Tampere University of Technology

TUTCRIS Research Portal

CNN-based edge filtering for object proposals

Research output: Contribution to journalArticleScientificpeer-review

Details

Original languageEnglish
Pages (from-to)631-640
JournalNeurocomputing
Volume266
DOIs
Publication statusPublished - 2 Jun 2017
Publication typeA1 Journal article-refereed

Abstract

Recent advances in image-based object recognition have exploited object proposals to speed up the detection process by reducing the search space. In this paper, we present a novel idea that utilizes true objectness and semantic image filtering (retrieved within the convolutional layers of a Convolutional Neural Network) to propose effective region proposals. Information learned in fully convolutional layers is used to reduce the number of proposals and enhance their localization by producing highly accurate bounding boxes. The greatest benefit of our method is that it can be integrated into any existing approach exploiting edge-based objectness to achieve consistently high recall across various intersection over union thresholds. Experiments on PASCAL VOC 2007 and ImageNet datasets demonstrate that our approach improves two existing state-of-the-art models with significantly high margins and pushes the boundaries of object proposal generation.

Keywords

  • Deep learning, Neural networks, Object detection, Object proposals, Region of interest

Publication forum classification

Field of science, Statistics Finland