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
- German Prosecutors Are Building AI In-Houseon February 26, 2021 at 2:30 am
European prosecutors and police are constructing their own image-recognition systems so they can explain in court how the algorithms work and meet strict privacy standards.
- DeepCube Unveils Deep Learning Suiteon February 25, 2021 at 2:17 am
DeepCube is launching a new suite of products and services including its first software-based deep learning accelerator based on current and future AMD ...
- Insilico Medicine discovers novel preclinical candidate to address idiopathic pulmonary fibrosison February 24, 2021 at 10:08 pm
Insilico Medicine has demonstrated a breakthrough in Artificial Intelligence ("AI") and drug discovery -- linking together generative chemistry and biology for the first time -- to discover a novel ...
- Image Recognition Market Movements by Trend Analysis, Growth Status and Revenue Expectation Forecast to 2028, Fortune Business Insightson February 24, 2021 at 9:30 pm
According to the report, the global image recognition market size is projected to reach USD 81.88 billion by 2026.
- Pushing computing to the edge by rethinking microchips' designon February 24, 2021 at 9:25 am
Responding to artificial intelligence's exploding demands on computer networks, Princeton University researchers in recent years have radically increased the speed and slashed the energy use of ...
- Insilico Medicine achieves industry first nominating preclinical candidate discovered by AIon February 24, 2021 at 8:57 am
Insilico Medicine Achieves Industry First Nominating Preclinical Candidate for Idiopathic Pulmonary Fibrosis With Both Novel Drug Target and Novel Molecule Discovered by Artificial Intelligence ...
- Image Recognition Market 2021 Industry Size, Business Opportunities, Top Key Players, and Global Analysis by Forecast to 2027on February 24, 2021 at 1:17 am
The global“Image Recognition Market Size”is expected to rise with an impressive CAGR and generate the highest revenue ...
- A practical guide on AI & the Cloud for Insurers & InsurTechs to growon February 22, 2021 at 4:00 pm
Artificial intelligence (AI) and the Cloud are two pinnacles driving innovative thinking and strategic implementations within today’s technology-led environment. As highlighted in my recent article ...
- The Worldwide Edge AI Software Industry is Expected to Reach $1.8+ Billion by 2026 - ResearchAndMarkets.comon February 22, 2021 at 2:41 am
The global edge AI software market size to grow from USD 590 million in 2020 to USD 1,835 million by 2026, at a Compound Annual Growth Rate (CAGR) of 20.8% during the forecast period. We sift through ...
- AR SDK Software Market to Witness Massive Growth by Blippar, Zappar, Kudanon February 19, 2021 at 12:43 pm
Stay up-to-date and exploit latest trends of AR SDK Software Market with latest edition released by AMA. AR SDK Software Market Comprehensive Study is an expert and top to bottom investigation on the ...
via Bing News