Home » Misc » Shape recognition activities

Shape recognition activities


25 Creative Activities and Ideas For Learning Shapes

Learning shapes is one of the earliest concepts we teach kids. This readies them for geometry in the years ahead, but it’s also an important skill for learning how to write and draw. We’ve rounded up our favorite activities for learning shapes, both 2-D and 3-D. They all work well in the classroom or at home.

1. Start with an anchor chart

Colorful anchor charts like these are terrific reference tools for kids learning shapes. Have kids help you come up with examples for each one.

Learn more: A Spoonful of Learning/Kindergarten Kindergarten

2. Sort items by shape

Collect items from around the classroom or house, then sort them by their shapes. This is a fun way for kids to realize that the world around them is full of circles, squares, triangles, and more.

Learn more: Busy Toddler/Shape-Sorting

3. Snack on some shapes

Everyone loves a learning activity you can eat! Some food items are already the perfect shape; for others, you’ll have to get a little creative.

ADVERTISEMENT

Learn more: Chieu Anh Urban

4. Print with shape blocks

Grab your shape blocks and some washable paint, then stamp shapes to form a design or picture.

Learn more: Pocket of Preschool

5. Go on a shape hunt

These “magnifying glasses” make an adventure of learning shapes! Tip: Laminate them for long-term use.

Learn more: Nurture Store UK

6. Hop along a shape maze

Use sidewalk chalk to lay out a shape maze on the playground or driveway. Choose a shape and hop from one to the next, or call out a different shape for every jump!

Learn more: Creative Family Fun

7. Assemble a truck from shapes

Cut out a variety of shapes (excellent scissors skills practice!), then assemble a series of trucks and other vehicles.

Learn more: Little Family Fun

8.

Stretch out shapes on geoboards

Teachers and kids love geoboards, and they’re a great tool for learning shapes. Give students example cards to follow, or ask them to figure out the method on their own.

Learn more: Mrs. Jones’ Creation Station

9. Drive on shaped roads

Use these free printable road mats to work on shapes. Bonus: Make your own road shapes from sentence strips!

Learn more: PK Preschool Mom

10. Find shapes in nature

Take your shape hunt outside and look for circles, rectangles, and more in nature. For another fun activity, gather items and use them to make shapes too.

Learn more: Nurture Store UK

11. Put together craft stick shapes

Add Velcro dots to the ends of wood craft sticks for quick and easy math toys. Write the names of each shape on the sticks for a self-correcting center activity.

Learn more: Surviving a Teacher’s Salary

12.

Blow 3-D shape bubbles

This is a STEM activity that’s sure to fascinate everyone. Make 3-D shapes from straws and pipe cleaners, then dip them in a bubble solution to create tensile bubbles. So cool!

Learn more: Babble Dabble Do

13. Prep a shape pizza

Cover a paper plate “pizza” with lots of shape toppings, then count the number of each. Simple, but lots of fun and very effective.

Learn more: Mrs. Thompson’s Treasures

14. Construct shapes from toothpicks and Play-Doh

This is an excellent STEM challenge: how many shapes can you make using toothpicks and Play-Doh? Marshmallows work well for this activity too.

Learn more: Childhood 101

15. Outline shapes with stickers

Kids adore stickers, so they’ll enjoy filling in the outlines of the shapes they’re learning. They won’t realize it, but this gives them fine motor skills practice too!

Learn more: Busy Toddler/Sticker Shapes

16.

Lace shapes

Lacing cards have long been a classic, but we really like this version that uses drinking straws. Just cut them into pieces and glue them along the edges of the cards.

Learn more: Planning Playtime

17. Make shapes with LEGO bricks

LEGO math is always a winner! This activity also makes a good STEM challenge. Can your students figure out how to make a circle from straight-sided blocks?

Learn more: Pocket of Preschool

18. Categorize shapes by their attributes

Work on geometry terms like “sides” and “vertices” when you sort shapes using these attributes. Start by placing shapes into paper bags and asking students questions like, “The shape in this bag has 4 sides. What could it be?”

Learn more: Susan Jones Teaching

19. Count and graph shapes

These free printable worksheets challenge kids to identify shapes, then count and graph them. Lots of math skills, all in one!

Learn more: Playdough to Plato

20.

Create a shape monster

Add arms, legs, and faces to create cheery (or scary) shape monsters! These make for a fun classroom display.

Learn more: Fantastic Fun and Learning

21. Sift through rice for shapes

Sure, kids can identify their shapes by sight, but what about by touch? Bury blocks in a bowl of rice or sand, then have kids dig them out and guess the shape without seeing them first.

Learn more: Fun With Mama

22. Craft an ice cream cone

Ice cream cones are made up of several shapes. Encourage kids to see how many different ways they can make a sphere of “ice cream.”

Learn more: Extremely Good Parenting

23. Ask “What does the shape say?”

If you don’t mind the risk of getting that song stuck in your kids’ heads, this is such a neat way to combine writing and math.

