Exemple #1
0
def text_detect(img,
                MAX_HORIZONTAL_GAP=30,
                MIN_V_OVERLAPS=0.6,
                MIN_SIZE_SIM=0.6,
                TEXT_PROPOSALS_MIN_SCORE=0.7,
                TEXT_PROPOSALS_NMS_THRESH=0.3,
                TEXT_LINE_NMS_THRESH=0.3):
    boxes, scores = detect.text_detect(np.array(img))
    boxes = np.array(boxes, dtype=np.float32)
    scores = np.array(scores, dtype=np.float32)
    textdetector = TextDetector(MAX_HORIZONTAL_GAP, MIN_V_OVERLAPS,
                                MIN_SIZE_SIM)
    shape = img.shape[:2]
    boxes = textdetector.detect(boxes, scores[:, np.newaxis], shape,
                                TEXT_PROPOSALS_MIN_SCORE,
                                TEXT_PROPOSALS_NMS_THRESH,
                                TEXT_LINE_NMS_THRESH)

    text_recs = get_boxes(boxes)
    newBox = []
    rx = 1
    ry = 1
    for box in text_recs:
        x1, y1 = (box[0], box[1])
        x2, y2 = (box[2], box[3])
        x3, y3 = (box[6], box[7])
        x4, y4 = (box[4], box[5])
        newBox.append([
            x1 * rx, y1 * ry, x2 * rx, y2 * ry, x3 * rx, y3 * ry, x4 * rx,
            y4 * ry
        ])
    return newBox
Exemple #2
0
def text_detect(img,
                MAX_HORIZONTAL_GAP=30,
                MIN_V_OVERLAPS=0.6,
                MIN_SIZE_SIM=0.6,
                TEXT_PROPOSALS_MIN_SCORE=0.7,
                TEXT_PROPOSALS_NMS_THRESH=0.3,
                TEXT_LINE_NMS_THRESH=0.3,
                bili=1.2):  #下面8行检测单个文字

    #下面几行是用yolo给出框.
    Image.fromarray(img).save("look.png")  #看看boxes,scores的含义 是所有rpn的结果.
    boxes, scores = detect.text_detect(np.array(img))  #这里面用的是yolo
    boxes = np.array(boxes, dtype=np.float32)
    scores = np.array(scores, dtype=np.float32)

    Allboxes = boxes
    AllScores = scores

    #函数下面部分是做行拼接.
    textdetector = TextDetector(MAX_HORIZONTAL_GAP, MIN_V_OVERLAPS,
                                MIN_SIZE_SIM)

    shape = img.shape[:2]

    #看看下行boxes 的含义.  scores:表示最后抽取的汉字对应的score?????????对的,下行的scores就是最后每行的
    #分数了!!!!!!!!!!!!!1 非常重要的参数. #下面几行做文字box拼接成seq #tp_groups 表示每一行的文字对应
    #boxesForSingle 中的index
    boxes, scores, keepIndForSingle, tp_groups, boxesForSingle, scoresForSingle = textdetector.detect(
        boxes, scores[:, np.newaxis], shape, TEXT_PROPOSALS_MIN_SCORE,
        TEXT_PROPOSALS_NMS_THRESH, TEXT_LINE_NMS_THRESH, bili)
    #tp_groups 是boxes对应的 box标号.
    text_recs = get_boxes(boxes)

    print(text_recs.shape, "text_recs.shape")
    newBox = []
    rx = 1
    ry = 1
    for box in text_recs:
        x1, y1 = (box[0], box[1])
        x2, y2 = (box[2], box[3])
        x3, y3 = (box[6], box[7])
        x4, y4 = (box[4], box[5])
        newBox.append([
            x1 * rx, y1 * ry, x2 * rx, y2 * ry, x3 * rx, y3 * ry, x4 * rx,
            y4 * ry
        ])

    return newBox, scores, boxesForSingle, scoresForSingle, keepIndForSingle, tp_groups, Allboxes, AllScores