From a6359e49d21cab9988934515af254ca047bfd122 Mon Sep 17 00:00:00 2001 From: Gourav Roy Date: Mon, 16 Dec 2019 11:12:32 +0530 Subject: [PATCH] Added tutorial for text skewness correction in C++ and Python. --- samples/cpp/text_skewness_correction.cpp | 74 ++++++++++++++++++++++ samples/python/text_skewness_correction.py | 58 +++++++++++++++++ 2 files changed, 132 insertions(+) create mode 100644 samples/cpp/text_skewness_correction.cpp create mode 100644 samples/python/text_skewness_correction.py diff --git a/samples/cpp/text_skewness_correction.cpp b/samples/cpp/text_skewness_correction.cpp new file mode 100644 index 0000000000..15df92e641 --- /dev/null +++ b/samples/cpp/text_skewness_correction.cpp @@ -0,0 +1,74 @@ +/* +This tutorial demonstrates how to correct the skewness in a text. +The program takes as input a skewed source image and shows non skewed text. + +*/ + +#include +#include +#include +#include + +#include +#include +#include + +using namespace cv; +using namespace std; + + +int main( int argc, char** argv ) +{ + CommandLineParser parser(argc, argv, "{@input | imageTextR.png | input image}"); + + // Load image from the disk + Mat image = imread( samples::findFile( parser.get("@input") ), IMREAD_COLOR); + if (image.empty()) + { + cout << "Cannot load the image " + parser.get("@input") << endl; + return -1; + } + + Mat gray; + cvtColor(image, gray, COLOR_BGR2GRAY); + + //Threshold the image, setting all foreground pixels to 255 and all background pixels to 0 + Mat thresh; + threshold(gray, thresh, 0, 255, THRESH_BINARY_INV | THRESH_OTSU); + + // Applying erode filter to remove random noise + int erosion_size = 1; + Mat element = getStructuringElement( MORPH_RECT, Size(2*erosion_size+1, 2*erosion_size+1), Point(erosion_size, erosion_size) ); + erode(thresh, thresh, element); + + cv::Mat coords; + findNonZero(thresh, coords); + + RotatedRect box = minAreaRect(coords); + float angle = box.angle; + + // The cv::minAreaRect function returns values in the range [-90, 0) + // if the angle is less than -45 we need to add 90 to it + if (angle < -45.0f) + { + angle = (90.0f + angle); + } + + //Obtaining the rotation matrix + Point2f center((image.cols) / 2.0f, (image.rows) / 2.0f); + Mat M = getRotationMatrix2D(center, angle, 1.0f); + Mat rotated; + + // Rotating the image by required angle + stringstream angle_to_str; + angle_to_str << fixed << setprecision(2) << angle; + warpAffine(image, rotated, M, image.size(), INTER_CUBIC, BORDER_REPLICATE); + putText(rotated, "Angle " + angle_to_str.str() + " degrees", Point(10, 30), FONT_HERSHEY_SIMPLEX, 0.7, Scalar(0, 0, 255), 2); + cout << "[INFO] angle: " << angle_to_str.str() << endl; + + //Show the image + imshow("Input", image); + imshow("Rotated", rotated); + waitKey(0); + return 0; +} diff --git a/samples/python/text_skewness_correction.py b/samples/python/text_skewness_correction.py new file mode 100644 index 0000000000..c8ee33b39d --- /dev/null +++ b/samples/python/text_skewness_correction.py @@ -0,0 +1,58 @@ +''' +Text skewness correction +This tutorial demonstrates how to correct the skewness in a text. +The program takes as input a skewed source image and shows non skewed text. + +Usage: + python text_skewness_correction.py --image "Image path" +''' + +import numpy as np +import cv2 as cv +import sys +import argparse + + +def main(): + parser = argparse.ArgumentParser() + parser.add_argument("-i", "--image", required=True, help="path to input image file") + args = vars(parser.parse_args()) + + # load the image from disk + image = cv.imread(cv.samples.findFile(args["image"])) + if image is None: + print("can't read image " + args["image"]) + sys.exit(-1) + gray = cv.cvtColor(image, cv.COLOR_BGR2GRAY) + + # threshold the image, setting all foreground pixels to + # 255 and all background pixels to 0 + thresh = cv.threshold(gray, 0, 255, cv.THRESH_BINARY_INV | cv.THRESH_OTSU)[1] + + # Applying erode filter to remove random noise + erosion_size = 1 + element = cv.getStructuringElement(cv.MORPH_RECT, (2 * erosion_size + 1, 2 * erosion_size + 1), (erosion_size, erosion_size) ) + thresh = cv.erode(thresh, element) + + coords = cv.findNonZero(thresh) + angle = cv.minAreaRect(coords)[-1] + # the `cv.minAreaRect` function returns values in the + # range [-90, 0) if the angle is less than -45 we need to add 90 to it + if angle < -45: + angle = (90 + angle) + + (h, w) = image.shape[:2] + center = (w // 2, h // 2) + M = cv.getRotationMatrix2D(center, angle, 1.0) + rotated = cv.warpAffine(image, M, (w, h), flags=cv.INTER_CUBIC, borderMode=cv.BORDER_REPLICATE) + cv.putText(rotated, "Angle: {:.2f} degrees".format(angle), (10, 30), cv.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2) + + # show the output image + print("[INFO] angle: {:.2f}".format(angle)) + cv.imshow("Input", image) + cv.imshow("Rotated", rotated) + cv.waitKey(0) + + +if __name__ == "__main__": + main()