A program for finding faces from photographs. FindFace – photo dating service

In this material I will tell you how to search by photo on social networks, and what we need for this. Imagine a situation: you have a photo of a person about whom you need to find everything available information. Social networks, which often contain accounts of the people we need, can provide invaluable assistance in the process of such a search. They may contain a variety of information about a person, including his photos and videos, interests, hobbies, favorite books and films, and other data useful to us. But how can you find such a page with just a photo?

Search the right person on social networks you can different ways(by first and last name, place of residence, geotags, age, and other relevant descriptors). If you already have a photo of him, then you can turn to the possibilities of special network tools, capable of providing significant assistance in our searches.

Some of these resources (for example, the popular “FindFace”) are specially “tailored” for searching for people in specific network(in the case of “FindFace” this is the Russian “VK”). Others, level search engines Google and Yandex allow you to search for identical and similar images on a variety of sites (including social networks), displaying all the richness of the results obtained.

In some cases it is necessary to prepare the desired photo to search for it (for example, using a template graphic editor" "). It is necessary to get rid of the presence of other people in the photo (if any), as well as remove other unnecessary details that could interfere with the search service in its work.

Let's look at ways to search for a person by their face image on social networks.

“FindFace” - effective photo search using neural networks

In November 2015, the University of Washington organized the “The MegaFace Benchmark” competition, in which more than a hundred teams took part, including from Google and Facebook. The goal of the competition is to create the most efficient algorithm for face recognition, allowing you to accurately select a similar face among many analogues.

Despite strong competition, the competition was won Russian company"N-Tech.Lab". Its algorithm, based on the work neural networks, provided the highest recognition accuracy among analogues - about 75% of all results obtained.

  • Later, this algorithm was embodied in the findface.ru service, which allows you to find the right person (or people similar to him) in social network"In contact with".
  • At the same time, a mobile application of the same name is also available to Android OS users.

The “findface” service will allow you to quickly find the right person on VK

How to use Fifindface search

How does this service work? To work with it, first of all you need to have a page on VK (if you don’t have one, create one). Then do the following:

  1. Go to findface.ru;
  2. Click on the red “Find identical” button;
  3. Allow the service to access your account by clicking on “Allow”;
  4. Upload the photo you need to search and wait for the search procedure to complete;
  5. Review your results.

The free capabilities of the service are limited to a certain number of searches on the social network (usually several dozen). For unlimited possibilities, you will have to pay the developers.

“Google Images” – with the ability to find a person by photo

The capabilities of the popular international search engine “Google” allow you to search by image online, including searching by photo of a person on social networks. In this case, the search engine displays both identical and similar results, with information on the found image (including the probable first and last name of the person in the photo).

To work with the service from Google, do the following:


"Yandex.Pictures" - will find anyone on a social network based on a face picture

Image search on social networks from the Yandex service is organized in a manner similar to Google. To search, go to “Yandex.Pictures" or use to launch the service, click on the camera image on the right, download the desired picture to the resource (or provide a link to it on the Internet). Review your results.

You can also use a special Yandex tool that searches for people on social networks. Follow this link https://yandex.ru/people, enter in search bar first and last name of the desired person, click on “Find” and view the result (usually a photo, link to social profile, short information).

To search, go to “Yandex.Images” and click on the camera icon on the right

Alternative resources for searching people by image

Among other services that search for images on social media. networks, I would also note the following resources:


Conclusion

Search by photo on social media networks will help you perform the services I listed above. Among the services mentioned, I recommend Special attention to the findface.ru service - its recognition efficiency is quite high level, allowing you to quickly find the pages of the people you need on VK.

In contact with

Find Face- This interesting service, which helps to find similar people in social networks. Working with the program is very simple - just upload a photo of the person for whom you want to find “doubles”, press the “Search” button and wait until the neural network is applied to users of the social networks VKontakte and Odnoklassniki with a similar appearance. It is important to note that to work with the service you must first authorize using account in one of the two above-mentioned “social networks”.

Advantages

The main advantage of Find Face is its fairly accurate search algorithms. The program really finds very similar people. Moreover, they are similar both in general and in individual facial features. Other interesting feature service - the ability to highlight the desired person in a group photo. That is, if you upload a photo in which there are several people posing at once, Find Face will recognize their faces and allow you to point to the desired one with the mouse cursor. Simultaneously search for “doubles” for several people service, at the time of writing this review, does not allow. Photos accepted for uploading are: PNG formats and JPG "weight" up to 5 MB.

After receiving search results with pages of similar users, you can filter them by age, city of residence (specified in the profile) and status. Last option It will be useful for those people who are trying to find a soul mate similar to themselves.

The service is completely free and works directly in the browser, that is, it does not require installing a desktop client.

Flaws

Each new Find Face user is provided with 50 checks. In order to increase their number, you need to invite friends using a referral link. Another annoying limitation is that you can only get links to people's profiles from search results if you set mobile app service on your smartphone or tablet.

