Nav: Home

Neural networks taught to recognize similar objects on videos without accuracy degradation

June 21, 2019

Andrey Savchenko, Professor at the Higher School of Economics (HSE University), has developed a method that can help to enhance image identification on videos. In his project, a network was taught by a new algorithm and can now make decisions on image recognition and classification at a rate 10 times faster than before. This research was presented in the paper 'Sequential three-way decisions in multi-category image recognition with deep features based on distance factor' published in Information Sciences.

The neural networks learned to identify humans and animals in videos a long time ago. Artificial neurons can learn by remembering what a certain object looks like in an image. Usually, researchers take an open database of photos (e.g., ImageNet, Places, etc.) and use it to teach a neural network. To speed up the decision-making process, our algorithm is set to pick only some of the sample images, or focus on a limited number of traits. Complications may arise when objects of different classes are in the same photo, and there are only small number of training examples for each category.

The new algorithm now can recognize images without significant accuracy degradation through the application of a sequential three-way decision-making method. By employing this approach, a neural network can analyze simple images in one way for clearly recognizable objects, while objects that are difficult to identify can be given a more detailed examination.

'Each photo can be described by literally thousands of features. So, it wouldn't make much sense to compare all of the features of a given input image with those of a basic training example, since most samples would not be similar to the analyzed image. So, we initially only compared just a few of the important features, and put aside the training instances, which obviously cannot be treated as final solutions. As a result, the training sample becomes smaller and only a few examples are left. At the next stage, we would increase the number of features for the remaining images, and then repeat this process until only one class is left,' Prof. Savchenko noted.

This approach reduced the time for recognition by 1.5 to 10 times, as compared to regular classifiers and known multi-category sequential three-way decisions. As a result, this technology could be used in future on mobile devices and other basic gadgets.
-end-
This study was made available online in March 2019 ahead of final publication in print in July 2019.

National Research University Higher School of Economics

Related Algorithm Articles:

Algorithm personalizes which cancer mutations are best targets for immunotherapy
As tumor cells multiply, they often spawn tens of thousands of genetic mutations.
Universal algorithm set to boost microscopes
EPFL scientists have developed an algorithm that can determine whether a super-resolution microscope is operating at maximum resolution based on a single image.
Algorithm designed to map universe, solve mysteries
Cornell University researchers have developed an algorithm designed to visualize models of the universe in order to solve some of physics' greatest mysteries.
Algorithm tells robots where nearby humans are headed
A new tool for predicting a person's movement trajectory may help humans and robots work together in close proximity.
Algorithm to transform investment banking with higher returns
A University of Bath researcher has created an algorithm which aims to remove the elements of chance, bias or emotion from investment banking decisions, a development which has the potential to reduce errors in financial decision making and improve financial returns in global markets.
Algorithm provides customized caffeine strategy for alertness
A web-based caffeine optimization tool successfully designs effective strategies to maximize alertness while avoiding excessive caffeine consumption, according to preliminary results from a new study.
New algorithm optimizes quantum computing problem-solving
Tohoku University researchers have developed an algorithm that enhances the ability of a Canadian-designed quantum computer to more efficiently find the best solution for complicated problems, according to a study published in the journal Scientific Reports.
Machine learning algorithm helps in the search for new drugs
Researchers have designed a machine learning algorithm for drug discovery which has been shown to be twice as efficient as the industry standard, which could accelerate the process of developing new treatments for disease.
Researchers create algorithm to predict PEDV outbreaks
Researchers from North Carolina State University have developed an algorithm that could give pig farms advance notice of porcine epidemic diarrhea virus (PEDV) outbreaks.
New algorithm provides a more detailed look at urban heat islands
Urban areas are warmer than the adjacent undeveloped land, a phenomenon known as the urban heat island effect.
More Algorithm News and Algorithm Current Events

Top Science Podcasts

We have hand picked the top science podcasts of 2019.
Now Playing: TED Radio Hour

Risk
Why do we revere risk-takers, even when their actions terrify us? Why are some better at taking risks than others? This hour, TED speakers explore the alluring, dangerous, and calculated sides of risk. Guests include professional rock climber Alex Honnold, economist Mariana Mazzucato, psychology researcher Kashfia Rahman, structural engineer and bridge designer Ian Firth, and risk intelligence expert Dylan Evans.
Now Playing: Science for the People

#541 Wayfinding
These days when we want to know where we are or how to get where we want to go, most of us will pull out a smart phone with a built-in GPS and map app. Some of us old timers might still use an old school paper map from time to time. But we didn't always used to lean so heavily on maps and technology, and in some remote places of the world some people still navigate and wayfind their way without the aid of these tools... and in some cases do better without them. This week, host Rachelle Saunders...
Now Playing: Radiolab

Dolly Parton's America: Neon Moss
Today on Radiolab, we're bringing you the fourth episode of Jad's special series, Dolly Parton's America. In this episode, Jad goes back up the mountain to visit Dolly's actual Tennessee mountain home, where she tells stories about her first trips out of the holler. Back on the mountaintop, standing under the rain by the Little Pigeon River, the trip triggers memories of Jad's first visit to his father's childhood home, and opens the gateway to dizzying stories of music and migration. Support Radiolab today at Radiolab.org/donate.