Clarifai Featured Hack: Musify finds the perfect background music for your videos

A great musical score can make or break a film, and it’s no different for your home videos, either. Musify is an app that matches the mood of your video to appropriate background music, making your vid as equally enjoyable to listen to as it is to watch!

Musify is an app that makes it easy for beginners and content creators to find suitable background music that matches the mood of their videos. Using Clarifai’s Custom Training technology, Musify identifies broad categories like action or calm in a video and uses JukeDeck’s API to find an appropriate soundtrack to match.

musify

WHY WE ❤ IT

Musify is one of the first developer hacks we’ve come across that combines Clarifai’s video recognition API with Clarifai’s Custom Training product. We’re really excited about the notion of a visual recognition model that can understand movie themes and film genres. Try it for yourself @ GitHub or read Yash’s excellent tutorial and code examples on his blog!

HOW YOU DO IT

We caught up with Yash Agrawal, a junior in Computer Engineering at the University of Illinois at Urbana-Champaign, to talk about the inspiration for Musify.

Clarifai: What inspired your idea for Musify?

Yash: We were thinking about something to make with Clarifai but couldn’t figure anything out so I was just browsing YouTube for some videos. I found a particular time lapse video with a really awkward background score and I realised that it was a real problem coming up with appropriate music. We wanted to make it easy for beginners and content creators to find suitable background music for their videos.

How did you build the app?

We used a bunch of Python libraries as we went along and a lot of caffeine. Musify takes in a video, uses Clarifai’s API on a custom trained model to find the mood and then uses JukeDeck’s API to find appropriate music. We also use a bunch of Python libraries to cut the original video into frames and overlay the sound.

What was the best part about working with the Clarifai API?

Clarifai’s API is so intelligent! The training of the entire set just took about 250 images and the results were near perfect so that was mind blowing!

Thanks for sharing, Yash!

To learn more, check out our documentation and sign-up for a free Clarifai account to start using our API – all it takes is three lines of code to get up and running! We’re super excited to share all the cool things built by our developer community, so don’t forget to tweet @Clarifai to show us your apps.

And give Yash some props in the comments below. Until next time!


Clarifai Featured Hack: frSecurity is an alarm that can tell friend from foe

frSecurity is an alarm that is designed to detect unauthorized entry by combining Clarifai’s face recognition API with a webcam and Amazon Alexa. When unknown people approach your home, frSecurity will send an alert and let you know you’re about to be burgled.

There are three ways to prevent burglary – locking your doors, setting an alarm, and/or not owning anything worth stealing. Even though we mostly fall into the third category (#hardknockstartuplife), we appreciate that some people might need some additional security for their homes. frSecurity is a smart alarm system that can recognize intruders and sound an alert when you’re being visited by unwanted visitors.

frsecurity

WHY WE ❤ IT

We love it when people combine hardware like the Amazon Alexa and webcams with our visual recognition software. Also, we love apps that help us protect our things from our neighbors’ grubby paws! Read more about frSecurity on Devpost!

HOW YOU DO IT

We caught up with Victor Le from New Jersey to talk about the inspiration for frSecurity.

Clarifai: What inspired your idea for frSecurity?

Victor: Our team believes safety is a growing matter of concern. We wanted to create a program that would benefit society in a revolutionary way by means of affordability, efficiency, and creativity. The program is an alarm that is designed to detect unauthorized entry by implementing face recognition using a webcam and Amazon Alexa. Clarifai’s API was a big help in determining who was an intruder and who was a friend.

A large amount of home owners are relying on a locked door as their only security measure. Don’t you think a thief would know that already? Some sort of sound, alert, attention is what what will scare the thief away. Not a locked door.

How did you build the app?

My team and I are insanely in love with Javascript. Angular JS for the front end. Node js for the back end. Some challenges we had to face was having Amazon Alexa sound the alarm without having the call its wake word. We solved it by having it connected through bluetooth to generate the sound from the server.

What was the best part about working with the Clarifai API?

The Clarifai API is extremely easy to use. Love how Clarifai has a live chat with a representative to help you out with any sort problem you have!

Thanks for sharing, Victor!

