Clarifai Featured Hack: Val.ai is a parking app for your self-driving car

What are self-driving cars supposed to do after they’re done driving you? It’s not a trick question, it’s a real problem that a team at TechCrunch Disrupt solved using Clarifai. Val.ai is an app that lets self-driving cars self-bid for self-parking spots.

One of the worst parts about driving is finding a place to park, especially if you’re a city-dweller. Even self-driving cars need to solve this problem at the end of the day. Val.ai is a way for autonomous vehicles to bid for nearby parking spaces … autonomously! When a self-driving car needs to park itself, it can submit real-time bids for local spots occupied by other autonomous cars. If a currently parked car knows it needs to pick someone up soon, it can accept a bid and relinquish its parking spot and earn some money. The winning bidder vehicle will then get directions to the vacated spot and secure a place to rest.

WHY WE ❤ IT

It takes special talent to foresee the problems of the future and solve for them today. Val.ai addresses something that most people don’t think about when they imagine a future with self-driving cars and solves a problem while monetizing it as well! Read more about Val.ai on TechCrunch.

HOW YOU DO IT

We caught up with Val.ai creator Gabriel Ortiz, CEO and Co-Founder of Nimblestack (a product shop that specializes in applying AI and automation to useful everyday products), to ask him to share his inspiration for Val.ai.

Clarifai: What inspired your idea for Val.ai?

Gabriel: We were inspired by ThingSpace and Mapquest and the power of managing traffic with A.I. we decided to combine this technology with Clarifai’s image recognition API and Autonomous vehicles to create a new style of business. We built Val.ai (Valet) with the ability to sell its parking space to other drivers. So owners of Autonomous vehicles can make money from their very special cars.

How did you build the app?

We used Clarifai, Verizon Thingspace, Mapquest, HTTP, JavaScript, JQuery, Geolocation, HTML5, CSS3. A challenge we ran into was the short amount of time to build the software, but we think we came up with a clever way to make money from autonomous vehicles while managing to complete our goals in the allotted time!

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

The Clarifai API was actually really easy to integrate. We loved how much functionality we got for so little programming. Well done guys!

Thanks for sharing, Gabriel!

To learn more, check out our documentation and sign-up for a free Clarifai account to start using our API – all it takes is a few 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 Val.ai team (@nimblestack @aarongfranco @nothinggrinder @nimblechat) some props in the comments below. Until next time!


Clarifai Featured Hack: Recyclodroid is a recycling robot made of recycled materials

The Recyclodroid is an advanced robotic device that uses image recognition as it moves around to determine if objects in its path are recyclable. Not only does the robot have an environmentally-friendly mission, it’s also made out of recycled materials. Basically, you’re looking at a real-life Wall-E!

Climate change is real, despite what non-scientists would have us believe. That’s why the Recyclodroid is on a mission to help the environment, one recyclable at a time. The Recyclodroid is a robot that can identify recyclable objects in its path as it navigates the world. It’s made up of a USB webcam mounted on a robotic car built from household materials like toothpicks, Gatorade caps, and a broken calculator case. The webcam captures video of its surroundings and uses the Clarifai API to “see” whether the object in its path is recyclable or not.

recyclodroid

WHY WE ❤ IT

We’ve got a soft spot for fellow do-gooders, so the environmentally-friendly mission of the Recylodroid was right up our alley. We also love it when developers use Clarifai’s software with their own hardware, and bonus points to the Recyclodroid for being made of common household items! Try it out – here’s Recyclodroid’s GitHub repo!

HOW YOU DO IT

We caught up with Alice Lai, a rising senior at High Technology High School who loves robotics, hardware hacking, and using technology for social good, to talk about her inspiration for Recyclodroid.

Clarifai: What inspired your idea for Recyclodroid?

Alice: I was trying to come up with an idea for my project for the ByteHacks hackathon and I had brought with me a DIY robotic car I had made out of household materials. I started to play around with ideas and thought it would be cool to make it a self-driving car through computer vision. Another hacker commented that it was super cool that I was reusing household materials to create my project, and that gave me the idea to make a robotic car focused on recycling and environmental sustainability.

How did you build the app?