Key Features

  • search for similar people using an uploaded photo;
  • 50 free checks all new users;
  • work directly in a web browser, without the need to download and install the program into the computer’s memory;
  • sorting search results by city, age and marital status;
  • authorization through accounts on the social networks Odnoklassniki and Vkontakte.

Represents computer application, capable of identifying or verifying a person from digital image or video clip. One way to do this is to compare selected facial features with an image and options from a database.

Facial recognition (software) is commonly used in security systems, and can be compared to other biometric systems (eg fingerprint or eye recognition). IN Lately it has also become popular as a commercial identification and advertising tool.

Some facial recognition algorithms identify facial features by extracting landmarks or objects from an image of the subject's face. For example, the algorithm may analyze the relative position, size and/or shape of the eyes, nose, cheekbones and jaw. This data is then used to find other images with matching parameters. Other algorithms normalize a gallery of facial images and then compress the facial information, retaining only the data in the image that is useful for facial recognition. The searched image is then compared with the available data. One of the earliest successful systems is based on pattern matching techniques applied to a set characteristic features faces, providing a sort of condensed view of appearance.

How does facial recognition software work?

It includes certain algorithms that can be divided into two main approaches:

  • Geometric, which considers the distinctive or photometric features of the face.
  • Statistical, which translates an image into values ​​and compares them to patterns to eliminate variances.

3D recognition

A new trend created to achieve more high precision, is a three-dimensional facial recognition. This method uses 3D sensors to collect information about the shape of the face. This information is then used to identify distinctive features such as the outline of the eye sockets, nose and chin.

One of the advantages of 3D facial recognition programs is that they are not affected by changes in lighting, unlike other options. This technology can also identify from a different range of viewing angles, including profile views. 3D data points significantly improve facial recognition accuracy. 3D research is being enhanced by the development of sophisticated sensors that improve the performance of 3D image capture. The sensors work by projecting structured light onto the face. Up to a dozen or more of these image sensors can be placed on a single CMOS chip - each capturing a different part of the spectrum.

However, even a perfect 3D matching method can be sensitive to facial expressions. For this purpose, a team of researchers at Technion applied tools from metric geometry to treat expressions as isometries. Vision Access then created its 3D facial recognition solution. The company was later acquired by Bioscrypt Inc., which developed a version of human facial recognition software known as 3D FastPass.

The new method is to introduce a way to capture 3D images using three tracking cameras that point at different angles. One of them will point to the front side of the object, the second - from the side, the third - at an angle. They will all work together to be able to track the subject's face in real time and be able to identify it. It is believed that any program for facial recognition through a camera will soon be based on this technology.

Skin Texture Analysis

Another new trend uses visual skin detail that is captured in standard digital or scanned images. This technique, called skin texture analysis, turns the unique lines, patterns and spots visible in a person's skin into a mathematical space.

Tests have shown that with the addition of this technology, facial recognition efficiency can increase by 20-25%.

Thermal chambers

Another form of receiving facial recognition input is through the use of thermal imaging cameras. Thanks to this procedure, cameras will only detect the shape of the head, and will ignore objects such as glasses, hats or makeup. The problem with using thermal images for facial recognition is that the databases for it are limited.

Researchers are currently studying the use of this technology in real life and operational landscapes and at the same time create new base thermal imaging data. The study uses low-sensitivity ferroelectric electrical sensors low resolution, which are capable of obtaining long-wave thermal infrared (LWIR) images. The results show that fusion of LWIR and conventional imaging cameras has great results in outdoor probes. This combination can work very well powerful program face recognition for the camera.

Mass use

While researchers are working on the latest technologies, available only to specialists, developers mass applications They also don’t stand still. After it was announced creation of Google Glass, there has been a lot of buzz around facial recognition and programs for this on the Internet. It is believed that this will open up a lot of opportunities for users not only to interact with each other, but also with various objects.

Today there is a large list of facial recognition interfaces available that you can use for your applications. The most common are the following.

Face Recognition Stephen

A development from Lambda Labs, which provides facial recognition based on the location of the eyes, the shape of the nose and mouth, and also carries out gender classification. Available on the developer's official website.

Face Detection

An online facial recognition computer program that is an ideal replacement for Face.com. Currently available free of charge.

Animetrics Face Recognition

The Animetrics Face Recognition API can be used to detect faces in photos. Information about facial features or landmarks is returned as coordinates in the image.

Skybiometry

To use it, you must have an application created in your SkyBiometry account. To create it, a simple registration is enough.

Face++

This application uses advanced technology and to provide 3 main services (detection, recognition and analysis). The program provides detection and analysis of Landmark (23 points), landmark (81 points), attributes: age, gender, glasses, race and so on.

FaceMark

It is a powerful facial recognition API. It finds 68 landmark points for the frontal face image and 35 for the profile one. FaceMark detects facial landmarks in an image specified by a URL or in an uploaded file, and produces the result as a JSON file containing a vector of facial landmarks and match points for each match found.

EmoVu by Eyeris

Intellectual software for emotion recognition, which allows cameras to read human micro-expressions, gender and age group. It is a real-time facial recognition program that works when users watch videos on their computers or mobile devices.

