• Home
  • Search
  • Repeated Pattern Detection Using CNN Activations
  • Open Access IconOpen Access
  • Cite Icon37
  • https://doi.org/10.1109/wacv.2017.13Copy DOI Icon

Repeated Pattern Detection Using CNN Activations

  • Mar 1, 2017
  • Louis Lettry +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

We propose a new approach for detecting repeated patterns on a grid in a single image. To do so, we detect repetitions in the space of pre-trained deep CNN filter responses at all layer levels. These encode features at several conceptual levels (from low-level patches to high-level semantics) as well as scales (from local to global). As a result, our repeated pattern detector is robust to challenging cases where repeated tiles show strong variation in visual appearance due to occlusions, lighting or background clutter. Our method contrasts with previous approaches that rely on keypoint extraction, description and clustering or on patch correlation. These generally only detect low-level feature clusters that do not handle variations in visual appearance of the patterns very well. Our method is simpler, yet incorporates high level features implicitly. As such, we can demonstrate detections of repetitions with strong appearance variations, organized on a nearly-regular axis-aligned grid Results show robustness and consistency throughout a varied database of more than 150 images.

Similar Papers
  • Conference Article
  • Citations6

Autonomous Object Detection in Satellite Images Using Wfrcnn

  • Dec 01, 2020
  • Nour Aburaed +5
  • Research Article
  • Citations1

Unsupervised Person Re-Identification via Deep Attribute Learning

  • Aug 15, 2025
  • Future Internet
  • Shun Zhang +4
  • Research Article
  • Citations63

Estimation and monitoring of product aesthetics: application to manufacturing of “engineered stone” countertops

  • Jan 06, 2006
  • Machine Vision and Applications
  • J Jay Liu +1
  • Research Article
  • Citations13

Subclass linear discriminant analysis for video-based face recognition

  • Aug 21, 2009
  • Journal of Visual Communication and Image Representation
  • Aristodemos Pnevmatikakis +1
  • Book Chapter
  • Citations16

Object Recognition via Local Patch Labelling

  • Jan 01, 2005
  • Christopher M Bishop +1
  • Book Chapter
  • Citations426

Deep Attributes Driven Multi-camera Person Re-identification

  • Jan 01, 2016
  • Chi Su +4
  • Research Article
  • Citations73

Multi-type attributes driven multi-camera person re-identification

  • Sep 12, 2017
  • Pattern Recognition
  • Chi Su +4
  • PDF
  • Research Article
  • Citations13

Person Re-Identification With Joint Verification and Identification of Identity-Attribute Labels

  • Jan 01, 2019
  • IEEE Access
  • Shun Zhang +5
  • Conference Article
  • Citations1181

The German Traffic Sign Recognition Benchmark: A multi-class classification competition

  • Jul 01, 2011
  • Johannes Stallkamp +3
  • Conference Article
  • Citations4

Exploiting low-rank structures from cross-camera images for robust person re-identification

  • Oct 01, 2014
  • Ming-Hang Fu +2
  • Conference Article
  • Citations3

Triplet CNN and pedestrian attribute recognition for improved person re-identification

  • Aug 01, 2017
  • Yiqiang Chen +4
  • PDF
  • Research Article
  • Citations14

Appearance evaluation of digital materials in material jetting

  • May 06, 2023
  • Optics and Lasers in Engineering
  • Ali Payami Golhin +1
  • PDF
  • Research Article
  • Citations24

Digital taxonomist: Identifying plant species in community scientists’ photographs

  • Oct 25, 2021
  • ISPRS Journal of Photogrammetry and Remote Sensing
  • Riccardo De Lutio +6
  • Conference Article

Concrete Crack, Spalling, and Exposed Rebar Detection Model Based on Improved YOLOv11

  • Nov 21, 2025
  • Song Zhang +4
  • Research Article
  • Citations8

Optical properties of tilted surfaces in material jetting

  • Aug 25, 2023
  • Optics & Laser Technology
  • Ali Payami Golhin +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.