Wifbs: A Web-Based Image Feature Benchmark System

Wifbs: A Web-Based Image Feature Benchmark System
复制标题

Wifbs:基于 Web 的图像特征基准系统

DOI:
10.1007/978-3-319-14442-9_14
复制
发表时间:
2015
期刊:
影响因子:
--
通讯作者:
Stefan Gumhold
Stefan Gumhold
中科院分区:
--
文献类型:
--
作者:
Marcel Spehr;Sebastian Grottel;Stefan Gumhold

文献摘要

相似文献

图像数据的自动分析对于许多应用来说非常重要。给定图像分类问题,需要三件事:(i)训练数据和工具来提取(ii)相关视觉信息(通常是图像特征),这些信息可以由(iii)分类算法使用。对于给定的 (i),许多候选人都提出了 (ii) 和 (iii) 的要求。模型选择成为主要问题。我们提出了一个基于网络的功能基准测试系统,使系统设计人员能够使用候选工具的可用实现来简化工具链以满足特定需求。我们的系统具有模块化架构、远程和并行计算、可扩展性以及(从用户的角度来看)由于其基于网络的性质而具有平台独立性。使用Wifbs,图像特征可以接受复杂且公正的模型选择过程,以针对给定的图像分类问题组成优化的管道。
Automatic analysis of image data is of high importance for many applications. Given an image classification problem one needs three things: (i)Training dataand tools to extract (ii)relevant visual information—usually image features—that can be used by (iii)classification algorithms. For given (i), a multitude of candidates present themselves for (ii) and (iii). Model selection becomes the main issue. We present a web-based feature benchmark system enabling system designers to streamline tool-chains to specific needs using available implementations of candidate tools. Our system features a modular architecture, remote and parallel computing, extensibility and—from a user’s standpoint—platform independence due to its web-based nature. UsingWifbs, image features can be subjected to a sophisticated and unbiased model selection procedure to compose optimized pipelines for given image classification problems.