Do you wish there was a way to search the internet for all your images simultaneously? PimEyes does exactly that. Pimeyes is an AI-powered face recognition search engine that can discover images of a specific face on the web. Faces, rather than photos, are the primary focus of this reverse image search tool, making it stand out from the competition. Both those looking for lost images and those concerned about remaining anonymous online can benefit from this tool.

Your PimEyes subscription also gives you access to all websites where a matched image was located. If the image is being used without your consent, you will be able to track it down and demand that it be taken down.

What is PimEyes?

PimEyes is a facial recognition and reverse image search tool that lets you look for online images of a specific person by uploading a photo of them. In order to do a reverse image search, PimEyes use facial recognition technology.

PimEyes offers a facial recognition tool that can be very effective and accurate. Anyone can try out the service by uploading an image of a face into its search engine. Once a photo has been uploaded, it only takes seconds for the search engine to perform its hunt of the vast internet and return its results. The free search only scratches the surface, as you will have to subscribe to a monthly package if you want a more in-depth search.

Facial recognition accuracy

When using a facial recognition tool like PimEyes, one of the most critical factors to consider is facial recognition accuracy. The accuracy of results can depend on several variables, including the quality of the uploaded image and the scope of the dataset the tool searches. While PimEyes claims to offer high precision in its results, users should be aware that face search accuracy can be impacted by factors such as outdated or low-resolution photos, leading to false positives or incomplete results. Understanding these limitations is crucial, as it can help users gauge whether they need to opt for a more thorough, paid search to achieve better results.

Reverse image search for social media

Many users rely on PimEyes for reverse image search on social media platforms like Facebook, Instagram, and LinkedIn. This feature enables individuals to locate photos that may have been shared publicly or, in some cases, stolen and repurposed without consent. PimEyes’ ability to scan across multiple platforms makes it particularly valuable for those looking to safeguard their online identity and ensure their images aren’t being misused.

Facial recognition tools can be used for a variety of purposes. One of the intended purposes is for users to be able to search the internet for images of themselves. In general, the features that PimEyes offers to you are as follows:

• Face search
• Finding the source of your image
• Exclude the image from public results

However, it could be used for more sinister purposes such as stalking someone.

There is an option to prevent your photographs from being indexed by the service. PimEyes notes that because of the complexity of the AI used, some images may be missed and remain concealed. You can submit a form to have images removed from search results if you discover they are still available.

As for January 19, 2023 #PimEyes’ PROtect team has successfully taken down 32924 images, illegally published on the open web. 💪
We would like to thank #PROtect team for hard work and dedication. ❤️‍🔥
Inspired with this success we made decision to expand our non-profit activity 💪

— PimEyes (@PimEyesOfficial) January 19, 2023

Let’s test it and learn how to use PimEyes.

Check out how to use GPT-4 and learn ChatGPT’s new features

How to use PimEyes?

It’s quite easy. It doesn’t take more than a few seconds to conduct a search. After uploading a photo of a face and checking a box to indicate your acceptance of the terms of service, you are presented with a grid of photos of other, similarly-appearing faces, along with clickable links to their respective online locations. If you are wondering how to use it step by step:

• Visit PimEyes
• Upload a photo and start the search

• Find yourself among the results
• Click an image and take action

Are the results successful? Only 1 of 17 results belonged to me. I took this photo 8 years ago, and it is only on Facebook right now. It would be wrong to say that PimEyes worked very well for me when compared to the results of others.

The site is called Pimeyes.

They use AI for facial recognition combined with reverse image search.

I tested it myself and was shocked by the speed and accuracy. Super creepy. pic.twitter.com/u3vE9gCO7R

— Rowan Cheung (@rowancheung) February 28, 2023

The more you have an online presence, the more efficient PimEyes can provide you. However, I would expect PimEyes also find the profile photo I used for this site.

Reminder: No publicly available image search or face recognition software can guarantee a 100% success rate.

