Discriminatively Trained Sparse Code Gradients for Contour Detection

Discriminatively Trained Sparse Code Gradients for Contour Detection
复制标题

DOI：
--
复制
发表时间：
2012-12
期刊：
--
影响因子：
--
通讯作者：
Xiaofeng Ren;Liefeng Bo
Xiaofeng Ren;Liefeng Bo
中科院分区：
其他
文献类型：
--
作者：
Xiaofeng Ren;Liefeng Bo

文献摘要

被引文献

相似文献

在自然图像中寻找轮廓是一个基本问题，它是图像分割和目标识别等许多任务的基础。轮廓检测技术的核心是一组手工设计的梯度特征，包括最先进的全局Pb （gPb）算子在内的大多数方法都使用了这些特征。在这项工作中，我们证明了通过计算稀疏代码梯度（SCG）可以显着提高轮廓检测精度，SCG使用通过稀疏编码自动学习的补丁表示来测量对比度。我们使用K-SVD进行字典学习，使用正交匹配追踪计算有向局部邻域上的稀疏码，并在使用线性支持向量机分类之前应用多尺度池化和幂变换。通过从像素中提取丰富的表示并避免过早地折叠它们，稀疏代码梯度有效地学习如何测量局部对比度并找到轮廓。我们将BSDS500基准上的F-measure度量提高到0.74（高于gPb轮廓的0.71）。此外，我们的学习方法可以很容易地适应新的传感器数据，如kinect风格的RGB-D相机：深度图和表面法线上的稀疏代码梯度导致使用深度和深度+颜色的轮廓检测，正如在纽约大学深度数据集上验证的那样。
Finding contours in natural images is a fundamental problem that serves as the basis of many tasks such as image segmentation and object recognition. At the core of contour detection technologies are a set of hand-designed gradient features, used by most approaches including the state-of-the-art Global Pb (gPb) operator. In this work, we show that contour detection accuracy can be significantly improved by computing Sparse Code Gradients (SCG), which measure contrast using patch representations automatically learned through sparse coding. We use K-SVD for dictionary learning and Orthogonal Matching Pursuit for computing sparse codes on oriented local neighborhoods, and apply multi-scale pooling and power transforms before classifying them with linear SVMs. By extracting rich representations from pixels and avoiding collapsing them prematurely, Sparse Code Gradients effectively learn how to measure local contrasts and find contours. We improve the F-measure metric on the BSDS500 benchmark to 0.74 (up from 0.71 of gPb contours). Moreover, our learning approach can easily adapt to novel sensor data such as Kinect-style RGB-D cameras: Sparse Code Gradients on depth maps and surface normals lead to promising contour detection using depth and depth+color, as verified on the NYU Depth Dataset.