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
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
def detect(
self,
text_proposals,
scores,
size,
TEXT_PROPOSALS_MIN_SCORE=0.7,
TEXT_PROPOSALS_NMS_THRESH=0.3,
TEXT_LINE_NMS_THRESH=0.3,
LINE_MIN_SCORE=0.8,
):
"""
Detecting texts from an image
:return: the bounding boxes of the detected texts
@@param:TEXT_PROPOSALS_MIN_SCORE:TEXT_PROPOSALS_MIN_SCORE=0.7##过滤字符box阀值
@@param:TEXT_PROPOSALS_NMS_THRESH:TEXT_PROPOSALS_NMS_THRESH=0.3##nms过滤重复字符box
@@param:TEXT_LINE_NMS_THRESH:TEXT_LINE_NMS_THRESH=0.3##nms过滤行文本重复过滤阀值
@@param:MIN_RATIO:MIN_RATIO=1.0#0.01 ##widths/heights宽度与高度比例
@@param:LINE_MIN_SCORE:##行文本置信度
@@param:TEXT_PROPOSALS_WIDTH##每个字符的默认最小宽度
@@param:MIN_NUM_PROPOSALS,MIN_NUM_PROPOSALS=1##最小字符数
"""
#text_proposals, scores=self.text_proposal_detector.detect(im, cfg.MEAN)
keep_inds = np.where(scores > TEXT_PROPOSALS_MIN_SCORE)[0] ###
text_proposals, scores = text_proposals[keep_inds], scores[keep_inds]
sorted_indices = np.argsort(scores.ravel())[::-1]
text_proposals, scores = text_proposals[sorted_indices], scores[
sorted_indices]
# nms for text proposals
if len(text_proposals) > 0:
text_proposals, scores = nms(text_proposals, scores,
TEXT_PROPOSALS_MIN_SCORE,
TEXT_PROPOSALS_NMS_THRESH)
scores = normalize(scores)
text_lines, scores = self.text_proposal_connector.get_text_lines(
text_proposals, scores, size) ##合并文本行
text_lines = get_boxes(text_lines)
text_lines, scores = rotate_nms(text_lines, scores, LINE_MIN_SCORE,
TEXT_LINE_NMS_THRESH)
return text_lines, scores
else:
return []
def detect(self,
text_proposals,
scores,
size,
TEXT_PROPOSALS_MIN_SCORE=0.1,
TEXT_PROPOSALS_NMS_THRESH=0.3,
TEXT_LINE_NMS_THRESH=0.99,
LINE_MIN_SCORE=0.1):
"""
Detecting texts from an image
:return: the bounding boxes of the detected texts
@@param:TEXT_PROPOSALS_MIN_SCORE:TEXT_PROPOSALS_MIN_SCORE=0.7##过滤字符box阀值
@@param:TEXT_PROPOSALS_NMS_THRESH:TEXT_PROPOSALS_NMS_THRESH=0.3##nms过滤重复字符box
@@param:TEXT_LINE_NMS_THRESH:TEXT_LINE_NMS_THRESH=0.3##nms过滤行文本重复过滤阀值
@@param:LINE_MIN_SCORE:##行文本置信度
"""
#text_proposals, scores=self.text_proposal_detector.detect(im, cfg.MEAN)
keep_inds = np.where(scores > TEXT_PROPOSALS_MIN_SCORE)[0] ###
text_proposals, scores = text_proposals[keep_inds], scores[
keep_inds] #1347,4
sorted_indices = np.argsort(scores.ravel())[::-1] # 获取分数顺序排列的索引
text_proposals, scores = text_proposals[sorted_indices], scores[
sorted_indices] #1347,4
# nms for text proposals
if len(text_proposals) > 0:
text_proposals, scores = nms(text_proposals, scores,
TEXT_PROPOSALS_MIN_SCORE,
TEXT_PROPOSALS_NMS_THRESH)
scores = normalize(scores)
text_lines, scores = self.text_proposal_connector.get_text_lines(
text_proposals, scores, size) ##合并文本行
text_lines = get_boxes(text_lines)
text_lines, scores = rotate_nms(text_lines, scores, LINE_MIN_SCORE,
TEXT_LINE_NMS_THRESH)
return text_lines, scores
else:
return []
