OPENCV学习
原创
mb62b85cd767e68博主文章分类：opencv ©著作权
文章标签 ide 泛洪 搜索 文章分类 Python 后端开发
©著作权归作者所有：来自51CTO博客作者mb62b85cd767e68的原创作品，请联系作者获取转载授权，否则将追究法律责任
环境安装
- opencv-Python
- opencv-contrib-Python
- pytesseract
Opencv模块架构
代码练习1（创建图片窗口，使用摄像头）：
import cv2 as cvimport numpy as npimage_path = "datasources/images/1 (1).jpg"def look_dog_image(): src = cv.imread(image_path, 1) cv.namedWindow("input image", cv.WINDOW_AUTOSIZE) cv.imshow("input image", src) gray = cv.cvtColor(src, cv.COLOR_BGR2GRAY) cv.imwrite("resule.png", gray) cv.waitKey(0) cv.destroyAllWindows() return srcdef get_image_info(image_path): print(type(image_path)) print(image_path.shape) print(image_path.size) print(image_path.dtype) print("-------------") print(np.array(image_path))def look_video(): capture = cv.VideoCapture(0) while(True): ret, frame = capture.read() frame = cv.flip(frame, 1) cv.imshow("video", frame) c = cv.waitKey(50) if c == 27 : breakif __name__ == "__main__": get_image_info(look_dog_image())
代码练习2（创建图像）：
import cv2 as cvimport numpy as npimage_path = "datasources/images/1 (1).jpg"def access_pixels(image_path): src = cv.imread(image_path, 1) print(src.shape) width = src.shape[0] height = src.shape[1] channels = src.shape[2] for w in range(width): for h in range(height): for c in range(channels): pv = src[w, h, c] src[w, h, c] = 255 - pv cv.imshow("colos", src) cv.waitKey(0) cv.destroyAllWindows()def create_image(): img = np.ones([400, 400, 3], np.uint8) img[:, :, 0] = np.ones([400, 400])*255 m = np.ones([5, 8], np.float32) m.fill(233) n =m.reshape([10, 4]) print(m) print("-----") print(n) cv.imshow("new image", img) cv.imwrite("ps.png", img) cv.waitKey(0) cv.destroyAllWindows()if __name__ == "__main__": create_image()
- 总结:
基本完成，对于泛洪的理解：参数3起始点的像素值减去参数5的像素值表示的是从起始点开始搜索周边范围的像素最低值，参数3起始点的像素值加上参数5的像素值表示的是从起始点开始搜索周边范围的像素最大值。有了这个范围，然后该函数就可以在这个连续像素范围内填充指定的颜色newVal参数值。高斯双边滤波，相当于磨皮操作，均值偏移滤波处理，想当与把图片转油画的操作。重点：numpy库的函数、二值化难点：ROI与泛洪填充、滤波
- 赞
- 收藏
- 评论
- *举报
Original: https://blog.51cto.com/u_15698638/5418941
Author: mb62b85cd767e68
Title: OPENCV学习
原创文章受到原创版权保护。转载请注明出处：https://www.johngo689.com/513711/
转载文章受原作者版权保护。转载请注明原作者出处！