Learn more: Around the Kampfire

24. Piece together shape puzzles

Use wood craft sticks to make simple puzzles for kids who are learning their shapes. These are inexpensive enough that you can make full sets for each of your students.

Learn more: Toddler at Play

25. Feed a shape monster

Turn paper bags into shape-eating monsters, then let kids fill their hungry bellies!

Learn more: Teach Pre-K

From teaching shapes to long division and everything in between, these are the 25 Must-Have Elementary Classroom Math Supplies You Can Count On.

Plus, 22 Active Math Games and Activities For Kids Who Love to Move.

10 Hands-On Shapes Recognition Activities for Preschoolers

  • Share
  • Email

Teaching children about shapes should be a fun, hands-on experience. It is by experiencing concepts through the body and the senses that real learning happens in the early years.

Scroll down to the section ‘10 simple shapes recognition activities’ for some great ideas.

Why is it Important to Learn About Shapes?

An important part of child development, shape recognition is about more than just being able to spot the basic shapes. It’s important for building early maths, reading and other areas too.

Shapes are found all around us and take many different forms, both two-dimensional and three-dimensional.

Children learn that shapes have properties – such as lines, curves, sizes, lengths and positions in space, and that all physical objects have shape. 

They develop their visual perception (when the brain interprets what the eyes see) as they are exposed to shapes around them. 

Shapes are a part of mathematical concepts (like geometry) and are also used in many scientific and technical fields.

The recognition of shapes is crucial for learning to read and building early literacy skills. 

Letters are made up of shapes and children need to learn to distinguish, recognize and remember the specific shapes in order to read fluently. Shapes are the first ‘symbols’ children learn to interpret. [source]

How Do You Teach Shape Recognition?

The best way for children to learn about shapes is through play. They need many opportunities to touch and see three-dimensional shapes in their daily lives.

These concepts can also be taught through shape recognition games and activities that are planned specifically to introduce the concept of shape.

Activities like tracing and worksheets are best kept for much older children as these are unlikely to hold a child’s attention for long, and they are not really meaningful to a young child.

It is more important to focus on doing hands-on activities during preschool so that a child fully understands the properties of shapes by experiencing them with their body and all their senses.

It is also important for parents and teachers to actively teach the vocabulary about shapes. They need to hear concepts such as:

  • Straight lines or curvy lines
  • Sides
  • Surfaces
  • Size – bigger, smaller, longer, etc.
  • Round, pointy
  • 2-dimensional, 3-dimensional
  • The names of shapes – oval, rectangle, triangular prism

This can be done in natural ways during a conversation:

  • Is your dinner plate round? 
  • What else is round in our house?
  • This picture of a tent looks like a triangle – it’s pointy at the top.

When teaching the shapes, remember children learn these in a concrete-pictorial-abstract way, as they do many other concepts. 

They learn the shape of a physical object, and then later learn to associate a picture of a shape with the physical object. After that, they can recognize an abstract representation of a shape.

An example of this is playing with a beach ball and learning that it is round; then understanding that a picture of a ball represents a round, circular shape; then identifying a simple circle drawn on paper.

10 Simple Shapes Recognition Activities and Games

Here are some simple shape activities to try at home or school.

1. Shape Sorting

Sorting is an important mental concept and it’s easy to do with shapes.

Provide a container of shapes – cutouts, wooden or plastic shapes – and get kids to sort them according to different criteria. 

Here are some examples:

  • Shapes with straight edges vs shapes with curved edges
  • Shapes with 3 sides and shapes with 4 sides
  • Shapes with corners and shapes without corners
  • 2D vs 3D shapes

Here are more fun sorting activities for preschoolers.

2. Body Shapes

Play a movement game with shapes. Say the name of a shape and ask children to make the shape with their bodies. 

Get them to straighten up into a tall rectangle, puff their arms out to the side to make themselves round, stand with legs far apart and arms pointed above you to make a triangle, etc.

Before you show or help with ideas, see if the kids can figure out on their own how to make these shapes. They may think outside the box and find new ways to make the shapes. 

This is a great activity for body awareness.

3. Block and Ball Play

Children need regular exposure to shapes by playing with blocks, balls and other toys during their free play time.

This is an activity that doesn’t need much regulation by an adult but is as important as planned shapes activities.

4. Playdough Shapes

Give kids playdough and shape cutters and let them explore different shapes this way.

Make a batch of easy homemade playdough and this will keep kids occupied for hours.

If you don’t have cutters in the form of shapes, then improvise with tins (round), plastic containers (square and rectangle), etc.

5. Yummy Shapes

For a tastier version of the above activity – that will leave a bigger imprint on kids’ memory – make shapes out of cookie dough and then eat them after!

6. Find the Shapes

Show children an example of a simple shape, such as a circle, and challenge them to find as many items as they can around them that have the same shape. (Here are more games about circles to try).

They could also draw pictures of all the things they can think of that have a circle shape.

This teaches kids that shapes are part of their world.