Recyclodroid is a robotic car built out of household materials (i.e. toothpicks, Gatorade caps, broken plastic case of a calculator) with a focus on recycling. A USB webcam is mounted on this robot, which then uses the Clarifai API to “see” whether the object in front of it is recyclable or not based on a long array of things that are recyclable.

I used the Javascript client for the Clarifai API to program the computer vision aspect of my project. I also used the Photon hardware development kit to control the movement of the robotic car (to move forward based on if the object was recyclable or not) and wrote a shell script to automate the process.

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

The Clarifai API was super easy to use and it was really nice how all the tags/concepts that the image recognition outputted came in a large JSON file.

Thanks for sharing, Alice!

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 Alice some props in the comments below. Until next time!


How Vintage Cloud uses Clarifai’s visual recognition API to archive and document old films

Industry

Film & Video

Use case

Understand and catalogue video content at scale

Result

Converted old film archives into searchable online video whose value can be preserved and monetized

peterenglesson1Peter Englesson, Co-Founder & CEO Vintage Cloud

Peter graduated from the Swedish National Film School in 1978. He holds a long-standing career in the film world, working as a Film and Sound Editor in several European countries. In the 1990’s, he introduced Digital Editing Workflows in Scandinavia and worked as a Post-Production Consultant on major international feature films such as the Bond movie “Tomorrow Never Dies” (1997).

Vintage Cloud is the fastest way to preserve, digitize and monetize your film assets. Based on Steenbeck’s legendary film transport, Vintage Cloud software’s “Smart Indexing” uses artificial intelligence and machine learning to dramatically increase the speed and precision with which metadata can be included within the film asset.

Introduction

The history of film goes back over 100 years – to the 1890s, in fact. Since that time, it’s estimated that more than half a million movies have been created. It wasn’t until 1925 that John Logie Baird gave his first demonstration of television – and it’s probably conservative to say that over 40 million hours of content have been created in the 90+ years since then.

But movies and TV aren’t the only sources of shows and films that were committed to film. Think of all the commercials, all the documentaries, all the in-house productions, all the public information footage that’s been created – and that’s just scratching the surface.

And here’s the thing – much of that material has been lost. But, huge amounts of it remain, in a wide variety of film archives around the world – both commercial and non-commercial. Those huge amounts of content have significant social and historical value. More than that: that content also has real monetary value.

Challenge

How can you understand millions of hours of video content without having to watch it all?

There are, however, difficulties in working with this archive material. The first challenge is that film degrades over time. It deteriorates if it hasn’t been stored in ideal conditions; it gets scratched through mishandling and sprocket holes start to fray through repeated playing. It’s valuable – but incredibly fragile. For many organizations, that means that capturing it in digital form has become a matter of urgency – before its physical condition means that it becomes inaccessible.

Rising to that first challenge is relatively straightforward. The second challenge is much more difficult: understanding exactly what content is included within the film reel. A documentary producer might be looking for footage of a steam train in the 1930s. How would they locate samples of the appropriate footage?

image2

Vintage Cloud is a company that was created to address these challenges – and the opportunities that solving those challenges presents. It specializes in transferring old film archives into digital files. In itself, that’s a fairly well-understood process – so long as appropriate care is taken of the fragile source material.

What’s much harder than simply converting the content into computer-storable, computer-retrievable files is to make sense of what those files contain – so that their value can be preserved and monetized. What’s needed is ‘metadata’ – information about the content, in as much detail as possible. Unfortunately, with much archive material, that metadata just doesn’t exist. Where it does exist, it’s often in rudimentary, unstructured, written form that requires substantial editing.

“During our film digitization process, which is in real-time in 4K resolution, we extract keyframes every third second. We send these keyframes to Clarifai for indexing so that metadata is completed in parallel with digitization. This maximizes the efficiency of our workflow while enhancing it with extremely detailed AI results.” – Peter Englesson, CEO & Co-Founder Vintage Cloud

Solution

With Clarifai’s visual recognition API, Vintage Cloud was able to understand the full content of hours upon hours of video in a matter of minutes.

Vintage Cloud quickly realized that the secret to the successful transfer of archive material to the digital world lay not just in capturing the source – but making the extraction and creation of metadata from the source as simple, straightforward, and fast as the physical transfer. The company quickly discovered that the manual method of watching and documenting film was not scalable and would take entirely too much time and manpower.