Rekognition.com

This is one of the best alternatives Face.com. The fast, reliable and scalable rekognition engine can perform face detection, scanning, recognition and search. It can be automatically trained using images and tags on Facebook. Since it is social media oriented, it is best program facial recognition for Android.

FaceRect

It is also powerful and free interface for face detection. It finds faces (both frontal and profile) in an image specified by URL or uploaded as a file, and can find multiple faces in a single photo, and outputs a response in JSON format. This loads the image with a bounding box for each face found.

Sometimes it happens that you only have a photograph of a person and you don’t know anything else about him. Let's say you need to identify him to check whether he actually witnessed the events or worked in a certain place. on the Internet will allow you to find a person if you know at least something about him. What if you only have a photograph? In this case, photo recognition and people search services will come to the rescue. Such online tools can “find out” who is shown in photographs. In some cases, the service will directly answer your question, indicating the first and last name of the person in the photo. But such an answer can not always be obtained. But find similar pictures or even the exact profile on a social network modern instruments recognition is quite capable.

In some cases, facial recognition helps to identify people on group photo, compare two faces.

Some search engines allow you to find similar faces, and some - to recognize the celebrities depicted in the photo.

Pictriev is search service with facial recognition function, which will provide you with basic information about the person in the photo by scanning the face in the photo. In addition, the service will show which celebrities are similar to the person depicted in the search query.

Here, as in Google service, you can upload a photo for analysis or provide a link to a photo published on the Internet.

True, in our test examples the service’s performance was strange - the service did not recognize Petra Kvitova, and among celebrities similar to her it named another tennis player, Anna Ivanovich.

At the same time, in another example of a photograph of Anna Ivanovich, the tennis player was recognized immediately with an accuracy of 52%, which is quite a lot for this service.

Betafacehttp://betaface.com/demo.html

Betaface is a professional facial recognition software aimed at media companies, allowing them to automatically recognize faces and find information about them. To study how this works paid product, you can use its demo version.

Users are asked to upload a photo to the site, after which the service big list information about the person depicted on it. These details include age, race, facial expression, presence of a beard and glasses, hair and beard color, presence of a mustache, chin size, eye color and position, eyebrow position, color and thickness, hair length, head shape, mouth and nose shape and size , teeth and other smaller parts.

Finding a person via the Internet is quite simple - now almost everyone has their own page on social networks. You just need to somehow reach it.

There are several ways to do this (I talked about them), but they all rely on searching for information. You must indicate your first name, last name, age, city of residence and other information. But even if you know everything about a person, down to his blood type, this is not a guarantee that he will be found.

It’s a completely different matter if you have a photograph, even a general one. Now there are services that can recognize faces and search for the pages of their owners.

Preparing the photo

First you need to crop the photo. So us and her computer size Let's reduce it (usually it's big), and remove all the excess. This is especially true if the photo is a group one.

1 . Open Start - All Programs - Accessories - Paint

2. Open the photo in this program (you can simply drag it inside the window).

3. Select the “Select” tool at the top and circle the desired person.

4 . Click the “Crop” button.

Search on VKontakte (findface.ru)

FindFace (findface.ru) is a special service for searching for people on the VKontakte social network. But to use it, you need to have a VK page.

You can get it for free in just a minute - to do this, go to the website vk.com and register.

To search through FindFace, follow the link and click on the “find identical” button.

The service will ask you to allow access to your VK page, to which we agree.

Upload the desired photo (you can simply drag it inside the window).

And we wait for the end of the search procedure.

That's all - all that remains is to find your lost one in the list :)

Search the entire Internet

Search by image. There are two for this special services: one is from Google (images.google.com), the other is from Yandex (images.yandex.ru). They are very easy to use: you just need to drag the photo into the search bar.


Google Image Search


Search by image Yandex

The result will appear immediately. First, the same picture will be shown, but in other sizes (if available on the network), just below - similar photos, even lower are the Internet pages on which they are posted.

TinEye (tineye.com). Popular foreign image search service.

Everything is exactly the same here: drag a picture from your computer into the search bar, and immediately get the result.

Browser extensions

Extensions or add-ons are small gadgets that are added to an Internet program and perform certain tasks in it. For example, there are extensions for downloading videos from Youtube or music from Contact. There are also such programs for searching by photographs.

Almost every browser has its own collection of various add-ons. But most of them are in Google Chrome. In other programs, there are literally one or two extensions for our purposes, and even then they do not work quite as they should. Therefore, I will show how to work with add-ons only using the example of Chrome.

Where to find and how to install the extension

1 . Click on the button at the top right and select Additional tools- Extensions.

2. We go down to the very bottom of the page (scroll with the wheel on the mouse) and click on “More extensions”.

3. IN top line search print keywords and press Enter. The found extensions and applications appear. We install what we need (it can then be deleted at any time).

If you install an application, it is added to an empty tab, in the Services item. That is, in order to find it later, you need to open it new tab browser and go to “Services” (top left).

Extensions are installed a little differently - they are added immediately after the address bar.