To learn more, check out our documentation and sign-up for a free Clarifai account to start using our API – all it takes is three lines of code to get up and running! We’re super excited to share all the cool things built by our developer community, so don’t forget to tweet @Clarifai to show us your apps.

And give Victor and the frSecurity team some props in the comments below. Until next time!


How Staples improved SEO using Clarifai’s multi-language image recognition API

Industry

eCommerce

Use case

Automatically tag images for SEO for 12 different languages

Result

Improved SEO while saving over $10,000

Staples Europe is the leading provider of workplace products, services and solutions to small, mid-sized, and large businesses in Europe. Staples Europe has operations across 17 countries in Europe and provides solutions across 29 European countries – each of which has its own eCommerce website.

kyleduckKyle Duck, SEO Specialist

Kyle Duck is a Search Engine Optimization (SEO) Specialist for Staples Europe, the office supplies mega-retailer. With years of SEO experience and a passion for new technology, Kyle uses artificial intelligence to solve real-world SEO problems.

Challenge

How do you adapt your e-commerce business for a global audience?

Staples is an office supply retail chain with operations all over the globe. With a large part of Staples Europe’s business coming from its online e-commerce store, the company relies on Search Engine Optimization (SEO) to surface relevant products to potential customers and stay ahead of the competition. However, with Staples Europe spanning countries that speak twelve different languages, attaching the right keyword metadata to products to improve SEO becomes twelve times as challenging (and expensive).

Staples needed a fast, accurate, and inexpensive solution to adapt its e-commerce business for multiple languages and improve SEO for its products in every target language.

“We needed descriptions for our product images translated in twelve different languages … and fast. Previously, we’d used outside agencies to do this but with an estimated cost over ten thousand dollars, we needed a better solution. Clarifai helped us save five figures in outsourcing costs and our project was finished in a single afternoon!” – Kyle Duck, Staples Europe SEO Specialist

Solution

Staples used Clarifai to translate product image tags into twelve different languages to improve SEO, increasing traffic to products in its e-commerce store and saving over $10,000 worth in agency fees.

E-commerce stores like Staples often rely on organic search traffic to its individual products to drive sales and revenue. There are many ways to improve organic search engine results, one of which is optimizing images for SEO. This includes writing descriptive keywords (ALT text) in the image tags, a practice that can be tricky to execute when you’re optimizing hundreds of images for multiple languages.

Staples used the Clarifai API’s multi-language feature, which recognizes over 11,000 different concepts in images in over twenty languages, to append the ALT tags of over 600 products to boost SEO – saving five figures worth in agency costs in the process.

“Optimizing product pages and images for SEO can be a time-consuming and costly process, especially when agencies and translation services are involved. Using the Clarifai API was orders of magnitude faster and cheaper and just as accurate!”

Implementation

Automatically “see” and understand images in multiple languages

Using Clarifai’s core visual recognition model, Staples was able to automatically add relevant keywords to their product images. These keywords were then added to the product images’ ALT tags in twelve different languages in order to improve SEO and increase traffic to Staples’ online e-commerce product pages.

Clarifai’s image recognition results were super accurate, but what was even more amazing was that the same high quality accuracy was applicable to all twelve languages we needed.

Save time and money automating services without sacrificing quality

With Clarifai’s image recognition technology, Staples was able to complete the work of an outside translation agency at a fraction of the time and cost with the same level of accuracy. Clarifai’s API doesn’t just translate English tags into other languages – each individual concept in the visual recognition model is actually trained and mapped to their respective words in twenty different languages. Thus, tricky lingual concepts like “crane” (the bird) and “crane” (the machinery) or “fall” (the verb) and “fall” (the season) are always correct in Clarifai’s multi-language API.

“Clarifai’s results were just as accurate as results we’d seen from humans at agencies. Once I saw how easy Clarifai was to setup and how accurate the AI was, going forward was a no-brainer.

Quick and easy implementation

Staples Europe’s SEO Specialist, Kyle Duck, selected Clarifai after some initial testing based on Clarifai’s superior accuracy and easy setup. All it took to start the SEO project was an API key and an unofficial Clarifai Ruby client. Once Kyle had URLs for all six hundred of the images he wanted to tag, he wrote a script to loop through the images and call Clarifai’s API for each image and language. The whole project took a single afternoon.

