Current Behavior:

The the wiki page APIExample, for the python example, the handle api is is run through the TessBaseAPIDelete funciton if the api failed to be initialized whereas for the C example below, this is not the case.

python:

rc = tesseract.TessBaseAPIInit3(api, TESSDATA_PREFIX, lang)
if (rc):
    te

Having a six character hex color as the current clipboard content makes the color preview for this hex color keep popping up every minute or so. This is very annoying and requires me to copy something different to make it stop appearing.

The issue is that with long correspondent and documents name that it gets confusing with many documents.
My Idea is to truncate the output and have the full name as tooltip. (maybe as title attribute)

From Issue #84, I did pod install, but facing following error:

ld: warning: directory not found for option '-F/Users/mahbub/Library/Developer/Xcode/DerivedData/NavigateMe-ehyamrhmeogwarbxhzbydagosybb/Build/Products/Debug-iphonesimulator/GPUImage'
ld: warning: directory not found for option '-F/Users/mahbub/Library/Developer/Xcode/DerivedData/NavigateMe-ehyamrhmeogwarbxhzbydagosybb/Build/P

cvNet = cv.dnn.readNetFromTensorflow('ctpn.pb', 'protobuf.pbtxt')
cv2.error: OpenCV(4.1.1) C:\projects\opencv-python\opencv\modules\dnn\src\tensorflow\tf_io.cpp:54: error: (-2:Unspecified error) FAILED: ReadProtoFromTextFile(param_file, param). Failed to parse GraphDef file: protobuf.pbtxt in function 'cv::dnn::ReadTFNetParamsFromTextFileOrDie'

Does anyone have any idea how I can solve this pr

Hello

I am trying to add a step to the wizard when uploading a new document where user can enter the name (label) manually.

I have added the step to the wizard and its working but the value of the label is still as the current situation.
(The label entered by user is not stored to the database)

Any guidance or help ?

我参考这个链接，yolov3-tiny.weights的这个模型用OpenCV的dnn是调用起来了的
https://github.com/spmallick/learnopencv/blob/master/ObjectDetection-YOLO/object_detection_yolo.cpp
但是直接替换模型路径为text.weights的输出不了文字区域坐标哦，反正前向传播是完成了的，net.forward(outs, getOutputsNames(net));就是没结果啊 不知道为啥。
还有请问下你的text.weights的直接输出不是文字外接矩吗？看你的代码的detector里面好像做了很多后处理啊，能稍微解释下整个流程吗？(yolov3的text.weights输出是什么，具体后面要做什么才能获得检测的文字的外接矩)

我看你的text_detect 有好多参

VECTOR_PAGE_DPI check does not consider whether there is printable text on the page when asking if we should scale up rasterizing resolution, causing text to be rendered at low resolution when using --force-ocr.

See for example ICC's version4pdf.pdf (text + 100 DPI images).

Hi,
There is a typo in readme - demo section (should be _ rather than -)
is:
python3 run_demo_server.py --checkpoint-path /tmp/east_icdar2015_resnet_v1_50_rbox/
and should be:
python3 run_demo_server.py --checkpoint_path /tmp/east_icdar2015_resnet_v1_50_rbox/

also i had to change:
/tmp/east_icdar2015_resnet_v1_50_rbox/
into:
tmp/east_icdar2015_resnet_v1_50_rbox/

Dear @bgshih, I get compilation errors when building the cpp part.

could you help me please in order to solve

WARNING:tensorflow:From /home/qgb/.local/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
/root/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:8: UserWarning: Update your `Co

I think we should add a paper which is named "Detecting Text in Natural Scenes with
Stroke Width Transform",although,it is very early,lots of classical papers mention it.
address:https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/201020CVPR20TextDetection.pdf

C:\Py3Conda\python.exe D:/python/opencv_test/lib/tesser.py
Traceback (most recent call last):
File "D:/python/opencv_test/lib/tesser.py", line 1, in
import tesserocr
ImportError: DLL load failed: Не найден указанный модуль.

Undefined symbols for architecture x86_64:
"_PyBuffer_Release", referenced from:
___pyx_pf_5utils_7cpu_nms_cpu_nms in cpu_nms-2726be.o
"_PyCFunction_NewEx", referenced from:
_initcpu_nms in cpu_nms-2726be.o
"_PyCFunction_Type", referenced from:
___pyx_pf_5utils_7cpu_nms_cpu_nms in cpu_nms-2726be.o
"_PyCode_New", referenced from:
_initcpu_nms in cpu_nms-2726b

I noticed that you used image height param format as the font size.
https://github.com/Belval/TextRecognitionDataGenerator/blob/33d8985521645280e102987e773bf1e424a045df/TextRecognitionDataGenerator/computer_text_generator.py#L14
In my test, image_font = ImageFont.truetype(font=font_size=500), no error was reported, but it was time consuming.
So I am confused, why set format, font_size

I noticed that we're forcing to(device) in GridGenerator. The reason for this may be we are using numpy (CPU) tensors in Lo

建议精简版抛弃exe，直接打包成压缩文件。再带一个批处理，利用已经安装好的Java环境直接命令行运行。

CXX src/caffe/layers/DenseBlock_layer.cpp
CXX src/caffe/layers/embed_layer.cpp
src/caffe/layers/data_layer.cpp: In member function ‘virtual void caffe::DataLayer::DataLayerSetUp(const std::vector<caffe::Blob>&, const std::vector<caffe::Blob>&)’:
src/caffe/layers/data_layer.cpp:54:32: error: ### ‘class caffe::Datum’ has no member named ‘label_size’

how to solve the