|
|
@@ -36,6 +36,16 @@ layout_detection:
|
|
|
# iou: 0.45
|
|
|
|
|
|
# ============================================================
|
|
|
+# Layout后处理配置
|
|
|
+# ============================================================
|
|
|
+layout:
|
|
|
+ # 将大面积文本块转换为表格(后处理)
|
|
|
+ convert_large_text_to_table: true # 是否启用
|
|
|
+ min_text_area_ratio: 0.25 # 最小面积占比(25%)
|
|
|
+ min_text_width_ratio: 0.4 # 最小宽度占比(40%)
|
|
|
+ min_text_height_ratio: 0.3 # 最小高度占比(30%)
|
|
|
+
|
|
|
+# ============================================================
|
|
|
# VL识别配置(表格、公式)
|
|
|
# ============================================================
|
|
|
vl_recognition:
|
|
|
@@ -68,8 +78,9 @@ vl_recognition:
|
|
|
ocr_recognition:
|
|
|
module: "mineru"
|
|
|
language: "ch" # 语言: ch, ch_lite, en, japan 等
|
|
|
- det_threshold: 0.3 # 检测阈值
|
|
|
- unclip_ratio: 1.8 # 文本框扩展比例
|
|
|
+ det_threshold: 0.6 # 检测阈值
|
|
|
+ unclip_ratio: 1.5 # 文本框扩展比例
|
|
|
+ enable_merge_det_boxes: false # 不合并框
|
|
|
batch_size: 8
|
|
|
device: "cpu"
|
|
|
|