[PYTHON] I just erased the object using image repair (inpaint) (OpenCV: C ++)

Background I will introduce the inpaint function that exists only in C ++, following I erased the object using image repair (inpaint) (OpenCV: Python).

Introduction

I summarized it roughly in the table.

Development

GNUmakefile

CXX = c++
CXXFLAGS =  -I/usr/local/Cellar/opencv/4.1.1_2/include/opencv4/
LDFLAGS = -L/usr/local/Cellar/opencv/4.1.1_2/lib/
LDLIBS =  -lopencv_core -lopencv_highgui -lopencv_imgcodecs -lopencv_imgproc -lopencv_fuzzy -lopencv_photo -lopencv_xphoto
CXXVERSION = -std=c++11

inpaint: inpaint.cpp
	$(CXX) $< -o $@ $(CXXFLAGS) $(CXXVERSION) $(LDFLAGS) $(LDLIBS)

clean :
	rm inpaint

inpaint.cpp

#include <opencv2/opencv.hpp>
#include <opencv2/highgui.hpp>
#include <opencv2/fuzzy.hpp>
#include <opencv2/photo.hpp>
#include <opencv2/xphoto.hpp>


int main(int argc, const char* argv[]) {
	cv::Mat src = cv::imread("./capture_2.png ");


	cv::Mat resizeMat, dst, mergeMat;
	cv::resize(src, resizeMat, cv::Size(), 0.5, 0.5);

	//Mask image background black-Repair section white
	cv::Mat mask_img = cv::Mat::zeros(resizeMat.size(), CV_8UC3);
	cv::rectangle(mask_img, cv::Point(185,255), cv::Point(470,300), cv::Scalar(255,255,255), -1, cv::LINE_AA); 
	cv::rectangle(mask_img, cv::Point(40,25), cv::Point(115,65), cv::Scalar(255,255,255), -1, cv::LINE_AA);
	cv::rectangle(mask_img, cv::Point(200,40), cv::Point(440,110), cv::Scalar(255,255,255), -1, cv::LINE_AA);

	cv::cvtColor(mask_img,mask_img,cv::COLOR_BGR2GRAY);

	cv::imwrite("mask.png ", mask_img);

	// ns
	cv::inpaint(resizeMat, mask_img, dst, 3, cv::INPAINT_NS);
	cv::imwrite("output_ns.png ", dst);
	dst.release();

	// telea
	cv::inpaint(resizeMat, mask_img, dst, 3, cv::INPAINT_TELEA);
	cv::imwrite("output_telea.png ", dst);
	dst.release();

	cv::Mat mask_inv = ~mask_img;
	resizeMat.copyTo(mergeMat, mask_inv);

	// xphoto
	cv::xphoto::inpaint(mergeMat, mask_inv, dst, cv::xphoto::INPAINT_SHIFTMAP);
	cv::imwrite("output_xphoto_shiftmap.png ", dst);
	dst.release();

	// fuzzy
	cv::ft::inpaint(mergeMat, mask_inv, dst, 3, cv::ft::LINEAR, cv::ft::ONE_STEP);
	cv::imwrite("output_fuzzy_linear_one_step.png ", dst);
	dst.release();

	cv::ft::inpaint(mergeMat, mask_inv, dst, 3, cv::ft::LINEAR, cv::ft::MULTI_STEP);
	cv::imwrite("output_fuzzy_linear_multi.png ", dst);
	dst.release();

	cv::ft::inpaint(mergeMat, mask_inv, dst, 3, cv::ft::LINEAR, cv::ft::ITERATIVE);
	cv::imwrite("output_fuzzy_linear_iterative.png ", dst);
	dst.release();

	src.release();
	mergeMat.release();
	resizeMat.release();
	mask_img.release();
	mask_inv.release();

   return 0;
}

Run

make
./inpaint

Supplement

How to load the mask image is different for each function. cv :: inpaint makes the area to be repaired white, but cv :: xphoto :: inpaint cv :: ft :: inpaint makes it black. Therefore, it is inverted with cv :: Mat mask_inv = ~ mask_img;.

Result

library	parameter	image	odds
photo	INPAINT_NS
photo	INPAINT_TELEA
xphoto	INPAINT_SHIFTMAP
fuzzy	ONE_STEP		×
fuzzy	MULTI_STEP		◎
fuzzy	ITERATIVE		○

If you want to erase the above time, it will be repaired based on the background image, so there is no problem with cv :: inpaint. As for the subtitles below, if you use cv :: inpaint, the crease will be sharp in the middle, but cv :: ft :: inpaint seems to be a little more relaxed. Although it is blurry than other parts, MULTI_STEP is finished naturally as a whole.

cv :: xphoto :: inpaint INPAINT_SHIFTMAP is pasted based on the section in the image, and it seems to be effective when there are many identical objects such as buildings and forests in the background image.

You can see that cv :: ft :: inpaint ONE_STEP is not supported because it is a parameter for small scratches.

Future Next time I will try to erase the subtitles in the video: smirk_cat:

Reference

-Image Inpainting --opencv-python doc -Repair image / remove unnecessary objects --opencv cookbook -Development memo # 69 Using Inpaint with OpenCV 3.2 with Contrib module

• Inpainting using F-transform - opencv doc