7. Build With Shapes

If you have plastic or wooden shapes that are relatively flat, let kids ‘build’ pictures out of them using the shapes. 

They could construct a house or a person, for example, by learning to use the shapes to substitute the various parts they need.

These shapes can also be made out of cardboard.

8. Feel the Shape

Use the same shapes from the activity above to do a sensory activity.

Blindfold a child, then give him a shape or ask him to pick a shape out of a bag. He must describe the shape (it is round and has no straight edges), then say what the shape is. 

If he guesses right, he can keep the shape. If not, it goes back into the bag. This can be turned into a game to see how many shapes each person can accumulate.

9. Shape Stamping

Provide poster paints on trays and get kids to stamp shapes onto them.

Use blocks for these shapes or make potato prints, sponge shapes, etc. Use your imagination.

10. Shape Pictures

A fun art activity, this can be attempted after children have had ample opportunity to make shape pictures out of real shapes. 

Provide lots of pre-cut paper shapes in various colours, white paper and glue.

Get kids to make their own shape pictures. Let them use their creativity and do not try to guide their creations.  

Definitely don’t give them a model to copy! This should be a form of process art, where the learning is in the doing, not the final product.

If you are looking for more creative art ideas, try these shape crafts for preschoolers.

Sources:

“Learning Through Play: A parent’s guide to the first five years”, written by Jan Natanson.

“Language and School Readiness”, written by Martie Pieterse.

Get FREE access to Printable Puzzles, Stories, Activity Packs and more!

Join Empowered Parents + and you’ll receive a downloadable set of printable puzzles, games and short stories, as well as the Learning Through Play Activity Pack which includes an entire year of activities for 3 to 6-year-olds.
Access is free forever.

Signing up for a free Grow account is fast and easy and will allow you to bookmark articles to read later, on this website as well as many websites worldwide that use Grow.

  • Share
  • Email

Recognition of documents for the purposes of remote banking / Sudo Null IT News

The emergence of remote banking services (RBS) has changed the entire banking business, providing the opportunity to receive financial services "in no time". Today we want to tell you about our new Smart Document Engine product, which will change the RBS process, providing the procedure for opening accounts and obtaining loans in "two clicks".

Remote banking service (RBS) is a convenient financial management tool, the level of development of which in our country can hardly be underestimated. The popularity of digital banking services is great both among ordinary people (individuals) and among companies. Faithful satellites of RBS are document recognition systems. They play an important role in the RBS process, having already solved the problem of instant and secure onboarding for individuals and implemented several convenient cases (for example, by automating card-to-card transfers or paying receipts using QR codes). nine0003

Today, advanced digital banks are actively using passport recognition and face verification technologies to open accounts for individuals. With opening an account for legal entities, everything is more difficult. The required set of documents is wider. Usually, to open an account, banks require the provision of a charter, certificates of registration of the company with various state bodies, statistics, an order to appoint a sole executive body, a card with a seal and signature, and other documents. nine0003

Imagine how much easier the process of opening an account would be if there was a remote banking function for automatically checking and recognizing images of specified documents with reserving an account for a new client. Of course, it is absolutely necessary to bring the originals of all documents to the bank or transfer them to the field employee later (these are the requirements of the law). But this can be done already in working order, and not in a “fever”, when the details are needed “here and now”.

Something like this (only more emotionally) we reasoned, plunging into the endless process of opening a current account in one of the largest banks in our country. Sadly, no automation was shown to us. The reason turned out to be simple: the document recognition solutions used are recognized only “in theory”, but in practice they “stumble” on technological barriers from the last century:

  • 300 DPI scans are expected as input images, photos from small format cameras do not provide the required image quality;

  • require high performance servers for deployment;

  • In fact, only OCR is provided out of the box, and all additional document mining needs to be implemented on your side.

Therefore, we decided to create a recognition system that does not have these limitations. We tried to rethink the problem of document recognition anew and fixed the following requirements for the new product:

  1. Support for scans and photos. This is one of the key requirements. We have repeatedly written that the method of digitizing paper documents from scanning is moving towards photography. It is faster, more convenient, but it has its own characteristics: a full range of problems arises associated with projective geometric distortions of the generated document image, lighting variability, and the presence of foreign elements on the photographed scene.

  2. On-premises only. Data must NOT be transmitted to any services, must NOT be stored, and the system must NOT require internet access to operate. All document processing must be carried out strictly locally on the client's device or within the bank's infrastructure.

  3. Works both on servers and on mobile devices. The operating time on mobile devices must be acceptable, while the optimization of the recognition time must be without sacrificing quality. nine0003

  4. Rigid and flexible shapes support. The new product must support all kinds of documents. Including multipage. In addition, we need the functionality of adaptation to arbitrary new types of documents.