The whole thing took an afternoon, and it was done. It just works. Plus, the descriptions produced were shockingly accurate. Everybody around the office was super impressed with the fancy “image recognition artificial intelligence” terminology, but I had to confess that implementing Clarifai was easier than Powerpoint.

DIY with Clarifai

Now that you’ve been inspired by Staples Europe’s automated SEO solution, it’s time to build your own. Clarifai’s core model includes tags for over 11,000 concepts you can apply to your business. Or, you can use Clarifai’s Custom Training solution to teach our AI new concepts. All it takes is three simple lines of code – sign up for a developer API account to get started for free!


Clarifai Featured Hack: Describe the world to the vision-impaired with See

See is an accessibility app that uses your webcam to describe what’s happening in the room around you. This can be handy for the vision-impaired, who can better understand their surroundings through the descriptive app.

See is an app that allows the user to ask for descriptive information about their surroundings using Clarifai’s API and the user’s computer webcam. This functionality can be useful to give additional context to the vision-impaired – just ask See if something is in the room, or get a description of the top five tags related to the room.

see

WHY WE ❤ IT

Accessibility for the vision-impaired is a common use of our technology. See is particularly interesting in the way it pairs language microservices with Clarifai’s visual recognition API. On a side note, we also happen to love apps that make it hard for people to sneak up on us! Read more abou See and try it out on Devpost!

HOW YOU DO IT

We caught up with Aran Long, Comp Sci student from Birmingham, to talk about his inspiration for See.

Clarifai: What inspired your idea for See?

Aran: Lack of sleep can often cause you to talk to inanimate objects – I tried to spin it into an accessibility hack. In the future I would love to explore the natural language processing aspect further, potentially generating full sentences describing the room and being able to infer the meaning of more advanced inputs.

How did you build the app?

There are several core microservices behind See:

LANGUAGE
Language is the microservice for taking in sentences, tokenizing them and offering several different services.

Similarity – This is the similarity of two words based on their shared synonyms
Nouns – This returns all of the nouns in a given sentence
Tag – This tags words with their correct word classes.
Language is hosted using Amazon AWS EC2.

TAGGING
Tagging is a microservice that is always connected to the client. Using Socket.IO and base64 encoded image streams I am able to have a real-time tagging service using the Clarifai API.

Tagging is also hosted using Amazon AWS EC2, it also statically serves it’s images using Caddy TLS at images.aran.site (which are named using UUID generation). This also using HTTPS.

What was the best part about working with the Clarifai API?

Clarifai has great docs, I would love to see more of this in the industry. I had originally spent a lot of time using the Microsoft cognitive service computer vision API. However, I found a flaw in the API regarding its Image URL parameter.

Thanks for sharing, Aran!

To learn more, check out our documentation and sign-up for a free Clarifai account to start using our API – all it takes is three lines of code to get up and running! We’re super excited to share all the cool things built by our developer community, so don’t forget to tweet @Clarifai to show us your apps.

And give Aran some props in the comments below. Until next time!


Clarifai Featured Hack: Trashifai is a smart trash can that auto-sorts recyclables

Trashifai is a smart trash can that takes the guesswork out of saving our environment. Using Clarifai’s Custom Training product, Trashifai learns about your trash and automatically sorts it into recyclables and non-recyclables.

Climate change is the most important issue facing our generation and poses an actual existential threat to humanity. Studies have shown that recycling and waste reduction are actually very much related to climate change, which is why Trashifai is such a cool and necessary hack. Trashifai is a smart trash can (or bin, as they say across the pond) that automatically sorts recyclables and non-recyclables, helping take the guesswork out of saving our environment. When the can is full, it then notifies waste disposal authorities to come pick it up!

WHY WE ❤ IT

We believe everyone should do their part to help prevent climate change, but we also understand that sometimes recycling can get confusing with all the different types of materials that can now be recycled. We love Trashifai because it helps reduce friction for people who want to recycle. Using artificial intelligence to improve life is part of our company mission, and using artificial intelligence to prevent climate change certainly fits the bill! Check out the live demo or the GitHub repo to learn more!

HOW YOU DO IT

We caught up with Adam, Janus, Natalie, Shi Kai to talk about their inspiration for Trashifai.