A period of investigating the possible alternative approaches led Vintage Cloud to Clarifai and its artificially intelligent visual recognition system – which, in effect, can take the place of a human being viewing all the footage in its entirety while frantically taking notes.

image1

“We found the tagged results amazing,” says Peter Englesson, CEO of Vintage Cloud. “The Clarifai vision recognition found objects that human eyes would never have found, especially not in real time. The results were stunning – even though much of our footage consists of “vintage” images, those items that you can’t find in today’s world. Take something like helmets, for example. Helmet design has changed radically over the last hundred years – but Clarifai AI is able to identify helmets from 1920 up to today. That’s astonishing.”

“Clarifai’s visual recognition AI can understand concepts with better-than-human accuracy in many cases. For example, the accuracy for “helmet” is fantastic even though the design of helmets has changed radically over time from the early 20th century until today.”

That ability to automatically detect objects that appear in the archived material – not only with the highest accuracy but also far faster than a human eye could ever achieve the feat – means that the creation of easily searchable metadata is transformed, as is the value of the archive asset.

Implementation

Quick and Easy Implementation

With a team of two talented developers, Vintage Cloud built a platform that automatically creates a keyframe every third second, while digitizing old film content, and sends the image to the Clarifai API – returning it, fully indexed, in real time.

“Thanks to my background as a film editor, I recognise the power of keyframes,” says Englesson. “It allows you to overview a massive amount of film footage without the need to view hours of video.”

Clarifai AI produces an enormous amount of tags while indexing, which gives Vintage Cloud the flexibility to narrow down results into ones that are relevant to a particular subject. The Vintage Cloud “Smart Indexing” platform has built-in efficient “search” functionality to filter out, for the time being, tags that are not needed. For example, one could search only for race cars in films and exclude all other vehicles like buses and trucks.

“This function makes it very easy for our clients to search throughout their whole catalogue for items or tools,” continues Englesson. “For example: if the client searches for ‘vintage car’, they’ll find all the instances within the archive where cars built between 1920 and, say, 1970 can be found.”

“The Clarifai API was very easy to use – our developers were able to implement Clarifai’s tools very quickly. On top of that, Clarifai’s support has been excellent – they worked with us to improve the quality of our visual recognition results for our unique use case.”

Vintage Cloud’s Smart Indexing capability is an integral part of its Steenbeck Digitizer – but it also works as a standalone application for material that has already been digitized. The fact that Vintage Cloud is a leader in helping owners of film archives derive the true value of their assets is due in no small part to the remarkable technology that it leverages from Clarifai.

DIY with Clarifai

Now that you’ve been inspired by Vintage Cloud’s automated video metadata 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. If you want more personalized insight into how Clarifai’s technology can optimize your unique business, let us know at sales@clarifai.com and work directly with our Data Strategy Team and machine learning experts!


Clarifai Featured Hack: Terrabeasts are the AI-powered Tamagotchis you wish you had

Terrabeasts is an app that lets you keep a virtual pet in your phone. You can feed it by taking photos of real food, which is then identified by Clarifai’s food recognition model. Depending on what you feed your Terrabeast, it will grow into … well, a beauty or a beast, naturally!

Remember the Tamagotchi craze? If you do, congrats, you’re old like us. If you don’t, sorry, kids – affordable housing and healthcare aren’t the only things you’ve missed out on (too soon?)! Terrabeasts are like Tamagotchis (which are like virtual pets, you plebe) in your phone, except you can feed them “real” food! Just take a photo of food in real life and watch your Terrabeast chow down. Based on the food’s “sustainability score,” your Terrabeast will evolve and grow according to its diet.

WHY WE ❤ IT

We love it when developers build apps that are not only fun and creative (not to mention stinking adorable!), but are also secretly teaching users a life lesson. By assigning a “sustainability score” to the food users feed to their Terrabeasts, this app is gently making users more aware of their environmental impact. “Like” Terrabeasts on Facebook and learn more about this amazing project!

HOW YOU DO IT

We caught up with Alex Zaman, software engineer at ZocDoc and one of the creators of Terrabeasts, to talk about his team’s inspiration for Terrabeasts.

Clarifai: What inspired your idea for Terrabeasts?