  5. Recognition of various elements. A document is more than just letters. Accordingly, recognition is not just OCR. It is necessary to additionally localize and recognize other mandatory elements of business documents: tables, labels and checkboxes, signatures and stamps, handwritten notes, etc. nine0003

  6. Document completion analysis. The built-in mechanism of the new product should provide control over the filling of the document, the presence of keywords and phrases, control over the absence of blots, corrections and other notes.

  7. Document authentication elements. Additional color control of both individual elements and the entire document as a whole, font style analysis, logo visualization allow the product to detect individual cases of fraud at an early stage. nine0003

  8. Native work on domestic computer systems. No comments here.

Starting to create the product, we realized that we already had most of the technological groundwork to provide the required functionality! Moreover, we even wrote about it on Habré:

  • Here we talk about how we taught our products to find the document quadrangle in the image. Adding color normalization to this functionality makes it possible to implement the technology of “scanning” a document using a mobile phone. nine0003

  • We have developed a training infrastructure for extremely compact computationally efficient convolutional neural networks (you can read about it, for example, here, here and here). In addition, we are constantly improving our own digital image processing apparatus, paying special attention to the complexity of the algorithms used (see here, here and here). All this makes it possible to create computationally efficient recognition systems that can run both on servers and on mobile devices. nine0003

  • We already have experience with rigid and quasi-rigid shape recognition, where the acceptable model for changing the shape of a document is simple and clear in advance. We can recognize documents in the form of a "booklet" (passport of the Russian Federation) and a "triple booklet" (certificate of registration of prostitutes in Germany).

  • We have already implemented the technology for classifying complex business documents.

  • We have long tested the mechanism for localization and recognition of graphic elements such as "seal", "stamp", "signature", "logo", etc. We have implemented our own barcode decoder that does a great job with 1D and 2D barcodes. nine0003

  • We have developed a unique approach to document authenticity analysis and have already implemented it in our passport recognition product.

  • All components of our platform work on Elbrus! And they also wrote about it here, here and here.

As a result, we succeeded. So, we are pleased to present you our new product that fully meets the above requirements - Smart Document Engine. What can he do?

Smart Document Engine 9 functionality0113

Rigid shape classification and recognition. Rigid forms are documents, different copies of which coincide "through the light" when the details are removed. The Smart Document Engine contains algorithms for fast localization and rigid forms on scans, photographs and video streams, which makes it possible to parse such documents.

Classification and recognition of flexible shapes. Flexible forms are documents whose elements and details can change their relative position on the form. Examples of flexible forms are tax and accounting documents, such as a 2-NDFL certificate, a company's balance sheet, a statement of financial results, etc. nine0003

Analysis of documents of arbitrary type. Smart Document Engine allows you to recognize and analyze documents of arbitrary type (power of attorney, consent, contract). Using the Smart Document Engine, you can classify such documents, extract details, verify the presence of signatures and seals, etc.

Support for scans, photos and videos. The Smart Document Engine can recognize documents and forms from both images taken from flatbed and line scanners, as well as photos and videos taken from smartphones, tablets and other mobile devices. nine0003

Analysis of multipage documents. Smart Document Engine allows you to classify and recognize multi-page documents. Processing a sequence of pages allows you to simplify the process of streaming scanning, sorting the stream and checking for the presence of necessary documents.

Recognition of text attributes. The stack of localization and character recognition technologies implemented in the Smart Document Engine system allows you to quickly and accurately recognize single-line and multi-line text fields in more than 100 languages, extract details from solid text, typewritten and handwritten fields in the layout, and much more. nine0137

Label and checkbox recognition. The Smart Document Engine accurately and reliably recognizes marks and checkboxes, whether printed or in pen.

Check for presence and recognition of handwritten notes and signatures. The Smart Document Engine allows you to extract handwritten fields and signatures, recognize digital fields made by hand in free form, and verify the presence of marks and signatures.

Table recognition. nine0032 The Smart Document Engine implements search and recognition of tabular data. Supported tables with a rigid structure, relational and non-relational, tables with a variable number of columns and structured sets of requisites with layout.

Search and recognition of seals. The Smart Document Engine is equipped with modules for fast detection, localization and classification of seals. In addition to searching for and verifying the presence of a seal, the platform allows the recognition of individual text components of seals. nine0003

Check for keywords and phrases . To identify significant phrases, as well as to detect incorrect changes in the text, the Smart Document Engine system allows you to check the presence of keywords, phrases and phrases.

Document filling control. Using the Smart Document Engine, you can control the filling of a document, including checking for the presence of mandatory text or graphic fields, and analyzing areas of the document intended for handwritten or handwritten filling. nine0003

Control of the absence of blots, corrections and other marks. The Smart Document Engine system allows you to detect, localize and recognize blots, strikethroughs, corrections and other marks on a document in order to control its reliability and extract additional information.

Control of logos and other graphic elements . Smart Document Engine allows you to detect, localize and control the presence of graphic elements such as company logos, as well as important graphic fields of documents, such as a photograph pasted into a questionnaire. nine0003

Document color check . The Smart Document Engine system determines both the color of the document as a whole and its individual elements (seals and signatures), which makes it possible to detect a black-and-white copy of the document.

