图片行数太多，识别的时候会漏识别其中几行文字，是什么原因导致？

[chongqingwei]

/请
/提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem

• 系统环境/System Environment：linux
• 版本号/Version：Paddle： PaddleOCR：2.6 问题相关组件/Related components：
• 运行指令/Command Code：无
• 完整报错/Complete Error Message：无

我们提供了AceIssueSolver来帮助你解答问题，你是否想要它来解答(请填写yes/no)?/We provide AceIssueSolver to solve issues, do you want it? (Please write yes/no):
/ yes

请尽量不要包含图片在问题中/Please try to not include the image in the [issue.](url)

[chongqingwei]

[chongqingwei]

上面这个图片中，有几行识别不出来？用最新的PP-OCRv4

[chongqingwei]

def read_params():
cfg = Config()

#params for text detector
cfg.det_algorithm = "DB"
cfg.det_model_dir = "./inference/ch_PP-OCRv4_det_server_infer/"
cfg.det_limit_side_len = 2000 #960
cfg.det_limit_type = 'max'

#DB parmas
cfg.det_db_thresh = 0.1 #0.3
cfg.det_db_box_thresh = 0.1 #0.5            # 0.3
cfg.det_db_unclip_ratio = 1.2            # 1.6
cfg.use_dilation = False
cfg.det_db_score_mode = "fast"

#EAST parmas
cfg.det_east_score_thresh = 0.6 #0.8        # 0.6
cfg.det_east_cover_thresh = 0.1
cfg.det_east_nms_thresh = 0.2

#params for text recognizer
cfg.rec_algorithm = "CRNN"
cfg.rec_model_dir = "./inference/ch_PP-OCRv4_rec_server_infer/"

cfg.rec_image_shape = "3, 32, 320"          # "3, 48, 320"
cfg.rec_batch_num = 6
cfg.max_text_length = 35 #25

cfg.rec_char_dict_path = "./ppocr/utils/ppocr_keys_v1.txt"
cfg.use_space_char = True

#params for text classifier
cfg.use_angle_cls = False                   # False
cfg.cls_model_dir = "./inference/ch_ppocr_mobile_v2.0_cls_infer/"
cfg.cls_image_shape = "3, 48, 192"
cfg.label_list = ['0', '180']
cfg.cls_batch_num = 30
cfg.cls_thresh = 0.9

cfg.use_pdserving = False
cfg.use_tensorrt = False
# cfg.drop_score = 0.5

return cfg

[data-ant]

大概率是检测的问题

[chongqingwei]

大概率是检测的问题

您好，怎么解决？看着图片很清晰。

[SWHL]

如果问题仍然存在，建议用可视化文本检测结果，估计是漏检了。