@seansvv

#stitch with @chrisjr404 How to correctly Opt-Out of #pimeyes #optout #howto #infosec #edutok #techtok

♬ original sound – SEAN

For detailed information about how to use it, click here.

Fortunately, there is a free trial option. But what if you run out of 3 free searches?

PimEyes pricing plans

PimEyes has 3 different pricing plans:

• Open Plus – $35.39/ mo
• PROtect – $47.19/ mo
• Advanced – $353.99/ mo

PimEyes reverse image search

When it comes to reverse image search, PimEyes stands out as a powerful tool for tracking down photos online. The PimEyes image search functionality allows users to upload a photo of a face and find visually similar images across the web. Unlike other image search engines, PimEyes is specifically designed to focus on facial recognition, making it ideal for users who are trying to locate personal images or verify where their likeness has appeared online. If you’re searching for a way to protect your privacy or simply find out where your photos are being used, PimEyes image search offers an effective solution.

However, if you’re looking for a cost-free option, there are free PimEyes alternatives available that offer similar services, though they may lack some of the advanced features that PimEyes provides. Still, these tools can be helpful for those wanting to explore facial recognition technology without committing to a paid service. Regardless of which route you take, understanding the balance between facial recognition privacy and utility is essential when using these tools.

PimEyes alternatives (Free & Paid)

These are some of the face recognition tools that you can try:

EagleEye

EagleEye is an open-source tool designed for ethical hacking and research purposes. It specializes in image search and facial recognition across various social media platforms and websites. While it requires some technical knowledge to set up, it’s a powerful tool for tracking images and finding matches.

Clearview AI

Clearview AI is a controversial yet highly effective facial recognition tool used by law enforcement agencies. It boasts a massive database of images scraped from public websites and social media platforms, making it one of the most comprehensive tools available. However, its use is heavily regulated due to privacy concerns.

TinEye

TinEye is a reverse image search engine that allows users to track where images appear online. It’s particularly useful for finding modified or cropped versions of an image, but it doesn’t specialize in facial recognition. TinEye offers both free and premium versions, with the paid version providing more robust search capabilities.

Google Reverse Image Search

Google Reverse Image Search allows users to upload an image or paste an image URL to find visually similar images across the web. While not specifically designed for facial recognition, it’s useful for identifying images or tracking where a face might have appeared online.

Pinterest Image Search/Lens

Pinterest Image Search/Lens is a visual search tool integrated within the Pinterest app. Users can upload an image, and Pinterest will search for similar visuals or ideas. While primarily used for fashion or decor inspiration, it can also be helpful for finding where a person’s image might have been shared across the platform.

Bing Visual Search

Bing Visual Search functions similarly to Google’s reverse image search but is integrated into Microsoft’s Bing search engine. It’s a free service that allows users to upload images and search for similar visuals online. While not as robust as facial recognition tools, it’s still useful for basic image tracking.

NTech Lab

NTech Lab is a powerful facial recognition platform that specializes in high-speed, accurate recognition across large datasets. It’s often used in security, retail, and urban surveillance applications. This tool is known for its ability to track individuals in real-time across public and private spaces.

FaceCheck.ID

FaceCheck.ID offers facial recognition software specifically designed for online investigations, security, and identity verification. It can search social media, news articles, and criminal databases to track down the online presence of a person based on their facial image.

Betaface

Betaface provides facial recognition and analysis services. It’s commonly used for tagging, categorizing, and analyzing faces in images. Users can try the free version, but the paid version includes more advanced features, like facial attribute extraction and custom face databases.

Face++

Face++ is a facial recognition and image analysis service that’s widely used by developers for AI applications. It offers a range of features, including face detection, landmark recognition, and facial expression analysis. While primarily a tool for developers, it’s a strong contender in the facial recognition space.

What is face recognition?

A facial recognition system is a technology capable of matching a human face from a digital image or a video frame against a database of faces. Such a system is typically employed to authenticate users through ID verification services, and works by pinpointing and measuring facial features from a given image.