Analysis of text field attributes. In addition to recognizing text fields, the Smart Document Engine analyzes the attributes of fields and individual text characters, such as font characteristics (presence of serifs, italics, boldness), uniformity and monotony scores, etc.

What banking processes does the Smart Document Engine solve?

1. Automation of the account opening process. Smart Document Engine makes it possible not only to read and enter data into the bank's information system, but also to verify the document: check that all required fields are filled in, check for signatures and seals, and perform cross-checks.

2. Automation of the loan approval process. Smart Document Engine speeds up and automates the decision to issue a loan for both individuals and legal entities by recognizing the 2-NDFL Certificate, Balance Sheet, Statement of Financial Results. nine0003

3. Automation of mobile agents. Thanks to full standalone operation on mobile devices, Smart Document Engine provides scanning, recognition and verification of completed questionnaires and other documents in the field.

A reader immersed in banking topics will independently find a dozen more useful applications of our new product. The important thing is that Smart Document Engine eliminates the routine of data entry, reducing the number of errors and freeing up valuable minutes to work with the client, and also expands the scope of RBS. nine0003

What do we have as a result?

A modern mobile phone allows using the Smart Document Engine to recognize a stream of document images from a specialized document scanner with a capacity of up to 30 pages per minute, which was previously available only to high-performance workstations or servers, providing the highest accuracy of recognition of text, digital and other document data. So, recognition of the 2-NDFL certificate on the Galaxy S10 phone takes less than 3 seconds on average. The system equally well and quickly processes both scans of questionnaires and photographs, automatically performing all the actions necessary for classification, data extraction from them and text recognition, taking into account geometric distortions, differences and irregularities in lighting typical for photographs. nine0003

Smart Document Engine out of the box recognizes a certificate of tax registration of a citizen of the Russian Federation (TIN), a 2-NDFL certificate, a payment order (form 0401060), a balance sheet (form 0710001), a statement of financial results (form 0710002), as well as certificates on the results of PCR analyzes of several popular laboratories in Russia. Smart Document Engine can be configured to recognize other documents (custom contracts and forms, agreements and powers of attorney, etc.).

Thus, we have created a complete line of products that meet all the needs of RBS in recognition systems. Smart ID Engine automates the input of the client's personal data (recognition of a passport, driver's licenses, etc.) and authenticates ID documents, solves the problem of face verification. Smart Code Engine solves the problem of quickly extracting and entering all the necessary data from a payment card to complete a transaction (bank card recognition), and also allows you to recognize QR Code, AZTEC, PDF417 and other 1D and 2D barcodes. And finally, our new flagship product - Smart Document Engine - solves the tasks of document recognition related to the registration and maintenance of legal entities, as well as processing a set of documents required for credit scoring, online accounting, and making payments. nine0003

Document Recognition (OCR) | Smart Engines

Document Recognition (OCR) | Software Smart Engines

Download demo

Smart Document Engine

is a Russian automatic document analysis and recognition system for desktop, server and mobile platforms.

Smart Document Engine is a software tool for businesses and developers that provides high-precision and high-speed recognition of text and other data of primary, business, statutory, accounting, tax, notary, legal, insurance and banking documents, as well as standard questionnaires and strict reporting forms. nine0003

Developed by our scientists, GreenOCR® is a high-tech optical character recognition technology that accurately recognizes the text of any documents in more than 100 languages, including Cyrillic, Latin, Arabic, Persian, Urdu, Japanese, Chinese, Korean and others. GreenOCR® provides high-accuracy typed text recognition (OCR), hand-typed and hand-written field completion (ICR), and mark and checkbox recognition (OMR). See datasheet

Easy integration without breaking the usual processes

Smart Document Engine is a unique tool that allows you to flexibly integrate document recognition into the current activities of the company. The program is easily and conveniently integrated into existing business processes without disturbing the usual user experience. The solution is available for integration with various information systems, such as ECM, CRM, RPA, 1C, ABS, etc.

Why do I need Smart Document Engine recognition? nine0208

The Smart Document Engine software product is designed to automate the processing and digitization of paper documents, workflow and optimize the processes of mass input of documents.

The Smart Document Engine solves OCR tasks for business documents, which were previously available only to high-performance servers, even on conventional mobile phones.

Our clients

Russian recognition software

Own development

Founders - residents of the Russian Federation

Support for
Russian operating systems

Entry 9617
in the software registry

  1. Technology authorship (patents, intellectual property)
  2. Own research and development center in Moscow
  3. Registration in the software register of the Russian Federation (No. 9617 dated March 15, 2021)
  4. The owners of the company are residents of the Russian Federation
  5. Lack of third-party services and software products
  6. Independence from the influence of foreign organizations and states

Privacy and security

Smart Document Engine software:

  • DOES NOT use Open Source code and foreign software components, ensuring technological sovereignty to third parties for manual input
  • DOES NOT save data: all processing is carried out in the local RAM of the device - 100% on-premise
  • DOES NOT require network connection

    Lawyers warn:

    licenses and certificates of recognition services will not protect you in case of data leakage

    financial responsibility. nine0003

    “Companies that transfer their customer data for processing to third parties, in the event of a leak, are deprived of the right to invoke violation of their rights by third parties and assume all responsibility to counterparties.” - concluded the lawyers of the company "INTELLECT", which is included in the group of the most successful Russian law firms according to the international rating of The Chambers Europe.

