Dartmouth researchers and their colleagues have created an artificial intelligence software that uses photos to locate documents on the Internet with far greater accuracy than ever before.
The new system, which was tested on photos and is now being applied to videos, shows for the first time that a machine learning algorithm for image recognition and retrieval is accurate and efficient enough to improve large-scale document searches online. The system uses pixel data in images and potentially video – rather than just text — to locate documents. It learns to recognize the pixels associated with a search phrase by studying the results from text-based image search engines. The knowledge gleaned from those results can then be applied to other photos without tags or captions, making for more accurate document search results.
The findings appear in the journal PAMI (IEEE Transactions on Pattern Analysis and Machine Intelligence).
“Images abound on the Internet and our approach means they’ll no longer be ignored during document retrieval,” says Associate Professor Lorenzo Torresani, a co-author of the study. “Over the last 30 years, the Web has evolved from a small collection of mostly text documents to a modern, gigantic, fast-growing multimedia dataset, where nearly every page includes multiple pictures or videos. When a person looks at a Web page, she immediately gets the gist of it by looking at the pictures in it. Yet, surprisingly, all existing popular search engines, such as Google or Bing, strip away the information contained in the photos and use exclusively the text of Web pages to perform the document retrieval. Our study is the first to show that modern machine vision systems are accurate and efficient enough to make effective use of the information contained in image pixels to improve document search.”
The researchers designed and tested a machine vision system – a type of artificial intelligence that allows computers to learn without being explicitly programmed — that extracts semantic information from the pixels of photos in Web pages. This information is used to enrich the description of the HTML page used by search engines for document retrieval. The researchers tested their approach using more than 600 search queries on a database of 50 million Web pages. They selected the text-retrieval search engine with the best performance and modified it to make use of the additional semantic information extracted by their method from the pictures of the Web pages. They found that this produced a 30 percent improvement in precision over the original search engine purely based on text.
The Latest on: Image-recognition software
via Google News
The Latest on: Image-recognition software
- Risk-Based Monitoring Software Market SWOT Analysis by Growth Opportunities During 2020 to 2025on September 3, 2020 at 5:06 pm
A risk-based monitoring is used to feed data from study sites into a dashboard that alerts the sponsor to situations that need further investigation ...
- North American Contactless Biometrics Technology Market to 2026 - ResearchAndMarkets.comon September 2, 2020 at 7:18 am
The "North America Contactless Biometrics Technology Market By Component, By Application, By End User, By Country, Industry Analysis and Forecast, 2020 - 2026" report has been added to ...
- 7 data science certifications to boost your resume and salaryon August 28, 2020 at 1:03 pm
IBM, Google, SAS, and Oracle offer online courses and exams to quantify data science skills and expertise with modeling and analysis software.
- Hachi Infinite M1, the First-Ever AI-Powered Interactive Touchscreen Projector, Launches on Amazonon August 28, 2020 at 6:00 am
PRNewswire/ -- Hachi, the creators of cutting-edge robotics solutions that enable consumers to build AI-enhanced smart living ecosystems, has announced ...
- BMW Boosting AI While Factory Lines are Paused from Pandemicon August 26, 2020 at 7:11 am
Source: AI Trends Staff With the Covid-19 pandemic forcing its factories to close, BMW AG is taking the opportunity to accelerate deployment of AI in its factories. Matthias Schindler, head of AI ...
- Algorithms Are Automating Fascism. Here’s How We Fight Backon August 25, 2020 at 1:06 am
The most common critique of these algorithmic decision-making systems is that they are “unfair”—software-makers ... that “cloaks” faces from image recognition algorithms.
- Algorithms Are Automating Fascism. Here’s How We Fight Backon August 24, 2020 at 5:14 am
Bias” can’t be fixed with a software update. Only by disrupting oppressive systems on every level can we make a more just world.
- Image Recognition Market to Benefit from Applications in Security and Surveillanceon August 18, 2020 at 3:19 am
According to a report published by Fortune Business Insights™, titled, "Image Recognition Market Size, Share & Industry Analysis, By Component (Hardware, Software, Services), By Services ...
- Image Recognition Market to Benefit from Applications in Security and Surveillanceon August 18, 2020 at 2:38 am
According to a report published by Fortune Business Insights™, titled, “Image Recognition Market Size, Share & Industry Analysis, By Component (Hardware, Software, Services), By Services ...
- Image Recognition Market Volume, Revenue, PESTEL Analysis, CAGR and SWOT Study|Attrasoft Inc, NEC Corporation, Google Incon August 14, 2020 at 5:09 am
Global Image Recognition Market Research Report offers ... Segmentation on the basis of component: Hardware, Software, Service, Segmentation on the basis of application: Augmented Reality ...
via Bing News