AI 101

Are you new to AI? You can still get on the AI train! We have created a detailed AI glossary for the most commonly used artificial intelligence terms and explain the basics of artificial intelligence as well as the risks and benefits of AI. Feel free the use them.

Other AI tools we have reviewed

Almost every day, a new tool, model, or feature pops up and changes our lives, like Bing AI mobile, and we have already reviewed some of the best ones:

• Text-to-text AI tools
  • Google Bard AI 
  • Chinchilla
  • Notion AI
  • Chai
  • NovelAI
  • Caktus AI
  • AI Dungeon
  • ChatGPT
  • Snapchat My AI

Do you want to learn how to use ChatGPT effectively? We have some tips and tricks for you without switching to ChatGPT Plus! AI prompt engineering is the key to limitless worlds, but you should be careful; when you want to use the AI tool, you can get errors like “ChatGPT is at capacity right now” and “too many requests in 1-hour try again later”. Yes, they are really annoying errors, but don’t worry; we know how to fix them.

• Text-to-image AI tools
  • MyHeritage AI Time Machine
  • Reface app
  • Dawn AI
  • Lensa AI
  • Meitu AI Art
  • Stable Diffusion
  • DALL-E 2
  • Google Muse AI
  • Artbreeder AI
  • Midjourney
  • DreamBooth AI
  • Wombo Dream
  • Tome AI
  • Interior AI
  • NightCafe AI
  • QQ Different Dimension Me
  • Random face generators

While there are still some debates about artificial intelligence-generated images, people are still looking for the best AI art generators. Will AI replace designers? Keep reading and find out.

• Other AI tools
  • Poised AI
  • Make-A-Video
  • Uberduck AI
  • MOVIO AI
  • Nvidia Eye Contact AI
  • Tome AI
  • Spotify AI DJ

It almost goes without saying that Tinder has taken the dating world by storm. Stats released late last year revealed that Tinder’s 50-million-strong userbase complete over a billion left and right swipes every single day. The success has often been attributed to the fact that Tinder is the closest virtual simulation of the bar experience; you see an attractive person across the bar, and in the that moment- having only seen them, and knowing precious little about them other than the way they look (and maybe their tipple of choice), you decide whether or not to make your approach. It’s virtual speed dating, where every encounter can end in the few moments it takes for you to swipe left or right without your potential partner ever even knowing.

However, another stat released by Tinder exposes that the average user spends 90 minutes a day swiping and reviewing their matches. That is a huge investment in terms of time and effort, without any guarantee you’ll end up matched with anyone.

Objectively the best Tinder profile of all time. 

For Justin Long, a Canadian entrepreneur & Chief of Research for a disruptive technology company, this was the biggest turn-off on Tinder. “Tinder has reached critical mass; I feel it’s been adopted by relatable people and the right variety of women. I became aware of how enjoyable it was to keep matching and swiping for the next match; however, I was dissatisfied with how much time I had to invest in it. Swiping is both Tinder’s best and worst feature.”

His solution? Automate the entire process. Of course, bots have already been created by other Tinder users which swipe right (accept) all possible matches. Whilst inventive, these bots don’t take into account personal preference, or get rid of spammers. Long had something a little more sophisticated in mind- a bot which learns your physical “type” using the Eigenfaces facial recognition algorithm, and automatically got the conversation going with your matches.

The code, dubbed Tinderbox, requires you to make 60 “swipes”- then, the model has enough data to understand your preferences and make auto-pilot matches on your behalf. Long’s blogpost outlines the workflow on the backend like so:

The built-in bot builds facial models using your likes/dislikes
Bot examines profile images, cropping faces
Faces are loaded into an “average” face representing choices
Eigenfaces are computed from average faces
Bot then makes future selections based on Eigenface comparison
Comparisons are essentially k-nearest neighbor selection