Clarifai: What inspired your idea for Trashifai?

Team: We wanted to do our little bit for the environment but we felt stumped when we had to choose which bin to toss our trash in. What if we threw it in the wrong bin?

How did you build the app?

We built our smart bin with Arduino, Python and, of course, Clarifai! We used an Arduino Uno to connect a servo motor and ultrasound sensors. We made a Python script to allow the Arduino to communicate with my Macbook to call the Clarifai API and return its classification.

What was the best part about working with the Clarifai API?

It was really simple using the API. Training and testing the model is really seamless with all the backend work done for us. The API makes machine learning a simple and frustration-free experience and allows for easy connectivity with apps. Also, working with friends and not having to worry that your trash will mess up the system was great, too!

Thanks for sharing, Trashifai team!

To learn more, check out our documentation and sign-up for a free Clarifai account to start using our API – all it takes is three lines of code to get up and running! We’re super excited to share all the cool things built by our developer community, so don’t forget to tweet @Clarifai to show us your apps.

And give Adam, Janus, Natalie, and Shi Kai some props in the comments below. Until next time!


Clarifai Featured Hack: Understand your carbon footprint with SaveUrPlanet

Everyone in the world can help stop climate change by reducing their individual carbon footprint. SaveUrPlanet is an app that analyzes your carbon footprint and gives you personalized tips to reduce your impact.

SaveUrPlanet is a web application that automatically calculates your carbon footprint by analyzing your daily activities in the three categories that make up a large part of the individual contribution to carbon emissions – travel, food, and household.

SaveUrPlanet automatically sorts your travel receipts, food receipts, and electricity bills to calculate part of your carbon footprint. The app also allows you take pictures of food to calculate the carbon contribution from your daily diet. Not only does the app track and compare your carbon footprint, it also provides personalized tips based on your activity.

WHY WE ❤ IT

We only have one planet, so any app that helps us preserve it is pretty awesome in our view. We also love that SaveUrPlanet incorporates so many different microservices and APIs in one project. Read more about the project on Devpost.

HOW YOU DO IT

We caught up with Hamid “Muneer” Muneerulhudhakalvathi, graduate student at the University of Texas at Dallas, to talk about his inspiration for SaveUrPlanet.

Clarifai: What inspired your idea for SaveUrPlanet?

Muneer: We were inspired by “Before the Flood,” a documentary by Leonardo Dicaprio. Climate change is one of the most serious issues at present and its impact should be understood by the people. So, we thought we could contribute towards the welfare of society by helping people understand about the seriousness of the issue and unite them using an application.

How did you build the app?

The app was primarily built in NodeJS. We automatically forward the mails containing travel receipts, food receipts and electricity bills from the user to the Sparkpost API using Google Scripts which runs every minute. Sparkpost API dumps the mail into a database. We parse the data from mail using regex and obtain the values of miles traveled, the kind of food ordered and the electricity bills for the month and store it in MongoDB. We also allow users to take pictures of the food and send it to our system. Then use the Clarifai API which helps us to identify the kind of ingredients and calculate the carbon footprint accordingly. Also, we used the Microsoft Cognitive API to convert the electricity bill to get the appropriate values. We then use our algorithm to calculate the carbon footprint and compare it with the national average and depict the results in various graphs. We also send tips to user in order to reduce the carbon emission using the Twilio API based on the user behavior. Twilio, Microsoft Cognitive API, and Clarifai APIs were incorporated using Rapid API.

What was the best part about working with the Clarifai API?

Clarifai was one of the easiest APIs I have worked with. Simple, easy to use and to the point. No learning curve.

Thanks for sharing, Muneer!

To learn more, check out our documentation and sign-up for a free Clarifai account to start using our API – all it takes is three lines of code to get up and running! We’re super excited to share all the cool things built by our developer community, so don’t forget to tweet @Clarifai to show us your apps.

And give Muneer some props in the comments below. Until next time!


Clarifai Featured Hack: GSTR can teach you sign language using computer vision

GSTR (Gesture) is a web-based application that helps bridge the gap in non-verbal communication. Using Clarifai’s Custom Training technology, GSTR recognizes sign language from visual inputs and then gives feedback and translation information.