    Read the full legal opinion.

    Wide functionality in one SDK

    38 document types out of the box

    Text recognition (OCR), tables and checkboxes

    Image data comprehension (ICR) - seals, stamps

    Color and fill control

    Document recognition in 101 languages ​​

    and Document Type Detection

    Multipage Document Analysis

    Handwriting Reading - Annotations and Signatures

    Working with Photo and Scan Formats

    Stream Recognition and Scanning

    38 document types out of the box

    Document type classification and identification

    Text recognition (OCR), tables and checkboxes

    Multi-page document analysis

    Image data understanding (ICR) – seals, stamps

    Handwriting reading data - marks and signatures

    Color and fill control

    Work with photo and scan formats

    Document recognition in 101 languages ​​

    Stream recognition and scanning

    Works everywhere

    Mobile or web, server or desktop - the choice is yours. We've got everything you need:

    • Easy application integration using interfaces for Objective-C, Swift, C, C++, Java, C#, PHP, and Python
    • Support for multiple operating systems: iOS, Android, Sailfish Mobile, Aurora MOS, Linux, Windows, macOS, Solaris, etc.
    • Wrappers for React Native and Flutter 9 are also available0016

    Set of necessary solutions.


    Or custom development for your needs
    • Invoices and payments »
    • Accounting documents »
    • Questionnaires and consents »
    • Smartphone Scan »
    • Primary documentation »
    • Stream recognition
    • Full text recognition

    An important aspect of the Smart Document Engine is the ability to create customized solutions for specific customers that allow automatic processing, classification, recognition and analysis of paper and scanned pdf documents and forms of any complexity. The system understands all required types of documents in the form of graphic files (jpg, tiff, png, etc. )

    Custom solutions will allow your organization to reduce costs and burden on staff by implementing highly efficient and highly accurate in-line scanning and document recognition, optimized for a specific data flow and for existing business processes, while eliminating the transfer of any data to third-party services or third parties persons.

    Recognize a document in 1 step

    Just provide a photo or scan of a document and the AI ​​will do the rest:

    Recognizes graphic and text data, stamps and signatures; analyze the relevance of the data and the completeness of the document

    Convert the read data into text and transfer the information in a structured form to your compatible system

    Check the quality of our technology

    Extract data from standard documents and forms on scanned copies or photographs.

    All the features of the Smart Document Engine

    Classification and recognition of hard shapes

    Rigid forms are documents, different copies of which coincide “through the light” when details are removed. Classic examples of rigid forms are sick leave or the USE form. The Smart Document Engine document recognition system includes state-of-the-art algorithms for fast localization and typing of hard forms on scans, photographs and video streams, which allows instant targeting and analysis of such documents, as well as verification of their type. nine0003

    Analysis of documents of arbitrary type

    The Smart Document Engine document recognition system allows you to create solutions for recognition and analysis of arbitrary documents, such as powers of attorney, consents, contracts. Using the Smart Document Engine, you can classify such documents, extract text or other details, verify the presence of signatures and seals, etc.

    Analysis of multipage documents nine0405

    Smart Document Engine allows you to classify and recognize both individual images of documents, questionnaires and forms, as well as multi-page documents, or sequences of pages containing several documents. Processing a sequence of pages allows you to simplify, sort the flow and check the availability of the necessary documents (completeness check).

    Recognition of labels and checkboxes

    The Smart Document Engine accurately and reliably recognizes marks and checkboxes, whether printed or in pen. nine0003

    Table recognition

    For the full processing of accounting, tax, banking and other documents, the Smart Document Engine system implements the search and recognition of tabular data. Supported as tables with a rigid structure, relational and non-relational, tables with a variable number of columns, and structured sets of requisites with lines.

    Checking for keywords and phrases

    In the processes of analyzing complex structured documents to identify significant phrases and paragraphs, as well as to detect incorrect changes in the text of printed documents, the Smart Document Engine system allows you to check the presence of keywords, phrases, phrases, and control the integrity of control paragraphs.

    Control of the absence of blots, corrections, and other marks

    The Smart Document Engine allows you to detect, localize, and recognize blots, strikethroughs, corrections, and other marks on a document in order to check its authenticity and extract additional information. nine0003

    Document color control

    The Smart Document Engine system allows you to determine the color of the document as a whole, as well as its individual elements (seals and signatures), which allows you to recognize a black and white copy of the document even when rescanning or photographing.

