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
[google_news title=”” keyword=”Image-recognition software” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Image-recognition software
- Nvidia releases software and services to boost rapid adoption of AIon July 29, 2024 at 5:44 pm
Nvidia inference microservices are software packages that take care of logistics needed to use AI. Read more at straitstimes.com.
- Nvidia releases software, services to boost rapid adoption of AIon July 29, 2024 at 2:02 pm
Nvidia Corp., the world’s most valuable chipmaker, announced a raft of updates to its software offerings that aim to make it easier for a wider variety of businesses to use generative artificial ...
- Why Facial Recognition at the Checkout is a Little Creepyon July 29, 2024 at 8:02 am
When convenience costs your privacy, the real question is, who truly benefits? Facial recognition to unlock your phone is one thing — but a little different when out in public.
- Image Recognition in Retail Market : Enhancing Shopping Experienceson July 28, 2024 at 5:00 pm
Key takeaways from the Image Recognition in Retail Market include the forecasted market size reaching approximately USD 17.5 billion by 2033, with a compound annual growth rate (CAGR) of 22.5%. As of ...
- Image processing articles from across Nature Portfolioon July 25, 2024 at 5:00 pm
Perera et al. developed a machine-learning approach for classifying whole-slide images into binary categories of tumour-infiltrating lymphocytes. They have benchmarked it against two established ...
- This Startup Wants to Be the Kayak.com of Movingon July 25, 2024 at 3:51 pm
WeMove.ai uses image recognition software and machine learning to help you book a move without ever talking to a salesperson. Lisa joined CNET after more than 20 years as a reporter and editor.
- This AI Startup Wants to Be the Kayak.com of Movingon July 25, 2024 at 3:51 pm
WeMove uses image recognition software and machine learning to help you book a move without ever talking to a salesperson. Lisa joined CNET after more than 20 years as a reporter and editor.
- Idemia forensic software extracts human faces, tattoos for investigative leadson July 23, 2024 at 4:01 am
Made for investigative agencies Face Expert is a web-based application built on the MBIS platform that extracts human faces and tattoos for investigative leads.
- Company’s Protest Stalls Georgia’s Recount-by-Software Planon July 22, 2024 at 1:09 pm
The idea was to triple-check this year’s presidential election results by uploading images of every ballot cast, scanning them with text-recognition software and creating an independent vote count.
- Selfie Spoofing: How hackers are duping facial recognition softwareon July 15, 2024 at 9:30 am
It turns out scammers can use our photos to bypass facial recognition software and hack into our accounts. It’s called "Selfie Spoofing." According to Leyla Bilge, the director of Scam Research Labs ...
via Bing News
