame :

could you please assist us how to solve the issue ??

all the best~~

Matija

Hey, you could manually increase these two lines, so a larger are is cropped: https://github.com/luxonis/depthai-experiments/blob/master/gen2-ocr/main.py#L241-L242.

I found out that rotate crops are slightly incorrect, but should be fixed with the ImageManip refactor which will be released soon. For now you can try increasing the width and height manually in the above lines, like:

rr.size.width  = int(rotated_rect[1][0] * 1.1)
rr.size.height = int(rotated_rect[1][1] * 1.1)

This will increase width and height for 10%.

Best,
Matija

king

Dear LUXonis partners :
We have OCR case as google drive as below and picture:

We want to check each OCR SET/CAN/RES , but results is still fail due to influence by pattern of + and -
we try every methods as you suggestion before (include rr.size.widthrr.size.height )but`still can't solve our customer needed.
This case our customer have 10pcs OAK-1 request, if we can solve the issue. maybe create a background pictures with any color code into gen2-OCR and combine with modifying EAST. but we don't know how to modify it yet~~
If you have a good solution for our case we can discuss more detail cooperation methods~

all the beat~~

Matija

king If you are limited to a set of these 3 words only, you could just filter them out with some distance metric or just check if the word is contained in the result. SET is in SSET, so you can know that SSET likely refers to SET, similarly CAN is in ICAN and RES in RESE.

If you are looking at other words as well, it's going to be hard to eliminate this + sign. You could try decreasing the factor by which you increase the width.

With image refactor that we are working on, I think the rotated squares should be cropped out better, but don't hold my word for it. I'll report some results when I'll be able to test it out. Until then, I propose you use one of the two approaches I mentioned above.

Best,
Matija

king

Dear Matija:

Thanks for your support of ROI OCR upgrade in this case ,we sincere that's could solve in this case , also we would like to know how long we could get the upgrade results??

all the best~~

king

Dear all:

We have another issue is autofocus function about OAK-1 as Picture below:

the OAK-1 is fixed on WD=150mm and only focus on A123 text ,we import autofocus.py into gen2-ocr
we set A123 is ok condition and output OK pictures . it shows clear image with OK pictures but also shows blurry image with NG pictures sometimes , we try to modify parameter of autofocus.py and still shows blurry image, could you please assist us how to modify the parameter of autofocus.py and only shows clear image:

import depthai as dai
import cv2
# Screen adjust for "left" "right" "up" "down"
# Step size ('W','A','S','D' controls)
STEP_SIZE = 8

# Create pipeline
pipeline = dai.Pipeline()

# Define sources and outputs
camRgb = pipeline.create(dai.node.ColorCamera)
videoEncoder = pipeline.create(dai.node.VideoEncoder)
stillEncoder = pipeline.create(dai.node.VideoEncoder)

controlIn = pipeline.create(dai.node.XLinkIn)
configIn = pipeline.create(dai.node.XLinkIn)
videoMjpegOut = pipeline.create(dai.node.XLinkOut)
stillMjpegOut = pipeline.create(dai.node.XLinkOut)
previewOut = pipeline.create(dai.node.XLinkOut)

controlIn.setStreamName('control')
configIn.setStreamName('config')
videoMjpegOut.setStreamName('video')
stillMjpegOut.setStreamName('still')
previewOut.setStreamName('preview')

# Properties
camRgb.setVideoSize(640, 360)
camRgb.setPreviewSize(300, 300)
videoEncoder.setDefaultProfilePreset(camRgb.getFps(), dai.VideoEncoderProperties.Profile.MJPEG)
stillEncoder.setDefaultProfilePreset(1, dai.VideoEncoderProperties.Profile.MJPEG)

# Linking
camRgb.video.link(videoEncoder.input)
camRgb.still.link(stillEncoder.input)
camRgb.preview.link(previewOut.input)
controlIn.out.link(camRgb.inputControl)
configIn.out.link(camRgb.inputConfig)
videoEncoder.bitstream.link(videoMjpegOut.input)
stillEncoder.bitstream.link(stillMjpegOut.input)

# Connect to device and start pipeline
with dai.Device(pipeline) as device:

    # Get data queues
    controlQueue = device.getInputQueue('control')
    configQueue = device.getInputQueue('config')
    previewQueue = device.getOutputQueue('preview')
    videoQueue = device.getOutputQueue('video')
    stillQueue = device.getOutputQueue('still')

    # Max cropX & cropY
    maxCropX = (camRgb.getResolutionWidth() - camRgb.getVideoWidth()) / camRgb.getResolutionWidth()
    maxCropY = (camRgb.getResolutionHeight() - camRgb.getVideoHeight()) / camRgb.getResolutionHeight()

    # Default crop
    cropX = 0
    cropY = 0
    sendCamConfig = True



    while True:
        previewFrames = previewQueue.tryGetAll()
        for previewFrame in previewFrames:
            cv2.imshow('preview', previewFrame.getData().reshape(previewFrame.getHeight(), previewFrame.getWidth(), 3))

        videoFrames = videoQueue.tryGetAll()
        for videoFrame in videoFrames:
            # Decode JPEG
            frame = cv2.imdecode(videoFrame.getData(), cv2.IMREAD_UNCHANGED)
            # Display
            cv2.imshow('video', frame)

            # Send new cfg to camera
            if sendCamConfig:
                cfg = dai.ImageManipConfig()
                cfg.setCropRect(cropX, cropY, 0, 0)
                configQueue.send(cfg)
                print('Sending new crop - x: ', cropX, ' y: ', cropY)
                sendCamConfig = False


        # Update screen (1ms pooling rate)
        key = cv2.waitKey(1)
        if key == ord('q'):
            break

        elif key == ord('t'):
            print("Autofocus trigger (and disable continuous)")
            ctrl = dai.CameraControl()
            ctrl.setAutoFocusMode(dai.CameraControl.AutoFocusMode.AUTO)
            ctrl.setAutoFocusTrigger()
            controlQueue.send(ctrl)
        elif key in [ord('w'), ord('a'), ord('s'), ord('d')]:
            if key == ord('a'):
                cropX = cropX - (maxCropX / camRgb.getResolutionWidth()) * STEP_SIZE
                if cropX < 0: cropX = maxCropX
            elif key == ord('d'):
                cropX = cropX + (maxCropX / camRgb.getResolutionWidth()) * STEP_SIZE
                if cropX > maxCropX: cropX = 0
            elif key == ord('w'):
                cropY = cropY - (maxCropY / camRgb.getResolutionHeight()) * STEP_SIZE
                if cropY < 0: cropY = maxCropY
            elif key == ord('s'):
                cropY = cropY + (maxCropY / camRgb.getResolutionHeight()) * STEP_SIZE
                if cropY > maxCropY: cropY = 0
            sendCamConfig = True

all the best~~

erik

Hello king ,
If the object is always 150mm away from the camera, I would suggest manually specifying the lens position instead of having autofocus enabled. You can achieve that like this:

camRgb = pipeline.create(dai.node.ColorCamera)
cam.initialControl.setManualFocus(90)

You can change the value between 0 and 255. You can see what's the best value by going through all focus values with this example (pressing , and . will change lens position).

Thanks, Erik

« Previous Page Next Page »