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
- New Software Shows Promise in Facial Recognition, Mask or Noton May 8, 2024 at 12:25 am
A recent development in the realm of facial recognition technology addresses the challenges posed by face masks during the COVID-19 pandemic, promising to recognize the face despite the mask, as ...
- New software trained on photographic database may allow facial recognition beneath the maskon May 7, 2024 at 12:32 pm
Research published in the International Journal of Computational Vision and Robotics discusses the potential of new software that might be ... mask has been superimposed on the image, to allow facial ...
- The next chapter in air travel: facial recognition and privacy concernson May 7, 2024 at 4:41 am
Facial recognition come with risks and privacy concerns, but industry experts say that the concerns will be addressed.
- How Facial Recognition Changes Dynamics of Campus Protestson May 2, 2024 at 2:39 pm
Video surveillance for security reasons is fairly common on college campuses, but as law enforcement increasingly uses facial recognition to identify suspects, protestors worry they could be targeted ...
- Police Say a Simple Warning Will Prevent Face Recognition Wrongful Arrests. That's Just Not True.on April 30, 2024 at 11:47 am
Even when police heed warnings to take additional investigative steps, they exacerbate the unreliability of face recognition results.
- Image Recognition in Retail Market CAGR of 21.80%, Maximizing the Value of Secondary Data Strategies for Effective Researchon April 25, 2024 at 10:54 pm
report_id=bw1357 Image Recognition in Retail Market is valued approximately at USD 1.14 billion in 2019 and is anticipated to grow with a healthy growth rate of more than 21.80% over the forecast ...
- IUG announces new software launchon April 22, 2024 at 12:01 am
SonoLystlive enhances ultrasound image recognition by automatically capturing images in real-time, as the clinician scans a mid-trimester patient. The AI software, using practice guidelines from the ...
- Global Image Recognition Market Insights and Outlook to 2029: QR/Barcode Recognition to Dominate in 2024on April 17, 2024 at 9:01 pm
Dublin, April 18, 2024 (GLOBE NEWSWIRE) -- The "Global Image Recognition Market by Offering (Hardware, Software, Services), Technology (QR/barcode, Digital Image Processing, Facial Recognition ...
- How Facial Recognition Technology Workson April 16, 2024 at 5:01 pm
After a customer consents, the ATM or check-cashing kiosk captures a digital image of him. The software then generates a faceprint of the photograph to protect customers against identity theft and ...
- How Generative AI is Improving Information Retrieval for Engineerson April 11, 2024 at 5:00 pm
Instead of simply returning products that match a specific user search query, AI-driven search relies on image recognition to infer the technical context of an application photo and then recommend ...
via Bing News