As with the spoken language, there are many different types of sign language being used around the world today. Each sign language has its own set of gestures that can be just as nuanced as different tones used in spoken languages. The best way to learn new languages is, of course, practice. GSTR is an application that can help you learn American sign language by providing feedback and translation on your gestures.

gstr

GSTR uses Clarifai through a custom visual recognition model that the GSTR team trained on sign language to recognize signs and gestures. It then responds in two different modes – educational and translation. Educational mode provides feedback confirming correct implementation of the sign. Translation mode gives the text and audio definition corresponding to the sign.

WHY WE ❤ IT

We love it when developers take advantage of our Custom Training technology, which is (shameless plug ahead) the only visual recognition product out there that lets devs teach new concepts to machine learning algorithms with less than 10 data examples and in less than a few seconds! Read more about the project on Devpost.

HOW YOU DO IT

We caught up with Fulton Garcia of the GSTR team to talk about the inspiration for GSTR. Fulton is currently studying Computer Science and Information Technology at the University of Central Florida and has a strong love for anything pug and/or tech related!

Clarifai: What inspired your idea for GSTR?

Fulton: We were inspired to work with people with disabilities, Sydney has a niece that is developmentally disabled and she has always wanted the opportunity to integrate her love for the community and her love for programming so we came together as a team to make that dream a reality.

How did you build the app?

GSTR was built on Node.js using Express and MongoDB for the backend. Clarifai for the image recognition and WebcamJs for capturing the images. Clarifai made it easy to create a model with multiple concepts and became accurate with the small amount of images we we’re able to collect at the hackathon.

What was the best part about working with the Clarifai API?

Clarifai is a very powerful tool that is very simple to use. It allows developers to easily implement image recognition into their projects even if they have very little experience. You can make great things with Clarifai – it’s just up to you to come up with creative ways to implement it!

Thanks for sharing, GSTR team!

To learn more, check out our documentation and sign-up for a free Clarifai account to start using our API – all it takes is three lines of code to get up and running! We’re super excited to share all the cool things built by our developer community, so don’t forget to tweet @Clarifai to show us your apps.

And give Fulton & the GSTR team some props in the comments below. Until next time!


Clarifai Featured Hack: AutoTag is an automatic #hashtag generator for social media

If a social media post gets no likes, did it ever really happen at all? AutoTag is an app that will automatically generate #hashtags for you so you never have to go through the humiliation that is posting a pic and getting no likes. Not that we speak from experience or anything – we’re one of the popular kids!

AutoTag uses Clarifai’s image recognition API to automatically generate hashtags for your images so you can easily edit and share them straight to your social media accounts. This app helps take the guesswork out of boosting your social media posts for maximum likes. Click here to download the app on Google Play!

autotagscreenies

 

WHY WE ❤ IT

Managing your real life can be stressful, and managing an online persona can be just as bad. Sometimes the pressure to come up with an #onfleek (#wtfdoesthatevenmean #so2016 #howdoyoudofellowkids) hashtag is just too great.

HOW YOU DO IT

We caught up with Null Labs’ Ayush Jha and Nick Persing, students majoring in Computer Science at Florida Institute of Technology, to talk about their inspiration for AutoTag.

Clarifai: What inspired your idea for Spectrum Navigator?

Null Labs: Seeing our friends and other people alike bombard their favorite social networks with hashtags that were obvious made us think, wouldn’t it be nice to have an intuitive, clean-looking app that could do all of that for you? And that’s when we decided to create AutoTag! We decided to use Clarifai API and make an app that looks cool and does intuitive work for the user!

How did you build the app?

Java, XML. Android Studio & Adobe Photoshop. We followed Google’s Material Design guidelines to perfect nearly every aspect of the app! Android Studio did create a lot of problems for us, especially when it came down to Github synchronization, but we kept going and never gave up. More importantly, we worked together on the app!

What was the best part about working with the Clarifai API?

The fact that it’s so freakin’ easy to set up!! Both of us would often ask each other “Are we sure we don’t have to execute or call anything else from Clarifai?”

Thanks for sharing, Null Labs!