The bot first extracts the faces using the Viola-Jones framework, and converts them to greyscale. Photos containing more than one identifiable face are filtered out, to avoid false positives. The pictures are then normalised, and the pixels are converted into a matrix, and used to create single, “average” faces for your “Yes” and “No” swipes for Eigenface comparison. The average face representations look a little something like this:

Implementing the algorithm and trying to find the best matrix library proved to be the trickiest part. “There’s more than one way to bake a cake,” Long says, “and finding the right recipe was difficult.” For those of you interested in the code, here’s a snippet that computes the Eigenfaces matrix using a pixel matrix of multiple images:

[code language=”Python”]/**
* Computes the EigenFaces matrix using a pixel matrix of multiple images.
* @param pixelMatrix
* @param meanColumn
*/
def computeEigenFaces(pixelMatrix: Array[Array[Double]], meanColumn: Array[Double]): DoubleMatrix2D = {
val diffMatrix = MatrixHelpers.computeDifferenceMatrixPixels(pixelMatrix, meanColumn)
val covarianceMatrix = MatrixHelpers.computeCovarianceMatrix(pixelMatrix, diffMatrix)
val eigenVectors = MatrixHelpers.computeEigenVectors(covarianceMatrix)
computeEigenFaces(eigenVectors, diffMatrix)
}

/**
* Computes the EigenFaces matrix for a dataset of Eigenvectors and a diff matrix.
* @param eigenVectors
* @param diffMatrix
*/
def computeEigenFaces(eigenVectors: DoubleMatrix2D, diffMatrix: Array[Array[Double]]): DoubleMatrix2D = {
val pixelCount = diffMatrix.length
val imageCount = eigenVectors.columns()
val rank = eigenVectors.rows()
val eigenFaces = Array.ofDim[Double](pixelCount, rank)

(0 to (rank-1)).foreach { i =>
var sumSquare = 0.0
(0 to (pixelCount-1)).foreach { j =>
(0 to (imageCount-1)).foreach { k =>
eigenFaces(j)(i) += diffMatrix(j)(k) * eigenVectors.get(i,k)
}
sumSquare += eigenFaces(j)(i) * eigenFaces(j)(i)
}
var norm = Math.sqrt(sumSquare)
(0 to (pixelCount-1)).foreach { j =>
eigenFaces(j)(i) /= norm
}
}
val eigenFacesMatrix = new DenseDoubleMatrix2D(pixelCount, rank)
eigenFacesMatrix.assign(eigenFaces)
} [/code]

And computing the distance between two images:

[code language=”Python”] /**
* Computes the distance between two images.
* @param pixels1
* @param pixels2
*/
private def computeImageDistance(pixels1: Array[Double], pixels2: Array[Double]): Double = {
var distance = 0.0
val pixelCount = pixels1.length
(0 to (pixelCount-1)).foreach { i =>
var diff = pixels1(i) – pixels2(i)
distance += diff * diff
}
Math.sqrt(distance / pixelCount)
} [/code]

So Long’s bot is now able to automate all of the swiping. But what about all of those matches that clutter up your notifications, where the person you’ve matched to never replies? Long wanted to go one step further, and identify only the women who genuinely wanted to strike up a conversation. For this, he programmed the bot to start conversations, and use StanfordNLP to analyse the sentiment of responses. “I’ll admit that StanfordNLP’s approach isn’t the best for examining sentiment,” Long confessed. “This is because it tries to analyze the message by its structure and not necessarily by its content. Sarcasm can register as negative (and humor is actually an expression of positive sentiment). Additionally, messages classified as neutral could still be positive – this is because in the bigger picture any message at all still indicates interest. If I were to do this again I would be much more comprehensive.”

If the sentiment was deemed positive, the bot sends out pre-programmed replies. Once three replies have been given, the user receives a conversation that their match is genuinely interested and the conversation is ready to enter. The process looks a little something like this:

Getting the bot up and running didn’t go without a hitch. In terms of technical snags, “The bug where all of my matches were repeatedly messaged tops the cake”, he said. “I had just revised the messaging system and when I went to test it, the bot just harassed all of my chats with constant openers. I think I got a couple spam reports from that. No long-term damage though!”

