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
- Facial Recognition Market size worth $ 10.2 Billion, Globally, by 2028 at 15.92% CAGR: Verified Market Research®on October 14, 2021 at 7:15 am
Verified Market Research recently published a report, "Facial Recognition Market" By Software (2D Facial Recognition, 3D Facial ...
- 7-Eleven told to delete customers’ photos after facial recognition software falls under privacy commissioner’s scopeon October 14, 2021 at 2:09 am
The privacy watchdog has taken aim at 7-Eleven after the convenience store chain rolled out facial recognition software in its Australian stores.
- Burj Khalifa’s Peace of Mind: ANPR Access Control System by Adaptive Recognitionon October 14, 2021 at 1:53 am
In a city of almost 16 million yearly visitors, security is of utmost importance. One pillar of Dubai’s peace of mind is the way safety & security of local residents/visitors is ensured.
- OAIC finds against 7-Eleven over facial recognition usageon October 14, 2021 at 1:15 am
OAIC: The convenience store group interfered with customers' privacy by collecting sensitive biometric information that was without necessity or reasonable consent. Between June 2020 and August 2021, ...
- Emotion Detection and Recognition Markets by Solution, Application, Technology, & End-User - Global Forecast to 2027 - ResearchAndMarkets.comon October 7, 2021 at 7:44 am
The “Emotion Detection and Recognition Market 2021-2027” report has been added to ResearchAndMarkets.com’s offering. The Emotion Detection and Recognition Market is anticipated to grow at the rate of ...
- North America Facial Recognition Market Covid-19 Impact In-Depth Industry Analysis 2028on October 6, 2021 at 8:40 am
According To Market Research, The North American Facial Recognition Market Is Anticipated To Rise With A Cagr Of 8.29% In The Estimated Years 2019-2028. The United States And Canada Together Shape The ...
- Uber is facing legal action for facial recognition ID checks that are racially biasedon October 6, 2021 at 7:56 am
In a legal test case, an Uber driver who lost his job when automatic face-scanning software failed to recognize him accuses the company of indirect race discrimination ...
- Augmented Reality SDK Software Market to Witness Huge Growth by 2026: Google, Zappar, Kudanon October 5, 2021 at 10:06 am
Stay up-to-date and exploit latest trends of Augmented Reality SDK Software Market with latest edition released by AMA.
- Image Recognition Market Analysis, Growth, Trends, Forecast by 2024 – TMRon October 5, 2021 at 5:22 am
The presence of companies such as Google, Twitter, Facebook, International Business Machines (IBM) Corporation, Apple, etc., which are spearheading the global image recognition market, naturally makes ...
- Image Recognition Market size worth $ 115.56 Billion, Globally, by 2028 at 18.25% CAGR: Verified Market Research®on October 4, 2021 at 6:15 am
Verified Market Research recently published a report, "Image Recognition Market" By Technology (Object Recognition, Facial Recognition, ...
via Bing News