zhch158_admin
|
48440201a0
feat: Enhance table processing by adding skew angle estimation and updating related methods
|
2 дней назад |
zhch158_admin
|
51c008723c
test: add unit test for skew estimation and a `.gitignore` file.
|
3 дней назад |
zhch158_admin
|
ce8c1f686b
test: add unit test for skew correction and create .gitignore
|
3 дней назад |
zhch158_admin
|
5dd9e06850
feat: Restructure test directory, add new test cases, a table line generator, and a .gitignore.
|
3 дней назад |
zhch158_admin
|
6d9159d719
添加“全局动态规划与行级动态规划详解”
|
3 дней назад |
zhch158_admin
|
6f3b10f065
feat: 添加倾斜校正阈值参数到表格单元格匹配器
|
4 дней назад |
zhch158_admin
|
f79ce70bd1
feat: 使用行级动态规划优化 HTML 表格单元格与 PaddleOCR 匹配
|
4 дней назад |
zhch158_admin
|
9639383156
贪婪算法 (Greedy)匹配行内单元格的终版
|
4 дней назад |
zhch158_admin
|
b89aafdc08
feat: 删除冗余的表格单元格匹配算法文档
|
4 дней назад |
zhch158_admin
|
f4ac7d0dc7
feat: 添加全局动态规划算法以优化HTML表格行与PaddleOCR文本行的匹配
|
4 дней назад |
zhch158_admin
|
1b49c2d5da
feat: 更新默认配置文件路径以支持新的数据集页面
|
4 дней назад |
zhch158_admin
|
af985f4378
feat: 更新默认配置文件路径以支持新的数据集
|
4 дней назад |
zhch158_admin
|
253b8b6635
feat: 添加倾斜校正阈值和增强的部分匹配防御逻辑,优化表格单元格匹配
|
4 дней назад |
zhch158_admin
|
9da5bd44bc
feat: 增强表格单元格匹配逻辑,新增文本预处理和子序列匹配功能
|
4 дней назад |
zhch158_admin
|
e4e1d1a927
feat: 更新默认配置文件路径,添加新的示例配置以支持特定数据集
|
4 дней назад |
zhch158_admin
|
ee4c55d812
feat: 添加全局动态规划算法以优化HTML与PaddleOCR文本行的匹配
|
5 дней назад |
zhch158_admin
|
32378311cf
feat: add enhanced table cell matcher for PaddleOCR integration
|
5 дней назад |
zhch158_admin
|
631d6cdd7d
feat: 优化表格单元格匹配逻辑,增强动态规划支持跳过HTML行,改进相似度计算
|
5 дней назад |
zhch158_admin
|
04cce2f558
feat: 更新默认配置文件路径,调整示例文件以支持新的数据集
|
5 дней назад |
zhch158_admin
|
8e4a81c034
feat: 添加倾斜角度计算和校正功能,优化表格单元格匹配逻辑
|
6 дней назад |
zhch158_admin
|
2e6f0e8da0
feat: 优化HTML行与Paddle分组的匹配逻辑,支持跳过无关组并防止贪婪匹配
|
6 дней назад |
zhch158_admin
|
696b3bc29a
feat: 更新默认配置文件路径以指向新的PaddleOCR_VL和PaddleOCR JSON文件
|
6 дней назад |
zhch158_admin
|
c943dca746
feat: 更新默认配置文件路径以指向新的PaddleOCR_VL和PaddleOCR JSON文件
|
6 дней назад |
zhch158_admin
|
9d45b5897e
_match_html_rows_to_paddle_groups还需优化
|
6 дней назад |
zhch158_admin
|
45bc511d97
feat: 更新数据处理逻辑以使用PaddleOCR_VL的旋转角度和原始图像尺寸
|
6 дней назад |
zhch158_admin
|
9c6ed0277d
feat: 增加边界框线宽以优化可视化效果
|
6 дней назад |
zhch158_admin
|
9f90a3c17f
feat: 更新表格单元格匹配逻辑以实现简单的1:1映射
|
6 дней назад |
zhch158_admin
|
363e45a366
feat: 更新默认配置文件路径以指向新的PaddleOCR_VL和PaddleOCR JSON文件
|
6 дней назад |
zhch158_admin
|
1ff40aab1d
feat: 更新合并逻辑以提取PaddleOCR的旋转角度和原始图像尺寸,增强数据处理能力
|
6 дней назад |
zhch158_admin
|
89bffd5fb5
feat: 更新合并逻辑以提取PaddleOCR的旋转角度和原始图像尺寸,增强数据处理能力
|
6 дней назад |