Develop Reference

Improving threshold result for Tesseract

I am kind of stuck with this problem, and I know there are so many questions about it on stack overflow but in my case. Nothing gives the expected result.
The Context:
Am using Android OpenCV along with Tesseract so I can read the MRZ area in the passport. When the camera is started I pass the input frame to an AsyncTask, the frame is processed, the MRZ area is extracted succesfully, I pass the extracted MRZ area to a function prepareForOCR(inputImage) that takes the MRZ area as gray Mat and Will output a bitmap with the thresholded image that I will pass to Tesseract.
The problem:
The problem is while thresholding the Image, I use adaptive thresholding with blockSize = 13 and C = 15, but the result given is not always the same depending on the lighting of the image and the conditions in general from which the frame is taken.
What I have tried:
First I am resizing the image to a specific size (871,108) so the input image is always the same and not dependant on which phone is used.
After resizing, I try with different BlockSize and C values
//toOcr contains the extracted MRZ area
Bitmap toOCRBitmap = Bitmap.createBitmap(bitmap);
Mat inputFrame = new Mat();
Mat toOcr = new Mat();
Utils.bitmapToMat(toOCRBitmap, inputFrame);
Imgproc.cvtColor(inputFrame, inputFrame, Imgproc.COLOR_BGR2GRAY);
TesseractResult lastResult = null;
for (int B = 11; B < 70; B++) {
for (int C = 11; C < 70; C++){
if (IsPrime(B) && IsPrime(C)){
Imgproc.adaptiveThreshold(inputFrame, toOcr, 255, Imgproc.ADAPTIVE_THRESH_GAUSSIAN_C, Imgproc.THRESH_BINARY, B ,C);
Bitmap toOcrBitmap = OpenCVHelper.getBitmap(toOcr);
TesseractResult result = TesseractInstance.extractFrame(toOcrBitmap, "ocrba");
if (result.getMeanConfidence()> 70) {
if (MrzParser.tryParse(result.getText())){
Log.d("Main2Activity", "Best result with " + B + " : " + C);
return result;
}
}
}
}
}
Using the code below, the thresholded result image is a black on white image which gives a confidence greater than 70, I can't really post the whole image for privacy reasons, but here's a clipped one and a dummy password one.
Using the MrzParser.tryParse function which adds checks for the character position and its validity within the MRZ, am able to correct some occurences like a name containing a 8 instead of B, and get a good result but it takes so much time, which is normal because am thresholding almost 255 images in the loop, adding to that the Tesseract call.
I already tried getting a list of C and B values which occurs the most but the results are different.
The question:
Is there a way to define a C and blocksize value so that it s always giving the same result, maybe adding more OpenCV calls so The input image like increasing contrast and so on, I searched the web for 2 weeks now I can't find a viable solution, this is the only one that is giving accurate results

You can use a clustering algorithm to cluster the pixels based on color. The characters are dark and there is a good contrast in the MRZ region, so a clustering method will most probably give you a good segmentation if you apply it to the MRZ region.
Here I demonstrate it with MRZ regions obtained from sample images that can be found on the internet.
I use color images, apply some smoothing, convert to Lab color space, then cluster the a, b channel data using kmeans (k=2). The code is in python but you can easily adapt it to java. Due to the randomized nature of the kmeans algorithm, the segmented characters will have label 0 or 1. You can easily sort it out by inspecting cluster centers. The cluster-center corresponding to characters should have a dark value in the color space you are using.
I just used the Lab color space here. You can use RGB, HSV or even GRAY and see which one is better for you.
After segmenting like this, I think you can even find good values for B and C of your adaptive-threshold using the properties of the stroke width of the characters (if you think the adaptive-threshold gives a better quality output).
import cv2
import numpy as np
im = cv2.imread('mrz1.png')
# convert to Lab
lab = cv2.cvtColor(cv2.GaussianBlur(im, (3, 3), 1), cv2.COLOR_BGR2Lab)
im32f = np.array(im[:, :, 1:3], dtype=np.float32)
k = 2 # 2 clusters
term_crit = (cv2.TERM_CRITERIA_EPS, 30, 0.1)
ret, labels, centers = cv2.kmeans(im32f.reshape([im.shape[0]*im.shape[1], -1]),
k, None, term_crit, 10, 0)
# segmented image
labels = labels.reshape([im.shape[0], im.shape[1]]) * 255
Some results:

Thresholding in Android using opencv

Not sure if this is the right way to ask, but please help. I have an image of a dented car. I have to process it and highlight the dents and return the number of dents. I was able to do it reasonably well with the following result:
The matlab code is:
img2=rgb2gray(i1);
imshow(img2);
img3=imtophat(img2,strel('disk',15));
img4=imadjust(img3);
layer=img4(:,:,1);
img5=layer>100 & layer<250;
img6=imfill(img5,'holes');
img7=bwareaopen(img6,5);
[L,ans]=bwlabeln(img7);
imshow(img7);
I=imread(i1);
Ians=CarDentIdentification(I);
However, when I try to do this using opencv, I get this:
With the following code:
Imgproc.cvtColor(source, middle, Imgproc.COLOR_RGB2GRAY);
Imgproc.equalizeHist(middle, middle);
Imgproc.threshold(middle, middle, 150, 255, Imgproc.THRESH_OTSU);
Please tell me how can I obtain better results in opencv, and also how to count the dents? I tried findcontour() but it gives a very large number. I tried on other images as well, but I'm not getting proper results.
Please help.

So you basically from the MATLAB site, imtophat does - Top-hat filtering computes the morphological opening of the image (using imopen) and then subtracts the result from the original image.
You could do this in OpenCV with the following steps:
Step 1: Get the disk structuring element
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (15, 15))
Step 2: Compute opening of the image and then subtract the result from the original image
tophat = cv2.morphologyEx(v, cv2.MORPH_TOPHAT, kernel)
This gives following result -
Step 3 - Now you could just manually threshold it or use Otsu -
ret, thresh = cv2.threshold(tophat, 17, 255, 0)
which gives you the following image -
Since the OP wants the code in Java, here is the probable code in Java:
private Mat topHat(Mat image)
{
Mat element = Imgproc.getStructuringElement(Imgproc.MORPH_ELLIPSE, new Size(15, 15), new Point (0, 0));
Mat dst = new Mat;
Imgproc.morphologyEx(image, dst, Imgproc.MORPH_TOPHAT, element, new Point(0, 0));
return dst;
}
Make sure you do this on a gray scale image (CvType.8UC1) and then you can threshold suitably.

Android: is there way to limit the barcode height and width

I am referencing this to generate code39 format 1D barcode using Zxing library.
Generate barcode image in Android application
I can generate the barcode. Because i will have three different codes to show in the UI.
Three different codes can have different length like below:
String barcode1_data = "1234567EA";
String barcode2_data = "1234567891012388";
String barcode3_data = "123456789000100";
bitmap1 = encodeAsBitmap2(barcode1_data, BarcodeFormat.CODE_39, 800, 120);
bitmap2 = encodeAsBitmap2(barcode2_data, BarcodeFormat.CODE_39, 1200, 150);
bitmap3 = encodeAsBitmap2(barcode3_data, BarcodeFormat.CODE_39, 1200, 150);
The result UI like this:
I would like to have the three different barcodes to have the same height, and also the width depends on the characters. In my sample code, i hard coded, but i want it to be dynamic. Is there any rule to calculate the height and width?

Since you're creating 1D barcode, how about download a free barcode TTF, and use it on TextView ?
I think it's easy to adjust TextView's width & height.

compare 2 images to avoid duplication

I am comparing 2 similar images and would like to see if both are similar .Currently I used the code:
public void foo(Bitmap bitmapFoo) {
int[] pixels;
int height = bitmapFoo.getHeight();
int width = bitmapFoo.getWidth();
pixels = new int[height * width];
bitmapFoo.getPixels(pixels, 0, width, 1, 1, width - 1, height - 1);
}
and I call the function : foo(img1) where :
img1=(Bitmap)data.getExtras().get("data");
I would like to know how to get the above getpixel,I tried assigning it to variable but did not work .Should it have a return type ?? and in format it is ?
And also how do I compare 2 images??
Also both the images may be of different dimensions based on the mobile camera the snapshot is taken from .
Also can it recognize if the same image is shot in the morning and night ???
Thanks in Advance.

This code will compare pixel from base image with other image.
If both pixel at location (x,y) are same then add same pixel in result image without change. Otherwise it modifies that pixel and add to our result image.
In case of baseline image height or width is larger than other image then it will add red color for extra pixel which is not available in other images.
Both image file format should be same for comparison.
Code will use base image file format to create resultant image file and resultant image contains highlighted portion where difference observed.
Here is a Link To Code with sample example attached.

If you want to copy the pixels of the bitmap to a byte array, the easiest way is:
int height = bitmapFoo.getHeight();
int width = bitmapFoo.getWidth();
pixels = new int[height * width];
bitmapFoo.copyPixelsToBuffer(pixels);
See the documentation
I should warn you that you will have to handle this with care, any other way you will get OutOfMemoryError.
To get All Pixels
bitmapFoo.copyPixelsToBuffer(pixels);
or
bitmapFoo.getPixels(pixels, 0, width, 0, 0, width, height);
To get One Pixel
The two arguments must be two integers within the range [0, getWidth()-1] and [0, getHeight()-1]
int pix = bitmapFoo.getPixel(x, y);

How to stop a Zebra Printer RW 420 from automatically feeding lots of extra paper when issuing command printImage from printer.getGraphicsUtil?

I am using a zebra RW420 in an android project and I am coding and I find that even when simply testing the printer using the ZSDK Developer Demos the printer is printing lots of extra paper when it is issued a print command. In this case I am testing out the signature capture and print demo. I do find that if I connect it to the computer and print a label created using Zebra Designer it prints the label properly with no extra paper (in fact i wouldn't mind a couple of millimeters extra in that case).
If any one knows how to save some trees here that would be great!
The code in question is:
connection.open();
ZebraPrinter printer = ZebraPrinterFactory.getInstance(connection);
GraphicsUtil g = printer.getGraphicsUtil();
Bitmap image = signatureArea.getBitmap();
g.printImage(image, 0, 0, image.getWidth(), image.getHeight(), false);
connection.close();

this works perfect for me:
Connection connection = getZebraPrinterConn();
connection.open();
ZebraPrinter printer = ZebraPrinterFactory.getInstance(connection);
// this is very important which sets automatic heigth setting for label
connection.write("! U1 JOURNAL\r\n! U1 SETFF 50 2\r\n".getBytes());
printer.printImage(new ZebraImageAndroid(bitmap), 0, 0,800, 1200, false);
connection.close();
This wont waste paper and it will print upto the availability of text/data
Assume that you have to print a receipt of width 800 and height 1200 , but it is printing a receipt of height approx. 1800 . so there is a wastage of a receipt for 600 px of white space to make use of that wastage you can use above code.

Do you have the keyword "FORM" in your CPCL label? It's usually before PRINT
This tells the printer to form feed after printing to the top-of-form setting the printer is configured to. To disable it, you can remove the FORM keyword from your format if you don't need it, or you can set the top-of-form to 0.
! U1 getvar "media.tof"
will show you what your top-of-form is currently set to
! U1 setvar "media.tof" "0"
will set it to 0, so that the FORM will feed 0 dots