Alex: We wanted a way for people to get emotionally engaged in the way their food choices were impacting the environment. Presenting the information through a cute pet offered a way to teach people without being pedantic.

How did you build the app?

Designs were created through adobe products and Invision. The backend was an API server created through flask and loaded onto amazon.

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

The Clarifai API was extremely straightforward and having a list of pre-created models was extremely helpful to get started without having to do massive amounts of training on the AI.

Thanks for sharing, Alex!

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 Terrabeasts some props in the comments below. Until next time!


Clarifai Featured Hack: Perfect your workout technique with Monopose

Monopose is an app that uses visual recognition to help you perform workout exercises with flawless technique. With Monopose, you can finally make sense of all those complicated machines at the gym!

Need to get swole but don’t have the means to hire a personal trainer? Monopose can help you perfect your workout technique by using visual recognition to evaluate and improve your exercise posture! Use the Monopose app to scan a QR code on gym equipment to help you better understand how the equipment is meant to be used. Then, turn on your camera and scan your current posture and Monopose will let you know if you’re doing it right or wrong!

monopose2

WHY WE ❤ IT

We’re really excited anytime someone uses our Custom Training product to teach our AI new concepts … like exercise poses! Can’t you tell by our amazing physiques that this app would be right up our alley? No? Well, fine, maybe we will hit the gym more now that Monopose can help us refine our technique. Learn more about Monopose on Devpost!

HOW YOU DO IT

We caught up with Monopose creators Harsh Patel, Ian Tobin, and Charlton Smith to learn what inspired their award-winning app and how they built it.

Clarifai: What inspired your idea for Monopose?

Charlton: A lot of people tear their ligaments or develop a hernia when exercising. We just want to help people avoid silly mistakes and use the equipment properly.

Harsh: What inspired us was the fact that we understood the problem. So many people at the gym don’t know how to properly work out and end up injuring themselves. We want to solve this through our Monopose app.

How did you build the app?

Ian: We used Java, Android studio, and the Clarifai API. I was also using html5 and css to start on a website advertising the app.

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

Harsh: The Clarifai API was fun to work with! We loved testing the camera and making it able to pick up certain positions by either saying it was good or bad. Your Clarifai rep was definitely helpful in getting us the answers to problems we had. I think the camera crashed like 17 times before our live demo!

Ian: The Clarifai API was enjoyable to use. I always wanted to work on image recognition, and Clarifai made it easier to do. We did have some issues at first with teaching it certain images, but we did get help from a mentor to resolve the issue.

Charlton: Training Clarifai to understand your postures was tedious but fun. Our team really enjoyed how Clarifai was able to tell the difference if you train it well.

Thanks for sharing, Monopose 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 Harsh, Ian, and Charlton some props in the comments below. Until next time!


Clarifai Featured Hack: Wishbnb recommends dream vacations based on your Pinterest boards

Wishbnb is an app that recommends dream vacations based on Pinterest boards, with a twist – these dream trips are meant for terminally ill children and their parents, and the recommendations can be used to create a crowdfunding listing to which others can contribute!

If you love the Make-A-Wish foundation’s mission, you’ll love Wishbnb – an app that takes a Pinterest board and turns it into a dream vacation for terminally or chronically ill children and their families. Children and their families “pin” dream photos to a Pinterest board and Clarifai helps analyze the selections and pick out top destinations based on trends in the photos. Airbnb suggestions also populate with the recommendation, and from there, the listing can be crowdfunded by the community. Check out the live app here!

WHY WE ❤ IT

Our mission at Clarifai is to understand every image and video to improve life, and this app definitely falls under “improve life.” Vacation recommendations from a Pinterest board are super cool, but we love that it didn’t just stop there – turning a fun hack into an amazing tool to help people in need goes the extra mile. Explore the GitHub repo!

HOW YOU DO IT

We caught up with Austin Lubetkin, student at Florida Polytechnic, to talk about his inspiration for Wishbnb.

Clarifai: What inspired your idea for Wishbnb?

Austin: My younger sister Sydney was chronically ill as a child. When she was in the hospital we told her she could have anything she wanted, so we got her Diva the diabetes dog. Looking back I see how that experience brought hope and joy to her life and I wanted to create an app that used AI to bring similar experiences to those less fortunate.

