• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Multimedia Tools and Applications >DeepSketch 3 Analyzing deep neural networks features for better sketch recognition and sketch-based image retrieval
【24h】

DeepSketch 3 Analyzing deep neural networks features for better sketch recognition and sketch-based image retrieval

机译：DeepSketch 3分析深度神经网络功能，以更好地进行草图识别和基于草图的图像检索

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Freehand sketches are a simple and powerful tool for communication. They are easily recognized across cultures and suitable for various applications. In this paper, we use deep convolutional neural networks (ConvNets), state-of-the-art in the field of sketch recognition, to address several applications of automatic sketch processing: complete and partial sketch recognition, sketch retrieval using query-by-example (QbE), and sketch-based image retrieval (SBIR) i.e the retrieval of images using a QbE paradigm but where the query is a sketch. We first focus on improving sketch recognition. For this purpose we compare different ConvNet architectures, training paradigms and data fusion schemes. This enabled us to outperform previous state-of-the-art in two large scale benchmarks for sketch classification. We achieved a mean average accuracy of 79.18% for the TU-Berlin sketch benchmark and 93.02% for the sketchy database. For partial sketch recognition, we were able to produce a system that achieves a mean average accuracy of 52.58% with only 40% of the strokes. We then conduct a comprehensive study of ConvNets features to enhance sketch retrieval and image retrieval, using a kNN similarity search paradigm in the ConvNet feature space. For the sketch retrieval tasks, we compare the performance obtained with features extracted from various depths (ConvNet layers) using one of the best performing model from the previous work. For the sketch-based image retrieval (SBIR), a sketch query is used to retrieve images of objects that belong to the same category, or even with a shape and pose close to the sketch query. The main challenge in the field of SBIR is to obtain efficient cross-domain features for sketch-image similarity measure. For this, besides comparing features extracted from different depth, we additionally compare different training approaches (some novel) for the ConvNets applied to sketches and images. Eventually, our best SBIR system achieves state-of-the-art results on the sketchy database (close to 40% recall at k = 1).
机译：写意草图是一种简单而强大的交流工具。它们在各种文化中都很容易识别，适合各种应用。在本文中，我们使用草图识别领域中的最新技术深度卷积神经网络（ConvNets）来解决自动草图处理的几种应用：完整和部分草图识别，使用按查询查询的草图检索示例（QbE）和基于草图的图像检索（SBIR），即使用QbE范式检索图像，但查询是草图。我们首先关注改善草图识别。为此，我们比较了不同的ConvNet架构，训练范例和数据融合方案。这使我们能够在草图分类的两个大型基准测试中胜过现有技术。对于TU-Berlin草图基准，我们的平均平均准确度为79.18％，对于草图数据库，则为93.02％。对于部分草图识别，我们能够生产出仅使用40％的笔画就可以达到52.58％的平均平均精度的系统。然后，我们使用ConvNet特征空间中的kNN相似性搜索范例对ConvNets特征进行全面研究，以增强草图检索和图像检索。对于草图检索任务，我们使用以前工作中表现最好的模型之一，将获得的性能与从各个深度（ConvNet层）提取的特征进行比较。对于基于草图的图像检索（SBIR），草图查询用于检索属于同一类别甚至具有接近草图查询的形状和姿势的对象的图像。 SBIR领域的主要挑战是获得有效的跨域特征以进行草图图像相似性度量。为此，除了比较从不同深度提取的特征之外，我们还针对应用于草图和图像的ConvNets比较了不同的训练方法（有些新颖）。最终，我们最好的SBIR系统在粗略的数据库上获得了最新的结果（在k = 1时召回率接近40％）。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号