    Classification and recognition of flexible forms

    Flexible forms are documents whose elements and details can change their relative position on the form. Classical examples of flexible forms are widely used tax and accounting documents, such as a certificate of income of an individual of the established form (formerly 2-NDFL), an enterprise balance sheet, a statement of financial results, a payment order, etc. Using the Smart Document Engine system, you can quickly identify documents of this kind, localize significant details, conduct their recognition and analysis. nine0003

    Support for scans, photos and videos

    The Smart Document Engine can recognize documents and forms from both images taken from flatbed and line scanners, and from photos and videos taken using smartphones, tablets and other mobile devices.

    Recognition of text attributes

    The Smart Document Engine technology stack allows you to quickly and accurately recognize single-line and multi-line text fields in more than 100 languages, extract details from solid text, typewritten and handwritten fields in line drawing, and much more. nine0003

    Search and recognition of seals

    The Smart Document Engine is equipped with modules for fast detection, localization and classification of seals. In addition to searching for and verifying the presence of a seal, the platform allows the recognition of individual text components of seals.

    Document filling control

    Using the Smart Document Engine, you can control the filling of a document, including checking for the presence of required text or graphic fields, analyzing areas of the document intended for handwritten or handwritten filling. nine0003

    Control of logos and other graphic elements

    The Smart Document Engine detects, localizes, and controls the presence of graphic elements such as company logos, as well as important document graphic fields, such as a photograph pasted into a questionnaire.

    Checking for and recognizing handwritten notes and signatures

    The Smart Document Engine allows you to extract handwritten margins and signatures, recognize freehand digital fields, and verify the presence of handwritten marks and signatures. nine0003

    Parsing Text Field Attributes

    In addition to recognizing text fields, the Smart Document Engine allows you to analyze the attributes of fields and individual text characters, such as font characteristics (presence of serifs, italics, boldness), uniformity and monotony scores, etc.

    Smart Engines Document Recognition Features

    Speed ​​
    The original integer image processing pipeline, including 8-bit and 4-bit deep neural network architectures, allows you to use intelligent document recognition even on budget phones by maximizing the use of available hardware resources. nine0003

    Accuracy
    We have created a new generation of OCR technologies that break the quality barrier of traditional approaches by leveraging our latest advances in computational intelligence and deep learning. The accuracy of document details recognition reaches 99.5% without human intervention.

    Performance
    The highest performance is achieved by combining computer vision algorithms and deep learning compact neural networks. A full cycle from type detection to recognition of all details takes from 2 seconds for an A4 document page. Demo version available for download. nine0003

    Convenience
    Our advanced algorithms automatically detect the document on the frame, automatically determine the document type, find the details and recognize them. The system is resistant to various geometric distortions, noise, lighting differences, print defects and low resolution. Download the product demo and test the convenience of

    technology

    Support for Russian platforms
    Smart Document Engine is the first document recognition system that natively (without emulation) supports the Russian hardware platforms Elbrus, KOMDIV and Baikal, which allows using the product in areas of maximum responsibility and security. The Smart Document Engine provides an unprecedented level of data processing security and protection against sanctions risks. nine0003

    Multiplatform
    Smart Document Engine supports a wide range of operating systems, including specialized operating systems designed to work with personal data: Elbrus OS, RED OS, Atlix OS, Astra Linux, Cent OS, Ubuntu, Red Hat Enterprise Linux, SUSE Linux Enterprise Server, Arch Linux and other Linux distributions, MS Windows, macOS, Aurora OS, iOS, Android, Sailfish Mobile OS.

    How this software is delivered

    With the Smart Document Engine SDK, you can add deep document analysis and recognition functionality to both your back office automation infrastructure solutions and mobile applications to make remote .

    The Smart Document Engine is delivered as a standalone SDK (software development kit) containing all the necessary precompiled libraries, API documentation, and integration examples for various programming languages. A simple but multifunctional API (application programming interface) has been prepared for developers, which allows you to implement document recognition in solutions using C ++, C #, Java, Python and Objective-C for a wide range of operating systems: iOS, Android, Linux, Windows, MacOS , including Sailfish Mobile, Avrora MOS, Elbrus OS, RED OS, Astra Linux, and others. The following hardware platforms are supported: x86_64, ARM v7, v8 (Aarch42, Aarch64), MIPS, Elbrus. It is possible to configure and connect to popular RPA frameworks and 1C products on request. nine0003

    Documents recognized “out of the box” include a certificate of tax registration of a citizen of the Russian Federation (TIN), certificate of income of an individual of the established form (formerly 2-NDFL), payment order (form 0401060), balance sheet ( form 0710001), income statement (form 0710002), applications for the issuance of a foreign passport, form ADI-REG, title page of the charter, self-employed certificate, extract from the Unified State Register of Legal Entities, consignment note (TORG-12), UPD form, invoice and other primary documents . nine0003

    More in one integration

    When ID documents are required, the technology is seamlessly complemented by our Smart ID Engine, which recognizes over 2,427 different types of documents with the highest quality and speed. Recognition of codified objects, such as machine readable zones (MRZ) and barcodes, is available through the use of the Smart Code Engine.