How did you build the app?

I made the whole website with JavaScript. There were some great tutorials on the Clarifai blog that helped me understand the JavaScript API. I then ported the website to native Android and iOS apps with PhoneGap. The entire project was made in 24 hours at WHACK and I won best iOS app.

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

I was really impressed with the accuracy of Clarifai. We were making an app aimed at children so we were testing with cartoons and other similarly abstracted subject matter. Clarifai continually gave accurate and relevant tags we could use to match users to their dream destinations. A great example is a photo we gave of Bambi. Clarifai was able to match it to animals which was one of the relevant tags that helped match a user to Yellowstone National Park.

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!


How Photobucket uses image recognition to protect its community from unwanted content

Industry

Online Community & Photo Marketplace

Use case

Automatically flag and moderate unwanted nudity from user-generated content (UGC)

Result

Increased hit ratio for unwanted content by 700x, mitigated Trust & Safety risks, created a better user experience

Photobucket is the one-stop shop for storing, accessing, and sharing photos. Services offered include:

  • Safely upload and store your photos from anywhere 
  • Transform your photos with easy to use editing tools
  • Quickly share your photos with just one click
  • Browse and search for content uploaded by the Photobucket user community
  • Turn your photos into stunning print products

Mike Knowles,  Lead Developer @ Photobucket

Mike is a lead developer at Photobucket where he works on the REST APIs and backend processing tasks that support the front-end web and mobile applications. Mike and Clarifai connected when he was researching ways to apply advancements in machine learning to improve Photobucket’s legacy processes for search and content moderation. Mike is passionate about building great products and applying new technologies in practical ways to improve the user experience.

Challenge

How do you moderate user-generated content (UGC) at scale?

Photobucket is one of the world’s most popular online image and video hosting communities. The platform hosts over 15 billion images, with two million more being uploaded every day. While user-generated content (UGC) is Photobucket’s bread and butter, it also poses a Trust and Safety risk of users who upload illegal or unwanted content. With a firehose of content constantly flowing in, it’s impossible for a team of human moderators to catch every image that goes against Photobucket’s terms of service.

Photobucket needed a solution that would provide a highly scalable system for moderating user-generated content while improving the hit ratio of finding offensive content and the productivity of Photobucket’s human moderation team.

“Before Clarifai, we were only able to monitor 1% of our user-generated content for illegal images. With Clarifai, we’re able to see inside 100% of the two million images per day uploaded to our site, allowing for a better user experience for our online community and our team of human moderators.” – Mike Knowles, Senior Infrastructure Developer

Solution

Photobucket uses Clarifai’s Not Safe for Work (NSFW) nudity recognition model to find and remove illegal and unwanted content from their platform, creating a safer community and better user experience for all 100 million of their members.

Before turning to Clarifai for computer vision-powered moderation, Photobucket used a team of five human moderators to monitor user-generated content for illegal and offensive content. These moderators would manually review a queue of randomly selected images from just 1% of the two million image uploads each day. Not only was Photobucket potentially missing 99% of unwanted content uploaded to their site, but their team of human moderators also suffered from an unrewarding workflow resulting in low productivity.

To catch more unwanted UGC, Photobucket chose Clarifai’s Not Safe for Work (NSFW) nudity recognition model to automatically moderate offensive content as it is being uploaded to their site. Now, 100% of images uploaded every day on Photobucket are passed through Clarifai’s NSFW filter in real-time. The images that are flagged ‘NSFW’ are then routed to the moderation queue where only one human moderator is required to review the content. Where’s rest of the human moderation team? They’re now doing customer support and making the Photobucket user experience even better.

Implementation

Automatically “see” and understand images

Using Clarifai’s NSFW recognition model with a probability threshold of 0.85 (85% likeliness that an image contains NSFW content), Photobucket saw immediate positive results in moderating UGC. When Clarifai recognizes an image uploaded to Photobucket as potentially NSFW, the image is sent to a queue for human review. Upon human review, 70% of those flagged images turned out to be unacceptable content like pornography, while the other flagged images fell in the acceptable range of swimsuit shots and questionable selfies.

