OpenCV : Threshold (Binary Image)

1. What is binary Image?

It is an image made up of two colors, black and white. It is useful to tracking shape or recognizing object.

result binary images

2. How to make Binary Image?

It can be made by using Threshold method and depending on the type of flag, you can use various binarizations.

double threshold(InputArray src, OutputArray dst, double thresh, double maxval, int type);

Type :

- THRESH_BINARY : if (src(x,y) > thresh) maxval else 0

- THRESH_BINARY_INV : if (src(x,y) > thresh) 0 else maxval

- THRESH_TRUNC : if(src(x,y) > thresh) threshold else src(x,y)

- THRESH_TOZERO : if (src(x,y) > thresh) src(x,y) else 0

- THRESH_TOZERO_INV : if(src(x,y) > thresh) 0 else src(x,y)

Mat img = imread("./res/text2.jpeg");
Mat gray, binary, binary2, binary3, otsuBinary;
cvtColor(img, gray, CV_RGB2GRAY); // convert to gray color image

// if scalar value is bigger then 128, the value changed to 255(white). else 0(black)

threshold(gray, binary, 128, 255, CV_THRESH_BINARY);
imshow("default binary", binary);

3. Adaptive Threshold

If original image has shadow or gradients, parts of the image are all filled with white or black. This is because one threshold is applied to the entire image. At this time it is more appropriate to use adaptive threshold.
adaptiveThreshold apply the threshold to smaller image divisions.

void adaptiveThreshold(InputArray src, OutputArray dst, double maxValue, int adaptiveMethod, int thresholdType, int blockSize, double C);

adaptiveMethod :

- ADAPTIVE_THRESH_MEANC (threshold value is the mean of neighbourhood area.)

- ADAPTIVE_THRESH_GAUSSIAN_C (threshold value is the weighted sum of neighbourhood values where weights are a gaussian window)

threshold Type :

- THRESH_BINARY

- THRESH_BINARY_INV

blockSize : 3, 5, 7, 9 ...(odd number)

adaptiveThreshold(gray, binary2, 255, ADAPTIVE_THRESH_MEAN_C, THRESH_BINARY, 15, 5);
adaptiveThreshold(gray, binary3, 255, ADAPTIVE_THRESH_GAUSSIAN_C, THRESH_BINARY, 15, 5);
imshow("adaptive Thresh mean", binary2);
imshow("adaptive Thresh gaussian", binary3);

4. Otsu binary

How can you determine the threshold value? If image has two peak of histogram, it can be found between two peaks. Otsu binary helps to calculate the value, so that you do not have to enter a threshold.

GaussianBlur(gray, gray, Size(7,7), 0); // remove noise by making blur

threshold(gray, otsuBinary, 0, 255, CV_THRESH_BINARY + THRESH_OTSU);
imshow("otsu binary", otsuBinary);
waitKey(0);