To learn more, check out our documentation and sign-up for a free Clarifai account to start using our API – all it takes is three lines of code to get up and running! We’re super excited to share all the cool things built by our developer community, so don’t forget to tweet @Clarifai to show us your apps.

And give Ayush and Nick some props in the comments below. Until next time!


Clarifai Featured Hack: Spectrum Navigator is a GPS app that helps people navigate by landmark

Spectrum Navigator is a GPS app aimed at improving the lives of the autistic community through visually-oriented navigation. Navigating by landmark is a more intuitive process than the traditional methods of text, number, and diagram-based alternatives.

Navigating can be a challenge for anyone, but it can be especially difficult for those in the autistic community. Unfamiliar territory and non-intuitive navigation tools can be a stressful combination. Research has shown that visual supports work well as a way to communicate with children and adults on the autism spectrum. That’s where Spectrum Navigator can help!

Presentation Template

Spectrum Navigator is a GPS app that pulls Google Street View images off a calculated route and then uses Clarifai’s image recognition API to identify specific landmarks associated with waypoints. It then uses this data to present a more human-centric and visually-oriented means of navigation.

WHY WE ❤ IT

We love apps that can help people explore the world around them in new and better ways. Spectrum Navigator is not only a useful and innovative app, it’s also an example of one of the more technically challenging hacks we’ve featured. Check out the code in the GitHub repo!

HOW YOU DO IT

We caught up with Austin Lubetkin, hacker and artist, to talk about his inspiration for Spectrum Navigator.

Clarifai: What inspired your idea for Spectrum Navigator?

Austin: I’m on the autism spectrum and it is a very common challenge to have trouble navigating. I thought about the interactions I’ve had with my mother where she has helped me navigate by talking about landmarks and I decided I wanted to make a web-app that improved upon its text, number, and abstract diagram based alternatives.

How did you build the app?

HTML, JavaScript, jQuery.  There are three API integrations occurring with Google Maps, Google StreetView, and Clarifai.  There were some issues making integrating calls from one API to the next, such as sending Clarifai images from secure Google API calls, so we ended up downloading and storing the images used for training as base64 byte data that would be uploaded in the API call.

What was the best part about working with the Clarifai API?

Clarifai was a really approachable solution for the AI elements we needed in our project. It had a really dynamic interface and was surprisingly accurate when we needed it to be.

Thanks for sharing, Austin!

To learn more, check out our documentation and sign-up for a free Clarifai account to start using our API – all it takes is three lines of code to get up and running! We’re super excited to share all the cool things built by our developer community, so don’t forget to tweet @Clarifai to show us your apps.

And give Austin some props in the comments below. Until next time!


Search images on Slack with Clarifai's visual recognition technology

Our partners at Stamplay made a slick and easy way to integrate Clarifai’s visual recognition technology with Slack, so you can search your images on Slack and use them to train your own custom visual recognition model – all without writing a single line of code!

If you’re like us, you practically live in Slack. And, if you’re like us, you can probably never find that one image someone sent you two months ago that you really, really need again. Well, our friends over at Stamplay have built a handy integration for Clarifai and Slack called a “Blueprint” that lets you search images on Slack using Clarifai’s powerful visual recognition technology. Not only can you search images, but you can also feed them back to Clarifai with a simple Slash Command to train your own custom visual recognition model without a single line of code!

stamplay1

Here’s everything you can do with Stamplay’s Clarifai x Slack Blueprint:

  • Create new models and add concepts to it
  • Extract content from images
  • Search images by concepts or by similarities with other images
  • Add new inputs with concepts associated with it
  • Train models

Excited to get started? Onward to the tutorial!

1. Get a Clarifai API Key

First, get a free Clarifai API Key by creating an account. Navigate to Applications and create a new one:

stamplay2

Once the application is created, copy the Client ID and Client Secret – we’re going to need them in a couple of minutes.

stamplay3

2. Creating the Slack Slash Command

This application is available as a Stamplay Blueprint, a pre-built integration that can be deployed in your Stamplay account with minimum effort. If you don’t have an account already, click here to create a Stamplay account!

If you haven’t heard of Stamplay, you should give the service a try. They make it easy for people to consume APIs and mashup services to create powerful business apps that automate day to day activities. Stamplay fills the gap between tools like Zapier (easy to use but good only for basic use cases) and Mulesoft (very powerful but actually usable only by very technical profiles).