Clarifai has been invaluable in improving our hit ratio for finding content with nudity and making our moderation team more productive overall. With Clarifai, we saw a 700x higher hit rate for inappropriate content. Before Clarifai, our hit ratio for NSFW images was something like 0.1% and now it’s 70% .

Protect your community and brand from harmful content

High-quality UGC is important to keep users on your platform and engaged in your community. Bad UGC, particularly in its more harmful forms of exploitative pornography and hate speech, hurts everyone. As part of their Clarifai-powered moderation workflow, Photobucket’s human moderators looked at accounts associated with flagged NSFW images to find even more unwanted content. Within the first month of using Clarifai, Photobucket was able to discover two child pornography accounts that they then passed onto the FBI. Not only was Photobucket able to make their platform safer, but they were also able to make the internet and the world a better place.

“Clarifai has helped mitigate the legal and financial risks associated with running an online community and content hosting business by identifying unwanted images on our platform. But, more importantly, Clarifai has helped us make the internet a safer place.”

Quick and easy implementation

Photobucket developer Mike Knowles was looking for a quick and easy way to implement machine learning-based image recognition technology in his tech stack. After ruling out building machine learning in-house as too costly and inefficient in the long-run, Mike decided using a visual recognition API would be the best way to validate his idea and go to market quickly. He tested half a dozen visual recognition APIs including Google Cloud Vision and Amazon Rekognition before deciding that Clarifai offered the best possible solution for his business.

Mike selected Clarifai based on the superior accuracy and ease of use of the technology, the transparency of the online demo, the completeness of the documentation, and the enthusiasm and professionalism of Clarifai’s team. He was also excited about the wide range of visual recognition models Clarifai has to offer, including the General visual recognition model that recognizes over 11,000 concepts and the Moderation model that currently recognizes different levels of nudity (e.g. explicit and suggestive) along with gore and drugs, with future plans to recognize symbols of hate and violence.

With a product team of four, Mike was able to launch Photobucket’s new content moderation workflow using Clarifai in 12 weeks from concept to internal rollout of the new moderation workflow process. With the new workflow increasing productivity for the human moderation team, 80% of Photobucket’s human moderation team was able to transition to full-time customer support.

“Clarifai has the focus and professionalism of a company that has been in business for ten years. They see beyond the dollar value of their customers and really worked with me to achieve my goals while respecting my budget. Using Clarifai gave me the results I wanted immediately, and their product roadmap gives me confidence that they will provide even more value to Photobucket over time.

DIY with Clarifai

Now that you’ve been inspired by Photobucket’s automated content moderation workflow, 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. If you want more personalized insight into how Clarifai’s technology can optimize your unique business, let us know at sales@clarifai.com and work directly with our Data Strategy Team and machine learning experts!


Clarifai Featured Hack: Check a company’s commitment to diversity with Diversif.ai

It’s common knowledge that there is a diversity problem in the tech industry. However, there’s a big gap from acknowledging a problem exists to actually fixing it. Accountability is the key to diversity and inclusion (D&I), and Diversif.ai is an app that allows you to hold companies to their word on D&I initiatives.

Last year, Clarifai signed the White House Tech Inclusion Pledge and we’re gearing up to release our first annual report detailing the steps we’ve taken toward building a diverse and inclusive company. So, when we saw Diversif.ai come out of TechCrunch Disrupt’s hackathon this summer, the app really hit home on the importance of holding ourselves and other tech companies accountable to D&I.

diversifai2

Diversif.ai allows you to enter any company’s website to gage its performance on D&I in a data-driven way. The app will scrape through a website’s images to populate, in real-time, a report of their gender, age, and multicultural appearance. The algorithm then compares this data to the data of peer institutions and produces a score relative to the industry. You can then share the data with your network or reach out to the company directly to expose the issue, thereby holding institutions accountable for D&I.

diversifai

WHY WE ❤ IT

D&I is near and dear to our hearts, so of course this app is right up our alley. It’s easy to talk about D&I initiatives but it’s way harder to actually put your money where your mouth is and show results. Using this app on our own company page, we realize that despite our commitment to D&I, even we still have a ways to go before total parity at every level in every field and we encourage you to share ideas and suggestions with us via #DiversifAI on Twitter. Check out the GitHub repo to give it a try!

