python - 在python中的图像中的表格上创建边框

Question

我有一个图像，其中有一个表格和一些其他数据。我需要为表格绘制边框以分隔每个单元格。

我的图片看起来像这样

我正在尝试: 1)扩大图像以创建连续点，看起来像

2) 寻找轮廓并绘图

问题:我无法正确绘制，因为看起来我的表格单元格太近了，并且在扩大时它们变成了一个连续的点 **我从网上拿了这段代码并试图修改但是对于这张图片效果不佳

代码:

    import os
    import cv2
    import imutils

    # This only works if there's only one table on a page
    # Important parameters:
    #  - morph_size
    #  - min_text_height_limit
    #  - max_text_height_limit
    #  - cell_threshold
    #  - min_columns


    def pre_process_image(img, save_in_file, morph_size=(7, 7)):
        # get rid of the color
        pre = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
        # Otsu threshold
        pre = cv2.threshold(pre,250, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
        # dilate the text to make it solid spot
        cpy = pre.copy()
        struct = cv2.getStructuringElement(cv2.MORPH_RECT, morph_size)
        cpy = cv2.dilate(~cpy, struct, anchor=(-1, -1), iterations=1)
        # cpy = cv2.dilate(img,kernel,iterations = 1)

        pre = ~cpy
        # pre=cpy
        if save_in_file is not None:
            cv2.imwrite(save_in_file, pre)
        return pre


    def find_text_boxes(pre, min_text_height_limit=3, max_text_height_limit=30):
        # Looking for the text spots contours
        contours = cv2.findContours(pre, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
        # contours = contours[0] if imutils.is_cv2() else contours[1]
        contours = contours[0]
        # Getting the texts bounding boxes based on the text size assumptions
        boxes = []
        for contour in contours:
            box = cv2.boundingRect(contour)
            h = box[3]

            if min_text_height_limit < h < max_text_height_limit:
                boxes.append(box)

        return boxes


    def find_table_in_boxes(boxes, cell_threshold=10, min_columns=2):
        rows = {}
        cols = {}

        # Clustering the bounding boxes by their positions
        for box in boxes:
            (x, y, w, h) = box
            col_key = x // cell_threshold
            row_key = y // cell_threshold
            cols[row_key] = [box] if col_key not in cols else cols[col_key] + [box]
            rows[row_key] = [box] if row_key not in rows else rows[row_key] + [box]

        # Filtering out the clusters having less than 2 cols
        table_cells = list(filter(lambda r: len(r) >= min_columns, rows.values()))
        # Sorting the row cells by x coord
        table_cells = [list(sorted(tb)) for tb in table_cells]
        # Sorting rows by the y coord
        table_cells = list(sorted(table_cells, key=lambda r: r[0][1]))

        return table_cells


    def build_lines(table_cells):
        if table_cells is None or len(table_cells) <= 0:
            return [], []

        max_last_col_width_row = max(table_cells, key=lambda b: b[-1][2])
        max_x = max_last_col_width_row[-1][0] + max_last_col_width_row[-1][2]

        max_last_row_height_box = max(table_cells[-1], key=lambda b: b[3])
        max_y = max_last_row_height_box[1] + max_last_row_height_box[3]

        hor_lines = []
        ver_lines = []

        for box in table_cells:
            x = box[0][0]
            y = box[0][1]
            hor_lines.append((x, y, max_x, y))

        for box in table_cells[0]:
            x = box[0]
            y = box[1]
            ver_lines.append((x, y, x, max_y))

        (x, y, w, h) = table_cells[0][-1]
        ver_lines.append((max_x, y, max_x, max_y))
        (x, y, w, h) = table_cells[0][0]
        hor_lines.append((x, max_y, max_x, max_y))

        return hor_lines, ver_lines

if __name__ == "__main__":
    in_file = os.path.join("data", "page1.jpg")
    pre_file = os.path.join("data", "pre.png")
    out_file = os.path.join("data", "out.png")

    img = cv2.imread(os.path.join(in_file))

    pre_processed = pre_process_image(img, pre_file)
    text_boxes = find_text_boxes(pre_processed)
    cells = find_table_in_boxes(text_boxes)
    hor_lines, ver_lines = build_lines(cells)

    # Visualize the result
    vis = img.copy()

    # for box in text_boxes:
    #     (x, y, w, h) = box
    #     cv2.rectangle(vis, (x, y), (x + w - 2, y + h - 2), (0, 255, 0), 1)

    for line in hor_lines:
        [x1, y1, x2, y2] = line
        cv2.line(vis, (x1, y1), (x2, y2), (0, 0, 255), 1)

    for line in ver_lines:
        [x1, y1, x2, y2] = line
        cv2.line(vis, (x1, y1), (x2, y2), (0, 0, 255), 1)

    cv2.imwrite(out_file, vis)

Answer 1

非常有趣的应用。

原始拨号可能不是最好的方法。

我建议使用 OCR 路由。如下图

输出是这样的

所以只要有两排靠的比较近的就可以了。例如，row1-row2< npixel。然后是近线。找到 (row1+height1) 和 row2 之间的中心位置。这条线应该很准确。

在我的样本中如果|292-335| < 50. 然后在 (292+27 + 335)/2 之间画一条线 意味着它介于 Assets 线和属性(property)线之间。

对于OCR包，坚持用python的可以试试tesseract。

https://pypi.org/project/pytesseract/

请参阅此处获取 python 文本坐标 Tesseract OCR Text Position

Tesseract.PageIteratorLevel myLevel = /*TODO*/;
using (var page = Engine.Process(img))
using (var iter = page.GetIterator())
{
    iter.Begin();
    do
    {
        if (iter.TryGetBoundingBox(myLevel, out var rect))
        {
            var curText = iter.GetText(myLevel);
            // Your code here, 'rect' should containt the location of the text, 'curText' contains the actual text itself
        }
    } while (iter.Next(myLevel));
}

rect 包含你想要的 x y 高度宽度的部分

我这里展示的demo其实是用了类似于windows OCR的样例

https://github.com/microsoft/Windows-universal-samples/tree/master/Samples/OCR

请随意尝试任何方法来获得您想要的表格行。