共67个项目结果

文本识别 Python Star 2

  • 本模型改编自GitHub开源项目:[https://github.com/myhub/tr](https://github.com/myhub/tr) 原项目是一款针对扫描文档的离线文本识别SDK,核心代码全部采用C++开发,并提供Python接口。
  • 浏览量:67 下载量:9 about 1 month前

    opencv C Star 0

  • 原始仓库地址:https://github.com/opencv/opencv.git 浏览量:1149 下载量:889 4 months前

    视频昆虫检测 C++ Star 0

  • # 视频昆虫检测 检测视频中运动的昆虫并计数,基于opencv和MOG2背景建模
  • 浏览量:1184 下载量:542 4 months前

    Blind Quality Assessment for Cartoon Images Matlab Star 0

  • Blind Quality Assessment for Cartoon Images --- -- Abstract: Current blind image quality assessment (BIQA) algorithms are mainly designed for natural images. Unfortunately, cartoon and cartoon-like images are quite different from natural images. Hence, recent BIQA methods are not very robust to cartoon images. In this paper, we propose a specific BIQA algorithm designed for cartoon images, which consists of the following terms. First, a cartoon image is divided into edge areas and nonedge areas via a Tchebichef moment (TM)-based process. Second, a multiorder sharpness statistic term is used to measure the quality of the edges, and a sharpness statistic prior model of high-quality (HQ) cartoon images is built. Third, a local encoding statistic term is adopted to describe the textural complexity in the nonedge areas, and a texture statistic prior model is also established. Experimental results on cartoon image datasets demonstrate that the proposed method can accurately evaluate the visual quality of cartoon images and is more suitable for cartoon scenarios than some traditional BIQA algorithms. --- DEMO codes (matlab) -- DEMO video --
  • 浏览量:1348 下载量:658 5 months前

    dindnf C Star 0

  • 原始仓库地址:https://github.com/weinformatics/dindnf.git 浏览量:1459 下载量:600 5 months前

    cuda_spatial_deform C Star 0

  • 原始仓库地址:https://github.com/qsyao/cuda_spatial_deform 浏览量:1848 下载量:805 5 months前

    opencv C Star 0

  • 原始仓库地址:https://github.com/opencv/opencv.git 浏览量:1104 下载量:943 5 months前

    ihub@pcl.ac.cn 鹏城实验室人工智能研究中心

    版权所有:鹏城实验室    粤ICP备18066427号-6    Powerd by 国防科技大学Trustie