HOW YOU DO IT

We caught up with one of the creators of Diversif.ai, Harry Merzin (high schooler and React fan), to talk about his team’s inspiration for their game-changing app.

Clarifai: What inspired your idea for Diversif.ai?

Harry: We saw that there was a diversity issue in tech and other industries, and wanted to empower consumers to support companies that are committed to solving it.

How did you build the app?

We used node, react, phantomjs, and of course, Clarifai. Our biggest problem was setting the app’s state correctly and managing our socket listeners to fire the correct amount of times. We were also working with two awesome, open-minded college students who were learning along the way so that caused a bit of a speed deficit. Teaching them what they needed to know to complete the app in the appropriate amount of time was, in fact, an act of magic.

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

I’ve used Microsoft’s Cognitive Services in the past, and I definitely prefer Clarifai. The response JSON is extremely straightforward, and the node SDK is fantastic. I have looked into using Google’s Cloud Vision services before, but Clarifai is still ahead in my book because of the ease of use in server and client side apps.

Thanks for sharing, Harry!

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 Harry some props in the comments below. Until next time!


Clarifai Featured Hack: Mansplainer is an app that will condescendingly explain images to you

“Mansplaining” is the all-too-common phenomenon of “a man explaining something to a woman in a condescending, overconfident, and often inaccurate or oversimplified manner.” Send the Mansplainer app a picture and have it described back to you in the worst way possible, just for funsies.

If you ask any woman in tech, she’s probably had to deal with “mansplaining” at some point in her career – you know, when a dude tells you, a woman, something you already know in a way that implies you’re some sort of simpleton without an advanced degree in whatever STEM field you worked your ass off to earn. It’s a special kind of feeling when one is mansplained to, and women shouldn’t be the only ones privileged enough to experience it. That’s where Mansplainer comes in!

Using Clarifai’s visual recognition API with the Twilio API, Mansplainer is able to take whatever image you send it via text message and describe it to you in the most condescending way possible. If you haven’t had the distinct pleasure of being mansplained to before, here’s your chance – try it now!

mansplainer

WHY WE ❤ IT

While we absolutely despise mansplaining, we love an app that can poke fun at it. Check out the GitHub repo for source code!

HOW YOU DO IT

Mansplainer was brought to you by Henry Shen, Khalid Alnuaim, Dandan Lin, and Erin Williams, courtesy of the HackNY student hackathon. We caught up with Henry to talk about the team’s inspiration for the app.

Clarifai: What inspired your idea for Mansplainer?

Henry: I really enjoy hackathons and the culture that comes with them. I love using computer science to create solutions to problems that never existed in people’s lives. There was a similar idea on Stupid Shit No One Needs & Terrible Ideas Hackathon where you talk to an app but then it interrupts you. We decided to extend on that idea by mansplaining your own photo back to you.

How did you build the app?

We used Clarifai, Twilio to handle the text messaging, the Flask python web framework, and the Wikimedia web search API. We also used food and caffeine, but we couldn’t deploy that on to the server.

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

I didn’t specifically interact with the Clarifai API – someone in our group that used it before did. But they love it!

Thanks for sharing, Henry!

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 Mansplainer team some props in the comments below. Until next time!


Clarifai Featured Hack: Discover your ancestry based on facial recognition with MiMi

MiMi is an app that uses machine learning to determine your ancestry by what continent you might have originated from based on your facial characteristics. The results might surprise you!

Do you have one of those ambiguously ethnic faces where everyone always asks, “Where are you from?” Well, if you’re not bothered by real humans guessing your origin, now computers can do it, too! MiMi is an app that uses machine learning to determine your ancestry by origin continent.

All you have to do is visit the live demo, allow the app to use your computer cam, and take a picture. Based on the picture, the app will determine the two most likely continents your ancestors came from. Give it a try!

mimi_screenshot

WHY WE ❤ IT

This is an interesting take on facial recognition that we haven’t seen before. Yes, Clarifai has its own Demographics recognition model, but that recognizes your age, gender, and multicultural appearance (otherwise known as ethnicity or race). MiMi is all about understanding your origins and where you came from based on origin location. Read more about the app on Devpost!