You’ll be prompted to pick a name for your project and then a wizard will start. After that, Stamplay will prompt you to:

  • provide Clarifai credentials
  • Connect your Slack account

The configuration is almost complete – the only thing left to do is to configure the Slash command on Slack. Once you have connected the services click on Next. 

The last view of the setup process will show the instructions to setup the Slack slash command, a URL is displayed and will look like this:

https://[APPID].stamplayapp.com/api/webhook/v1/clarifai/catch?sync=true

Copy it and save it for later.

stamplay4

3. Configuring the Slack command

Let’s create and configure the Slack command. Open https://slack.com/apps/manage/custom-integrations and make sure that the same organization that you’ve connected to this blueprint previously is selected in the upper right corner.

stamplay5

Select Slash Command custom integration (if you don’t see it listed, you can add it. Search it from the App Directory search bar on the top!) and create a New configuration.

Here you decide which command your users will have to type (we used /clarifai) and provide a URL – the one we copied a few seconds ago.

stamplay6

Other fields in this view let you customize the look of the command with a name and an icon. The thing you don’t want to miss is the Autocomplete section so you can add the slash command to the autocomplete list and add some usage hints.

stamplay7

Now you’re all set. Go to Slack and start typing “/clarifai help” to see all the commands that you can use. Easy, right?

stamplay8

If you have any feedback or questions tweet our partners at @stamplay and/or join the Stamplay Slack organization. Enjoy!


How Architizer uses image recognition to unlock the potential of user-generated content

Industry

Architecture

Use case

Categorize & recommend user-generated content

Result

Served more relevant recommendations to buyers on their platform

Architizer is a revolutionary marketplace that connects architects with the building products they need. With over 1.5 million visits a month, Architizer is the world’s premier marketplace for finding, pricing, and specifying building products. Architizer makes the process of connecting with top architecture firms easier than ever by matching manufacturers to live project opportunities and helping to get their products and materials in world-renowned projects. The company has already brought over $3.5 billion worth of construction projects this year. Sourcing products starts with finding visual precedents and that’s where Clarifai comes in.

petergerber_architizerPeter Gerber, Chief Product Officer

Peter is the Chief Product Officer @architizer. He is a design-focused technologist who is passionate about platforms and products that service the creative industry. He has over 15 years experience working with the world’s most innovative companies in design, technology, film, marketing, and creative direction.

Challenge

How do you better connect buyers and sellers in an online marketplace?

Architizer is an online platform that connects architects working on commercial-scale buildings with the manufacturers they need. Architizer’s platform has over 1.8 million images that users rely on to make purchasing decisions and get inspiration for their architecture projects. Every month notable architecture firms add over 30,000 new images of recently completed residential, commercial and institutional buildings.

With user-generated content playing a large role in helping buyers connect with sellers on their platform, Architizer needed a solution that would provide a highly scalable system for exploring user-generated content and images to increase user engagement and boost conversions in their online marketplace.

“With image recognition seeing is believing; we’ve benchmarked every service out there and we believe in Clarifai.” – Peter Gerber, Chief Product Officer of Architizer

Solution

Architizer used Clarifai to surface highly relevant related content to users based on image similarity, thus retaining users longer and facilitating architects in their sourcing process.

In the Architizer ecosystem, buyers are typically architecture firms and sellers are building materials manufacturers. Buyers, or architects, on the platform rely on user-generated content and images of architecture materials for purchasing decisions and design inspiration. Because architecture is such a visual and design-driven medium, surfacing content based on images is the best way to serve relevant recommendations to users.

In order to recommend relevant image-based content to its buyers, Architizer used Clarifai’s Custom Training and Visual Search products to detect patterns and visual similarities in a wide array of architecture-related photos and make content more discoverable on their platform.

Implementation

Automatically “see” and understand images

Using Clarifai’s Custom Training product, Architizer was able to create a custom image recognition model to understand architecture-related features like “facade system,” “cantilever,” “Brutalist,” and “living wall.” These custom concepts allowed Architizer to personalize their image recognition solution and categorize their images in a way that was most relevant to their business, rather than relying on a one-size-fits all general visual recognition model.