Still, within 3 weeks, the bot was up and running, and Long was presented with a list of matches who were genuinely interested in speaking with him. But did this actually improve his Tinder experience? Famously, Chris McKinlay spent months using K-modes to hack OkCupid, only to end up on a string of disappointing dates- and then met his future wife when she messaged him out of the blue.

Long’s strategy, I’m happy to report, seems to be more effective. “I made a huge mistake here by not keeping track of my before/after data, so most of my feedback is anecdotal,” he says. “I discovered two huge improvements: 1) massive increase in personal time, and 2) I had a large increase in the quality of my matches. People that I not only found more attractive, but also were better conversationalists.”

He also set up a new account, to see how it would perform with a fresh dataset in 48 hours. In that short time frame, the bot made over 300 “moves” (swipes and messages), established 21 matches, and sparked 4 extended conversations. All this is two days, requiring just 60 swipes from the user.

Of course, the point of TinderBox is not to find love- or whatever else you happen to be looking for. It’s supposed to filter out the hours of wading through incompatible matches, and starting conversations which never get a response. What happens from there is up to you; it’s safe to say that Long made the most it. Speaking about his post-bot dates, he told us “I probably made someone’s night running around the beach in our socks and kissing in the rain. I also came up with one of my best date ideas: bake some cookies, show up at the nearest firehouse, bribe firemen with said cookies, and take a tour.”

His blogpost intimates he’s now turned off the bot. “Admittedly, it worked too well and started to conflict with work. Although in a couple cases I had follow-ups and I’m still seeing one person.”

For those of you curious about TinderBox, Long has uploaded the code to Github for “personal use”. We asked Long how he’d react if he went on a date with a girl who’d used the TinderBox code to set up the match. “I’d be totally shocked because I actually tried using the bot with a female friend previously, and it freaked her out. So she’s either got some balls to be turning over her Tinder account to the bot, or she’s super smart to modify the code and make it work for her. Either way, those are people I want to know.”

Follow @DataconomyMedia

(Image credit: Unsplash)

Face++, a Beijing-based startup who provide face recognition technology on the cloud, recently bagged $22 million worth of series B funding from Quiming Ventures and Series A investor Innovation Works. The round reportedly values the company at $100 million and was raised from Legend Star, the incubation program under Lenovo.

The face recognition technology Face++ is a new vision platform built by Megvii Inc. Aiming at providing compact, powerful, and cross-platform vision service. Face++ uses the cutting-edge technology of computer vision and data mining to provide 3 core vision services (Detection, Recognition, and Analysis). With the service and huge database of celebrities from Face++, the developers can apply the face technology into their own websites, mobile Apps, and smart TVs, enhancing the user experience.

Face++ services have basic and enterprise versions. Basic Face++ service is API-based. Enterprise version has a much better accuracy and system performance. In addition, offline SDK and customized cloud service are available for enterprise partners. Their SDK packages cover comprehensive platforms (including ios, Android, Linux, and Windows). Their enterprise partners include Lenovo, 360, Meitu and Camera360.

The startup plans to increase the commercial application of its face recognition technology with the new funding, mainly from two perspectives.

1) Application in Financial Services: Financial services now have the option to use facial biometric data as a security feature, making the security of their customer’s accounts watertight.Face++ has already announced a partnership with Ant Financial, (Alibaba’s finance branch, responsible for Alipay) in this sector, as well as several commercial banks.

2) Camera data + IFTTT model: By fusing together camera data and the IFTTT service, businesses can set the technology to execute certain pre-defined functions when the cameras register a certain client. In retail for example, the camera would be able to alert staff about the arrival of a VIP client, who could then tailor and customise services accordingly.

Sources state that the face recognition tech is integrated into more than 14,000 apps, covering over 40 million mobile devices per month.

Read more here.

Follow @DataconomyMedia

(Image credit: Face++)