HOW YOU DO IT

We caught up with the diverse MiMi team – Malika from Uzbekistan, Alicia from Cuba, Geeticka from India, and Ashley from Jamaica – to learn what inspired their app and how they built it.

Clarifai: What inspired your idea for MiMi?

MiMi Team:

We were inspired by the most common question asked in Miami: “Where are you from?” We started with the idea of building a software that can tell you about your ancestry depending on your voice intonation. After further refinement, we settled on using facial recognition due to the availability of Clarifai API in the hackathon. We were also inspired by this video on testing the DNA of diverse people in order to bring them together.

How did you build the app?

We created it using Clarifai, HTML, JS, CSS and Adobe Illustrator.

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

We were able to reach out to a Clarifai sponsor and were able to find a UI for training our model as opposed to coding it with JS.

Thanks for sharing, MiMi 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 a few 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 MiMi team some props in the comments below. Until next time!


Clarifai Featured Hack: TYP helps you automatically sort large photo libraries into new folders

Any shutterbug can attest – taking photos is the fun part, sorting through photos at the end can be a hassle. Most digital cameras upload all your photos into a folder on your computer by date. TYP is an app that lets you sort pictures on your computer into descriptive folders by the actual content in your pics!

Large, general photo libraries can be a pain to sort through. For the most part, digital cameras upload photos onto your computer in folders sorted by date. You can’t search for a specific photo, like the one where your dog is humping a stuffed bear (what, just me?), and you can’t easily sort your pics into more relevant folders based on subject matter. Well, TaggedYourPic (TYP) is an app that allows you to do just that!

TYP works by taking a folder that has pictures in it and getting words that describe those pictures via the Clarifai API. Then, it lets the user choose which words are most important to them, where to create new folders, and then copies each picture into a new, descriptive folder for easy sorting and searching.

WHY WE ❤ IT

Productivity hacks are always a win, particularly when they’re solving a problem that many people have. Check out the GitHub repo for TYP to try it on your own pics!

HOW YOU DO IT

We caught up with Myles Bradley, student at Coe College studying mathematics and computer science, to talk about his inspiration for TYP.

Clarifai: What inspired your idea for TYP?

Myles: We were inspired by the great opportunity to save a lot of people a lot of time and strife thanks to the great information that Clarifai’s API provided.

How did you build the app?

We used python 2.7. We imported tkinter, os, and shutil. We struggled with sorting the tags for the user to choose from based on how often the tag appeared between the group of photos. We also struggled with coding the program to put the photo in the tag that was most strongly correlated to it when there was more than one chosen tag that applied to a photo.

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

The Clarifai API was super easy to use once we had the right software installed. It was a lot of fun and made our project very easy to accomplish for us. We couldn’t have asked for a better API when it came to this project.

Thanks for sharing, Myles!

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 Myles some props in the comments below. Until next time!


Clarifai Featured Hack: Use NSFW Blocker to protect your eyes from the internet

The internet can be a scary place lurking with things you can’t unsee. NSFW (Not Safe for Work) Blocker is a Chrome extension that uses Clarifai’s NSFW recognition model to block images that contain unwanted nudity.

Have you ever Googled something only to be rewarded with unwanted and irrelevant content? Perhaps with some genitalia involved? Don’t worry, you’re not the only person to innocently search for “cream pie” without including “recipe” at the end (pro tip: don’t do it). NSFW Blocker is a Chrome extension that will warn you of unwanted nudity from your browser, blocking the offending image and giving you the option to click to proceed.

nsfwblock

WHY WE ❤ IT

Any app that helps us avoid a full frontal assault on the eyes is a good app! Check out Clarifai’s NSFW model to see how the technology works, and visit the NSFW Blocker GitHub repo to learn more about the hack.

HOW YOU DO IT

We caught up with Kaizhao Liang to talk about the inspiration for NSFW Blocker.

Clarifai: What inspired your idea for NSFW Blocker?

Kaizhao: When we were brainstorming ideas, we found out there was a NSFW model already, so we decided to use that model to do something.

How did you build the app?

We use Python for the backend and Javascript for the front end.

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

We used the Clarifai API and trained it with hundreds of online pictures to give us an accurate representation of which pictures are NSFW and which pictures are not.

Thanks for sharing, Kaizhao!

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 Kaizhao some props in the comments below. Until next time!