aklenka's profile - activity

Thanks for your comments.

I am trying use the sample opencv code of Features2D + Homography to find a known object. When I used in opencv C++ platform I am not getting any issue. But when the same code used in Android system and the above code used inside jni .cpp then the below error getting.

fatal error: opencv2/nonfree/features2d.hpp: No such file or directory DetectionBasedTracker_jni.cpp /OpenCV Sample - face-detection/jni line 15 C/C++ Problem

SurfDescriptorExtractor' is not a member of 'cv' DetectionBasedTracker_jni.cpp /OpenCV Sample - face-detection/jni line 453 C/C++ Problem.

Even I checked the nonfree module is not available in Android OpenCV-2.4.4-android-sdk\sdk\native\jni\include\opencv2.

Where I can get this SurfDescriptorExtractor typedef in open cv android native. Is there any alternative. Please suggest me.

I am just giving one example. My objective is how to remove non text background of any image object. If you have any concept please share.

There are multiple uses are there for this activities, how can extract the text from an image and display in text form. I have taken some data of credit card. The main object of this activities is to detect any credit card number through mobile and do some online transaction over this.

I have updated the image. please recheck.

I am developing an app for extracting number from image card using sample code of android-ocr(tesseract-ocr). I have trained the data as per the card font. It is detecting few card if the card having unique background, but if the card having multi background (attached sample) then the number is not recognizing. Even if the card number little overlapping the background then also not recognition.

I tried to use the below steps to remove the background.

1. Smoothing the cropped image using GaussianBlur( crop, crop, Size(3,3), 0, 0, BORDER_DEFAULT ); cvtColor( crop, crop, CV_RGB2GRAY );
2. Edge detection using sobel: crop = SobelEdgeDetect(crop);
3. Converting to bitwise not: cv::bitwise_not(crop,crop);
4. Used adaptiveThreshold to remove shadowed kind of things: adaptiveThreshold(crop,crop,255,CV_ADAPTIVE_THRESH_MEAN_C, CV_THRESH_BINARY,75,10);

After using these steps I am getting the image (attached bar-Process`png, citi1-Process.png, citi-Process.png), which is coming bold with blank space inside the number. In this case the ocr application is not recognize the number. I do not know how can fill these number with bold letter.

Now the big challenge for me to remove the background from any image card with out disturbing the text part of the card. So please suggest me how can I overcome all the above issue specific how can remove the background of the image.

I have attached few sample & output data for your reference. Thanks & regards

Anil