I notice that almost all the answers here relate to the ineffectiveness of the concept of CAPTCHA, in principle – and while I very much agree with them, in fact gave a talk at OWASP a few months ago explaining just that – the question is very specific, so I will provide for a demonstration. … Read more
Here is my result: Here is the code: #include <iostream> #include <vector> #include <stdio.h> #include <stdarg.h> #include “opencv2/opencv.hpp” #include “fstream” #include “iostream” using namespace std; using namespace cv; //—————————————————————————————————– // //—————————————————————————————————– void CalcBlockMeanVariance(Mat& Img,Mat& Res,float blockSide=21) // blockSide – the parameter (set greater for larger font on image) { Mat I; Img.convertTo(I,CV_32FC1); Res=Mat::zeros(Img.rows/blockSide,Img.cols/blockSide,CV_32FC1); Mat inpaintmask; … Read more
Although the documentation suggests that you can set which format the image data should arrive from the camera in, in practice you often have a choice of one: NV21, a YUV format. For lots of information on this format see http://www.fourcc.org/yuv.php#NV21 and for information on the theory behind converting it to RGB see http://www.fourcc.org/fccyvrgb.php. There … Read more
Create a config file (e.g “letters”) in tessdata/configs directory – usually /usr/share/tesseract/tessdata/configs or /usr/share/tesseract-ocr/tessdata/configs And add this line to the config file: tessedit_char_whitelist abcdefghijklmnopqrstuvwxyz …or maybe [a-z] works. I don’t know. Then call tesseract similar to this: tesseract input.tif output nobatch letters That will limit tesseract to recognize only the wanted characters.
When it comes to identifying text in images you better use Stroke Width Transform. Here’s a little result I obtained on your image (the basic transform + connected component w/o filtering): My mex implementation based on code from here #include “mex.h” #include <vector> #include <map> #include <set> #include <algorithm> #include <math.h> using namespace std; #define … Read more
From your input image, you need to make text as white, and background as black You need then to compute the rotation angle of your bill. A simple approach is to find the minAreaRect of all white points (findNonZero), and you get: Then you can rotate your bill, so that text is horizontal: Now you … Read more
for recognition or classification most OCR’s use neural networks These must be properly configured to desired task like number of layers internal interconnection architecture , and so on. Also problem with neural networks is that they must be properly trained which is pretty hard to do properly because you will need to know for that … Read more
OCR can be pretty CPU intensive, you might want to reconsider doing it on a smart phone. That aside, to my knowledge the popular OCR libraries are Aspire and Tesseract. Neither are straight up Java, so you’re not going to get a drop-in Android OCR library. However, Tesseract is open source (GitHub hosted infact); so … Read more
Here’s a modified implementation of the Projection Profile Method to correct skewed images as described in Projection profile based skew estimation algorithm for JBIG compressed images. After obtaining a binary image, the idea is to rotate the image at various angles and generate a histogram of pixels in each iteration. To determine the skew angle, … Read more
Here’s an implementation of the Projection Profile Method algorithm for skew angle estimation. Various angle points are projected into an accumulator array where the skew angle can be defined as the angle of projection within a search interval that maximizes alignment. The idea is to rotate the image at various angles and generate a histogram … Read more