Replies: 8 comments
-
原图是什么样子的呢? |
Beta Was this translation helpful? Give feedback.
-
以下是原图: |
Beta Was this translation helpful? Give feedback.
-
请问,可以调整哪个参数开放以使得不截断之前的图像内容吗? |
Beta Was this translation helpful? Give feedback.
-
uvdoc矫正过后就是会导致坐标发生变化,应该是不好恢复的。 |
Beta Was this translation helpful? Give feedback.
-
意思是矫正后没法获取全部图像内容? |
Beta Was this translation helpful? Give feedback.
-
矫正后只能得到矫正区域的信息,想到完整原始的图片信息,得关掉图片矫正。 |
Beta Was this translation helpful? Give feedback.
-
我的想矫正后做一次整图OCR,如果矫正后内容有截断,就要分矫正前OCR和矫正后OCR了 |
Beta Was this translation helpful? Give feedback.
-
这个模型应该主要针对文档图片矫正的,用在其他场景可能效果不理想。 |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
🔎 Search before asking
🐛 Bug (问题描述)
使用pipeline调用UVDoc矫正模型后图像内容被截断,怎么设置参数保留全部内容?
在使用该方式调用时,也需要保留矫正完的所有图像,不需要截断,因为会将边缘部分带有文字的内容截断。
🏃♂️ Environment (运行环境)
使用docker镜像:ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/paddle:3.0.0-gpu-cuda12.6-cudnn9.5-trt10.5
🌰 Minimal Reproducible Example (最小可复现问题的Demo)
Beta Was this translation helpful? Give feedback.
All reactions