Evaluation of an Integer Optimized Shape Matching Algorithm

Gernot Fiala, Johannes Loinig, Christian Steger

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review


Computer vision and machine learning algorithms are often used for quality control for industrial products. Nowadays, neural networks can perform very well to detect the desired objects. Sometimes, the system has limited resources and is not capable of processing complex algorithms or use neural networks. Here, simpler algorithms are used for shape or object detection. The scope of the present work is to even lower the complexity of the shape matching algorithm by converting a shape detection algorithm to an integer version and evaluate the results. This allows to remove floating-point units (FPU) of processors and reduce the area of a System-on-Chip (SoC) design of a smart image sensor.
Original languageEnglish
Title of host publication2021 IEEE Sensors Applications Symposium, SAS 2021 - Proceedings
PublisherIEEE Publications
Number of pages6
ISBN (Electronic)9781728194318
ISBN (Print)978-1-7281-9432-5
Publication statusPublished - 23 Aug 2021
Event16th IEEE Sensors Applications Symposium: SAS 2021 - Virtual, Sundsvall, Sweden
Duration: 23 Aug 202125 Aug 2021

Publication series

Name2021 IEEE Sensors Applications Symposium, SAS 2021 - Proceedings


Conference16th IEEE Sensors Applications Symposium
CityVirtual, Sundsvall


  • Image sensors
  • Program processors
  • Machine learning algorithms
  • Shape
  • Neural networks
  • Quality control
  • Sensors
  • Computer vision
  • Shape matching
  • Shape detection
  • Integer optimization
  • Object detection
  • Sensor SoC
  • Edge

ASJC Scopus subject areas

  • Artificial Intelligence
  • Instrumentation
  • Computer Vision and Pattern Recognition
  • Computer Science Applications


Dive into the research topics of 'Evaluation of an Integer Optimized Shape Matching Algorithm'. Together they form a unique fingerprint.

Cite this