Efficient Development of User-Defined Image Recognition Systems

2013 ◽  
pp. 242-253 ◽  
Author(s):  
Julia Moehrmann ◽  
Gunther Heidemann
Keyword(s):  
Image Recognition ◽  
Recognition Systems

An Integrated Memory Array Processor for Embedded Image Recognition Systems

2007 ◽  
Vol 56 (5) ◽  
pp. 622-634 ◽  
Author(s):  
Shorin Kyo ◽  
Shin'ichiro Okazaki ◽  
Tamio Arai
Keyword(s):  
Image Recognition ◽  
Array Processor ◽  
Memory Array ◽  
Recognition Systems ◽  
Embedded Image

scholarly journals Diagnosing Gender Bias in Image Recognition Systems

2020 ◽  
Vol 6 ◽  
pp. 237802312096717
Author(s):  
Carsten Schwemmer ◽  
Carly Knight ◽  
Emily D. Bello-Pardo ◽  
Stan Oklobdzija ◽  
Martijn Schoonvelde ◽  
...  
Keyword(s):  
Machine Learning ◽  
Gender Bias ◽  
Image Recognition ◽  
Gender Stereotypes ◽  
Expert Knowledge ◽  
Physical Appearance ◽  
Past Research ◽  
Learning Systems ◽  
Gender Biases ◽  
Recognition Systems

Image recognition systems offer the promise to learn from images at scale without requiring expert knowledge. However, past research suggests that machine learning systems often produce biased output. In this article, we evaluate potential gender biases of commercial image recognition platforms using photographs of U.S. members of Congress and a large number of Twitter images posted by these politicians. Our crowdsourced validation shows that commercial image recognition systems can produce labels that are correct and biased at the same time as they selectively report a subset of many possible true labels. We find that images of women received three times more annotations related to physical appearance. Moreover, women in images are recognized at substantially lower rates in comparison with men. We discuss how encoded biases such as these affect the visibility of women, reinforce harmful gender stereotypes, and limit the validity of the insights that can be gathered from such data.

scholarly journals Implementing Convolutional Neural Networks for Simple Image Classification

2019 ◽  
Vol 9 (2) ◽  
pp. 3616-3619
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Image Recognition ◽  
High Volume ◽  
Classification Systems ◽  
Learning Tools ◽  
Huge Amount ◽  
Recognition Systems

In recent years, huge amounts of data in form of images has been efficiently created and accumulated at extraordinary rates. This huge amount of data that has high volume and velocity has presented us with the problem of coming up with practical and effective ways to classify it for analysis. Existing classification systems can never fulfil the demand and the difficulties of accurately classifying such data. In this paper, we built a Convolutional Neural Network (CNN) which is one of the most powerful and popular machine learning tools used in image recognition systems for classifying images from one of the widely used image datasets CIFAR-10. This paper also gives a thorough overview of the working of our CNN architecture with its parameters and difficulties.

scholarly journals Diagnosing Gender Bias in Image Recognition Systems

2018 ◽  
Author(s):  
Carsten Schwemmer ◽  
Carly Knight ◽  
Emily Bello-Pardo ◽  
Stan Oklobdzija ◽  
Martijn Schoonvelde ◽  
...  
Keyword(s):  
Machine Learning ◽  
Gender Bias ◽  
Image Recognition ◽  
Gender Stereotypes ◽  
Expert Knowledge ◽  
Physical Appearance ◽  
Past Research ◽  
Learning Systems ◽  
Gender Biases ◽  
Recognition Systems

Image recognition systems offer the promise to learn from images at scale without requiring expert knowledge. However, past research suggests that machine learning systems often produce biased output. In this article, we evaluate potential gender biases of commercial image recognition platforms using photographs of U.S. members of Congress and a large number of Twitter images posted by these politicians. Our crowdsourced validation shows that commercial image recognition systems can produce labels that are correct and biased at the same time as they selectively report a subset of many possible true labels. We find that images of women received three times more annotations related to physical appearance. Moreover, women in images are recognized at substantially lower rates in comparison with men. We discuss how encoded biases such as these affect the visibility of women, reinforce harmful gender stereotypes, and limit the validity of the insights that can be gathered from such data.

Sign in / Sign up

Export Citation Format

Share Document