    Specification

    Supported CPU architectures nine0405
    • x8,
    • x86_64
    • ARMv7-v8 (AArch42 and AArch64)
    • MIPS (MIPS32 and MIPS64)
    • Elbrus
    Supported Russian processors
    • Elbrus-4s
    • Elbrus-8s
    • Elbrus-8SV
    • Elbrus-1c+
    • Elbrus-2S+
    • Elbrus-3. 0013 Computer-32 (1890VM2T, 1900VA, 1900VA, 1900VA, 1900VA, 1900VA, 1900VA, 1900VA, 1900VA, 1900VA2T, 1900VA2T, 1900VA2T, 1900VA2T, 1900VA2T) 1890VM5F, 1890VM6Ya, 1890VM8Ya)
    • KOMDIV-128 (1890ВМ7Я, 1890ВМ9Я)
    • Baikal-T1
    • Baikal-M
    Supported mobile OS
    • Android (version 5.1 and up)
    • iOS (version 9 and up)
    • Sailfish Mobile OS (version 2.2 and up)
    • Aurora OC (version 3.1.0 and up)
    Supported OS for PC
    • MS Windows (all versions officially supported by the copyright holder)
    • OS family based on the Linux kernel (including Ubuntu 14.04 and above, CentOS 6 and above, SUSE Linux Enterprise Server 12 and above, Astra Linux 1.6 and above, RED OS 7 and above)
    • macOS (version 10.13 High Sierra and above)
    • OS Elbrus (version 8.11 and above)
    Recognized Documents
    • Certificate of income of physical. faces
    • Work Acceptance Certificate
    • Act of acceptance and transfer of inventory items for storage
    • Act on the return of inventory items deposited
    • Act
    • ADI-REG
    • Balance sheet
    • PCR test
    • Title page of charter
    • Bill of lading
    • Extract from the Unified State Register of Individual Entrepreneurs
    • Extract from the Unified State Register of Real Estate
    • Extract from the Unified State Register of Legal Entities
    • Statement of financial results
    • PCR test in English
    • Invoice for payment
    • Invoice
    • Invoice for payment - form 1C
    • Certificate of registration of a legal entity with the tax authority at the location in the Russian Federation, Form No. 09-1-2
    • Certificate of state registration of a legal entity, Form No. P51001
    • Certificate of making an entry in the Unified State Register of Legal Entities, Form No. P50003
    • Certificate of state registration of a legal entity, Form No. P51003
    • Certificate of making an entry in the Unified State Register of Legal Entities on a legal entity registered before July 1, 2002, Form No. P57001
    • Certificate of registration of the organization with the tax authority at its location, Form No. 1-1-Accounting
    • Payment order
    • Payment request
    • Protocol for the negotiation of prices for the supply of medicinal products
    • Certificate of registration
    • Certificate 182n from the previous place of work
    • Certificate of the cost of work performed and costs
    • Register of declarations, certificates
    • Information on labor activity in the form of STD-R
    • Certificate TIN
    • Waybill TORG-12
    • Universal Transfer Document
    • Bill of lading

    Other document types can be added on request.

    Supported text recognition (OCR) languages
    • Cyrillic (Russian, Abkhazian, Belarusian, Bulgarian, Kazakh, Kyrgyz, Mongolian, Ossetian, Serbian, Tajik, Uzbek, Ukrainian)
      • nine0013 Latin (English, Azeibarjan, Aymara, Albanian, Afrikaans, Berber, Bosnian, Hungarian, Woleai, Haitian Creole, Danish, Zulu, Indonesian, Irish, Icelandic, Spanish, Italian, Cantonese, Castilian, Catalan, Quechua, Comorian, Xhosa, Latvian, Lithuanian, Luxembourgish, Macedonian, Malay, Maltese, Mandarin, Maori, Moldavian, Nauruan, Ndau, Ndebele, German, Dutch, Norwegian, Palauan, Polish, Portuguese, Rwanda, Romanian, Rundi, Swazi, Northern Sotho, Seychelles Creole, Sesotho, Slovak, Slovenian, Somali, Swahili, Tamazight, Tetum, Tok Pisin, Tonga, Tswana, Tsonga, Turkish, Turkmen, Fiji Hindi, Fijian, Filipino, Finnish, French, Croatian, Cheva, Czech, Chibarwe, Chicheva, Shangani , Swedish, Shona, Estonian, Southern Ndebele)
    • Chinese (classical, 20,000 characters)
    • Japanese (Hiragana, Katakana and Kanji)
    • Korean (Hangul)
    • Sinhalese
    • Greek
    • Georgian
    • Armenian
    • Hebrew
    • Arabic
    • Farsi
    • Urdu
    • Tamil
    • Thai
    Compatible programming languages

    Smart Document Engine contains APIs for the following programming languages: