tesseract

I am working information reading from Identity Card information using Tesseract Library.I got Confidence score of each word or each line. Box[0]: x=13, y=12, w=1134, h=57, confidence: 40, text: REPUYBLIQUE FRANCAISE Box[1]: x=21, y=75, w=1119, h=50, confidence: 42, text: 7 NN99 3W F 59W Box[2]: x=17, y=137, w=539, h=52, confidence: 30, text: V7 7 D5 NOM1BOHEL Box[3]: x=6, y=189, w=954, h=46, confidence: 0, text: Box[4]: x=12, y=239, w=1016, h=34, confidence: 40, text: 5 Q HV2 H CHRISTIANL NICBLE HBNIOIJE Box[5]: x=21, y=310, w=975, h=53, confidence: 67, text: 2 E 20 06 1329 Box[6]: x=28, y=372

I'm using Ubuntu 14.04 and I'm trying to compile this code, but I get these errors no matter what, I believe it has something to do with including the OpenCV library, but I'm not sure. Could anyone help me out? Errors: main.cc:66:37: error: ‘CV_RETR_EXTERNAL’ was not declared in this scope main.cc:66:55: error: ‘CV_CHAIN_APPROX_NONE’ was not declared in this scope main.cc:81:28: error: ‘CV_BGR2GRAY’ was not declared in this scope The Code(sorry for the formatting, I just can't get this right): #include <opencv2/imgproc.hpp> #include <opencv2/highgui/highgui.hpp> #include <tesseract/baseapi.h>

I need to identify handwritten text (icr). No need to understand arbitrary text - I am able to instruct my users to write very clearly, with separate letters and etc. However still there will be some amount of difference between any training set and the real letters. I am hoping to train tesseract for this purpose. Has anyone tried this? Any hope in this path? You must have fonts similar to those handwriting letters. You may create them with any font designing tool(a sample is here ). Then you can follow the training process as described here . 来源： https://stackoverflow.com/questions/10763017

When running configure it fails with checking for leptonica... yes checking for pixCreate in -llept... no configure: error: leptonica library missing But I have leptonica 1.69 built (downloaded source and ran ./configure && make install ) Edit I think configure: error: leptonica library missing is a bit misleading, please note that it first says checking for leptonica... yes , and then fails on checking for pixCreate in -llept... no . So maybe the problem is not that the library is missing, but something else. I finally managed to make it compile, after reading this and this thread. The proper

The objective is to create bounding boxes using text recognition methods (eg: OpenCV) for US floor plan images, which can then be fed into a text reader (eg: LSTM or tesseract). Several methods which have been tried cv2.findContours and cv2.boundingRect methods have been attempted but have largely failed to generalise to different types of floor plans (there is a wide deviation in how the floor plans look). For example, cv2.findContours using grayscale, adaptive thresholds, erosion and dilation (with various iterations) before applying the cv2.findContours function results in the bellow. Note