https://github.com/alixunxing/caffe_ocr

主流ocr算法研究实验性的项目，目前实现了CNN+BLSTM+CTC架构

https://github.com/alixunxing/caffe_ocr

Repository

主流ocr算法研究实验性的项目，目前实现了CNN+BLSTM+CTC架构

https://github.com/alixunxing/caffe_ocr/blob/master/

# 
caffe_ocrocrCNN+BLSTM+CTClstmwarp-ctcmulti-labelinceptionrestnetdensenetwindowslinuxcaffe
## caffe
 1. data layermulti-label

 2. lstmjunhyukohlstmlstm_layer_Junhyuk.cpp/cushape(TxN)xHTxNxHctc

 3. WarpCTCLossLayersequence indicatorsCNNsequence indicator layer

 4. densenetReshapebug

 5. transpose_layerreverse_layerCNN feature maplstmshape

## 
  1. opencv,boost,cuda,3rdpartydebuglib:http://pan.baidu.com/s/1nvIFojJ

  2. caffe-vsprojvs2015tools_bincaffe.exe

  3. dllhttp://pan.baidu.com/s/1boOiscJ

## 
  1. caffe-vsproj/libClassification,examples\cpp_classification

  2. caffe-vsproj/ocr_testocrocrexamples/ocr/lexicon.txt

## 
1. 

 1[VGG Synthetic Word Dataset](http://www.robots.ox.ac.uk/~vgg/data/text/)

 2https://pan.baidu.com/s/1dFda6R3 

  ![](https://github.com/senlinuc/caffe_ocr/blob/master/examples/ocr/20436312_1683447152.jpg)  ![](https://github.com/senlinuc/caffe_ocr/blob/master/examples/ocr/20436328_800384098.jpg)
  ![](https://github.com/senlinuc/caffe_ocr/blob/master/examples/ocr/20436765_2556130357.jpg)  ![](https://github.com/senlinuc/caffe_ocr/blob/master/examples/ocr/20437703_937698549.jpg)
  ![](https://github.com/senlinuc/caffe_ocr/blob/master/examples/ocr/20438234_4066860539.jpg)  ![](https://github.com/senlinuc/caffe_ocr/blob/master/examples/ocr/20440484_2127180630.jpg)
>>*  +

>>*  5990

>>*  10

>>*  280x32

>>*  3609:16


2. 

  examples/ocr

3. 


*  VGG Synthetic Word Dataset:

|  | predict-CPU | predict-GPU | -no lexicon | -lexicon-minctcloss |  |
| ---------- | -----------| ---------- | ---------- | -----------| -----------|
| crnn | 67.13ms | 10.28ms | 0.8435 | 0.9163 | 32MB |
| inception-bn-res-blstm | 41.62ms | 8.68ms | 0.7353 | 0.8609 | 15MB |
| densenet-res-blstm	| N/A	| 6.07ms	| 0.7548	| 0.893 | 11MB| 

* :

|  | predict-CPU | predict-GPU |  |  |
| ---------- | -----------| ---------- | -----------| -----------|
| inception-bn-res-blstm | 65.4ms | 11.2ms | 0.92 | 26.9MB |
| resnet-res-blstm	| 64ms	| 10.75ms	| 0.91	| 23.2MB| 
| densenet-res-blstm	| N/A	| 7.73ms	| 0.965	| 22.9MB| 
| densenet-no-blstm	| N/A	| 2.4ms	| 0.97	| 5.6MB| 
|densenet-sum-blstm-full-res-blstm|N/A|7.83ms|0.9805|15.5MB|
|densenet-no-blstm-vertical-feature|N/A|3.05ms|0.9816|9.6MB|

http://pan.baidu.com/s/1i5d5zdN
>

>>*  CPUXeon E3 1230, GPU1080TI

>>*  densenetmemory-efficientCPUblas

>>*  res-blstmblstmno-blstmlstmCNNCTC

>>*  ,,"-no lexicon""-lexicon-minctcloss"Edit Distance <=2ctcloss

>>*  predict-CPU/GPUpredict-CPUopenblasMKLopenblas280x32100x32
>>*  densenet-sum-blstm-full-res-blstmdensenet-res-blstm1lstmblstmconcatsum2blstmCNNChannelblstm
>>*  densenet-no-blstm-vertical-featuredensenet-no-blstm1x4poolingCNNfeature maps4reshape BxCxHxW --> Bx(CxH)x1xW1feature maps, CNN feature
4. tricks

 1 blstm0.94-->0.965BLSTM0.9805

 2 CNNBLSTM

5. 

 1blstmCNN+CTCdensenet-no-blstm

   aCNNb)lstm

6. 

 111llCNN

## TODO
 1. : (https://yq.aliyun.com/articles/109555?t=t1)

 2. traintest lossAttention,STN,loss

## 
  1. crnn(https://arxiv.org/abs/1507.05717)
 
  2. multi-label(http://blog.csdn.net/hubin232/article/details/50960201)

  3. junhyukohlstmhttps://github.com/junhyukoh/caffe-lstm

  4. caffe-warp-ctc(https://github.com/BVLC/caffe/pull/4681)

  5. memory-efficient densenet(https://github.com/Tongcheng/caffe/)

  6. http://www.sogou.com/labs/resource/cs.php

 

Owner

GitHub Events