Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Association Areas of the Cortex01:21

Association Areas of the Cortex

Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...
Automatic Processing and Automatic Social Behavior01:28

Automatic Processing and Automatic Social Behavior

Automatic processing refers to the cognitive operations that occur without conscious intent or awareness, playing a fundamental role in shaping social cognition and behavior. These processes enable individuals to navigate complex social environments efficiently by relying on mental shortcuts and pre-existing knowledge structures known as schemas. One of the most influential mechanisms underlying automatic processing is priming, which subtly activates mental representations through exposure to...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same journal

UniNDM: A Unified Noise-driven Detection and Mitigation Framework Against Sexual Content in Text-to-Image Generation.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Prototype-Anchored Generalized Manifold Regression for Unknown-Domain Object Detection.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

STPP: Efficient and Progressive Structured Pruning Via Enhanced Sparsification Paradigm.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Incomplete Multimodal Probability Flow Recovery for Emotion Recognition.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

MIDAS: Mutual Information Disentanglement With Uncertainty-Aware Fusion for Incomplete Multimodal Sentiment Analysis.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

How Relation Enrichment Improves Clustering Ensemble Performance: A Second Order Induced Relation View.

IEEE transactions on pattern analysis and machine intelligence·2026

Related Experiment Video

Updated: May 29, 2026

Using Insect Electroantennogram Sensors on Autonomous Robots for Olfactory Searches
07:23

Using Insect Electroantennogram Sensors on Autonomous Robots for Olfactory Searches

Published on: August 4, 2014

Automatic feature design for optical character recognition using an evolutionary search procedure.

F W Stentiford1

  • 1British Telecom Research Laboratories. Ipswich, Suffolk, England.

IEEE Transactions on Pattern Analysis and Machine Intelligence
|August 27, 2011
PubMed
Summary

This study introduces an automatic evolutionary search for optical character recognition (OCR) feature extraction. The method achieved a low error rate on machine-printed characters, offering a cost-effective solution.

Related Experiment Videos

Last Updated: May 29, 2026

Using Insect Electroantennogram Sensors on Autonomous Robots for Olfactory Searches
07:23

Using Insect Electroantennogram Sensors on Autonomous Robots for Olfactory Searches

Published on: August 4, 2014

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Optical Character Recognition (OCR) systems require robust feature extraction for accurate character identification.
  • Traditional feature extraction methods can suffer from 'peaking effects', where performance degrades with too many features.
  • Developing efficient and cost-effective OCR solutions remains an active area of research.

Purpose of the Study:

  • To apply an automatic evolutionary search for optimizing feature extraction in OCR.
  • To develop features that are independent and avoid performance degradation (peaking effects).
  • To evaluate the performance of the developed features on a real-world dataset.

Main Methods:

  • An automatic evolutionary search algorithm was employed for feature generation.
  • A performance measure based on feature independence was utilized.
  • Features were extracted from a large dataset of 30,600 machine-printed alphanumeric characters from British mail.
  • Classification accuracy was assessed using both training and test datasets with varying numbers of features.

Main Results:

  • A low forced decision error rate of 1.01% was achieved on the test set using 316 features.
  • The extracted features demonstrated independence, mitigating peaking effects.
  • The approach yielded competitive performance compared to existing low-cost OCR page readers.

Conclusions:

  • Automatic evolutionary search is an effective method for OCR feature extraction.
  • The developed feature set offers high accuracy and robustness.
  • The proposed OCR solution is potentially cost-effective and suitable for practical applications.