The custom training was the deal clincher, but overall, Clarifai’s level of communication and insight has been hugely helpful to our initiative.

Connect buyers with sellers at the right time

With Clarifai’s Visual Search product, Architizer built a truly relevant content recommendation experience around their custom visual recognition model. Architizer was able to automatically understand 1.5 million user-uploaded images on their platform and use that information to surface visually similar content to users. This content helped connect architects with materials they felt inspired by or might want to buy.

“Clarifai allowed us to find new ways to explore the world of architecture.

Quick and easy implementation

Architizer’s Chief Product Officer, Peter Gerber, tested visual recognition APIs like Imagga, Google Cloud Vision, and IBM Watson before deciding that Clarifai offered the best possible solution for his business. He selected Clarifai based on its superior accuracy and customer support, as well as Clarifai’s Custom Training product that enabled him to easily create custom visual recognition models using a handful of data examples for each new concept. With a product team of 12, Peter plans to launch Architizer’s innovative initiative and go from concept to production rollout in eight weeks.

“We’ve been evaluating image recognition and learning for 3 years now. The Clarifai team and product were always on the leading edge and, with the release of their custom training and similar image API, are now our solution of choice.”

DIY with Clarifai

Now that you’ve been inspired by Architizer’s user-generated content solution, it’s time to build your own. Clarifai’s core model includes tags for over 11,000 concepts you can apply to your business. Or, you can use Clarifai’s Custom Training solution to teach our AI new concepts. All it takes is three simple lines of code – sign up for a developer API account to get started for free!


Clarifai Featured Hack: Make the perfect toast with Toastifai, an AI-powered toaster

Toastifai is an AI-powered toaster that uses Clarifai’s visual recognition API to produce the perfect piece of toast every time. Using Clarifai’s Custom Training, the Toastifai team trained a visual recognition model on photos of toast in different stages of toastiness and used the results to build “smart” toaster!

In honor of National Toast Day, we have a solution for all your toast-burning woes! Toastifai is a “smart” toaster that can help you reach toast nirvana every single time. Using Clarifai’s Custom Training, Toastifai can recognize toast in various states of toastiness and pop out toast at exactly the moment it reaches toasty perfection – and send you a text alert that it’s ready. Say that fast ten times!

toastifai

WHY WE ❤ IT

Obviously, Toastifai is the greatest thing since sliced bread! We love when hackers combine our software with hardware – particularly hardware that can create delicious edible enjoyment. Check out Toastifai’s GitHub repo here!

HOW YOU DO IT

We caught up with Jessie Pullaro and Frank Callas, students at Florida Polytechnic University, to talk about Toastifai.

Clarifai: What inspired your idea for Toastifai?

Jessie: My group and I all like toast. We all wanted something to make perfect toast and we made Toastifai!

Frank: We were in the car talking with our friend, Muneer. Now Muneer is a busy guy. He was telling us that he hates making toast because he either burns it or he leaves it because he gets distracted and doesn’t remember to get it before he leaves. What we set out to do on October 15th, 2016 was fix Muneer’s problem.

How did you build the app?

Jessie: The entire project is in Python. We also used openCV and a package call Pillow. We also used Twillio for the texting part. Oh! And the hardware was a Logitech camera and a Raspberry Pi with an Arduino and temperature sensor to tell the webcam to turn on.

Frank: To take images from a webcam we used openCV and to manipulate it we used pillow, which uses numpy. We also used Clarifai to determine when the toast was ready, which also included using the JSON library. All of this was on the Raspberry Pi.

What was the best part about working with the Clarifai API?

Jessie: Honestly, it was the easiest thing in our project to use.

Frank: It was SO EASY TO USE! The web app for it has DRAG AND DROP! HOW MUCH BETTER DOES IT GET! Plus there is super low latency, which was great since we had to do real time processing.

Thanks for sharing, Toastifai team!

To learn more, check out our documentation and sign-up for a free Clarifai account to start using our API – all it takes is three lines of code to get up and running! We’re super excited to share all the cool things built by our developer community, so don’t forget to tweet @Clarifai to show us your apps.

And give the Toastifai team some props in the comments below. Until next time!