论文标题
传统方法启发了深度神经网络以进行边缘检测
Traditional Method Inspired Deep Neural Network for Edge Detection
论文作者
论文摘要
最近，基于深神经网络（DNN）的边缘预测正在迅速发展。尽管基于DNN的方案的表现优于传统边缘检测器，但它们具有更高的计算复杂性。可能是基于DNN的边缘检测器通常采用专为高级计算机视觉任务（例如图像分割和对象识别）设计的神经网络结构。边缘检测是一项相当局部且简单的工作，不必要的构造过度和大量参数。因此，我们提出了一个传统方法启发的框架，以最少的复杂性产生良好的边缘。我们简化了网络体系结构，包括功能提取器，富集和摘要器，它们与传统边缘检测方案中的梯度，低通滤波器和像素连接大致相对应。提出的结构可以有效地降低复杂性并保留边缘预测质量。我们的TIN2（传统灵感网络）模型的精度高于最近的BDCN2（双向级联网络），但具有较小的模型。
Recently, Deep-Neural-Network (DNN) based edge prediction is progressing fast. Although the DNN based schemes outperform the traditional edge detectors, they have much higher computational complexity. It could be that the DNN based edge detectors often adopt the neural net structures designed for high-level computer vision tasks, such as image segmentation and object recognition. Edge detection is a rather local and simple job, the over-complicated architecture and massive parameters may be unnecessary. Therefore, we propose a traditional method inspired framework to produce good edges with minimal complexity. We simplify the network architecture to include Feature Extractor, Enrichment, and Summarizer, which roughly correspond to gradient, low pass filter, and pixel connection in the traditional edge detection schemes. The proposed structure can effectively reduce the complexity and retain the edge prediction quality. Our TIN2 (Traditional Inspired Network) model has an accuracy higher than the recent BDCN2 (Bi-Directional Cascade Network) but with a smaller model.
