We work every day to improve features of our platform and build more public models for developers to use. Here’s what we’ve been up to!
Apparel Detection Model: The ‘Apparel Detection’ model recognizes over 200 fashion-related concepts. Use this model for automatic tagging to quickly identify clothing and accessories to reduce the time to website workflow. This model is great for anyone building a fashion-related app such as an e-commerce platform or a fashion curation site.
Saved Searches: Record search results so that model building experiments are easily reproducible. Saved searches drastically simplify and improve the process of optimizing high performance models. Searches are recorded at a given moment in time along with a specific model version, giving data strategists the power to track, review and fine tune models.
OCR Beta: We are excited to announce optical character recognition on the Clarifai platform. Convert images of typed, handwritten or printed text into machine-encoded text, whether from a scanned document, a photo of a document, a scene-photo or from subtitle text superimposed on an image. OCR is widely used as a form of data entry from printed paper data records.
Air-gapped on premise: Our complete platform is now available completely disconnected from the internet. You can now run our advanced AI models while guaranteeing that your data stays on site. Air-gapped deployments provide uncompromising cybersecurity by isolating your computer network from the internet and local area networks. You can integrate computer vision into your workflow while enjoying our full feature set. Our Portal user interface is included.
Collaborators: Perform as a team on our open and flexible AI platform. Fast-track progress by sharing AI with your team, or collaborators outside your company. Portal now gives you full control over the permissions available in your apps, so that you can manage the capabilities and information available to each user.
Search bar dropdown: We improved the search experience in Portal by introducing helper text to demonstrate how to do advanced searches on our platform. Searches for metadata and geolocation now pre-populate and are easily editable within the search bar. This new functionality makes it easy to modify your search and iterate.
Introducing Clarifai Portal: We’ve given our UI, now called Clarifai Portal, a facelift to enhance your user experience and to bring you new features even faster. Once you log-in you can expect a unified experience where you can manage your App Details, Account Settings, the Explore mode all in one place, keyboard shortcuts and prediction thresholding features to help you label images more efficiently, and a massive under-the-hood cleanup to give you a more performant and reliable app experience. To learn more, please check out our blog.
Search Demo: You can now discover how visual search can best work for you with our newly launched public demo of Clarifai Search, a computer vision-powered search product. The search demo allows you to automatically retrieve and discover the most relevant images from your dataset, all without the need to tag every image. You can play with it yourself on our (demo page to see the different search functionalities in action.
Updated Face Detection Model: We’ve updated the face detection model to better detect faces that are at different angles to the camera, far away from the camera, or partially obstructed. Learn more about the new enhancements to our face detection model in our model gallery.
PHP Client: Allows you to easily take advantage of Clarifai’s functionality in your PHP applications. Check out our documentation for more information.
Android SDK: The Android SDK enables machine learning directly on your device, bypassing the traditional requirement of internet connectivity and extensive computing power. For more information check out our documentation.
Amazon Web Services (AWS) Marketplace: Clarifai has become a part of the AWS Marketplace. This means that you can access all of Clarifai’s products, and receive one single integrated bill through AWS. For more information, read the press release.
Landscape Quality Model: A new model that analyzes images and returns probability scores that can help determine the technical quality of a photograph.
Portrait Quality Model: A new model that analyzes images and returns probability scores that can help determine the technical quality of a Portrait photograph.
Textures and Patterns: A model that is designed to acquire and apply knowledge for recognizing textures/patterns in a two-dimensional image.
Customized Visual Search: Visual Search (Search by Image) can now be trained at a more granular level, customized to only the images that are inside your app. This customization notably improves the quality of search. This feature is currently available to our Enterprise Tier customers only. Contact us to learn more!
Usage Dashboard: Displays real-time usage data, as well as historical usage data for your account. The real-time graphs represent the usage within the current monthly billing cycle. The historical data can be filtered by selecting different monthly billing cycles. To find your usage, log into your Clarifai account and then click on the “Usage” section.
Face Embedding Model: The ‘Face Embedding’ model analyzes images and returns numerical vectors that represent each detected face in the image in a 1024-dimensional space. The vectors of visually similar faces will be close to each other in the 1024-dimensional space.
Base Workflow: Allows you to build a custom trained model using the knowledge base from any of our public models (not just the General Model). This increases the accuracy of your custom model by building on top of a Clarifai model which has closer resemblance the to the model you wish to build. Our blog has more details on how it works, and learn how to take advantage of it.
Workflow Predict (Beta): Workflows encompass one or more Public or Custom models. You can make a predict operation on a Workflow endpoint which will return results from the multiple models connected to that workflow. Learn more about it in our Guide.
Moderation Model: A new model that analyzes an image and returns the confidence scores in regards to if gore, suggestive content, explicit content, or drugs are within the photo.
Video Support in V2 (GA): We released Video support in V2 for public models! You can make predict calls with video inputs. Read more about it in our Guide.
Mobile SDK (Limited Preview): We have released Clarifai’s Mobile SDK which enables machine learning directly on your device, bypassing the traditional requirement of internet connectivity and massive computing power. In order to gain access, please submit your information on the form on our Mobile SDK page. You will need a Clarifai Account to request access to the SDK.
Model Evaluation (Beta): We just added a Model Evaluation tool to our Custom Training! This feature will allow you to test the performance of your custom trained model before using it in the production environment. This tool is currently available on the Explorer only. Learn more about the model evaluation feature in our documentation guide!
API Keys: developers can authorize their API calls through API Keys. These Keys contain finer level of scopes, which enables the developer to create a “predict-only” or “search-only” key, restricting unauthorized API calls, and making their application more secure. Keys can be accessed from Developer Hub and more details are found in our Guide. We also wrote a blog to talk about why we introduced API Keys to our platform!
Predict Parameters: we are enabling our developers to customize their predict requests to receive exactly what they require in the response. We have introduced 3 capabilities:
Video Support in v2 API: released in private beta, developers can request access to the API that allows them to make predict calls on videos as the input.
Geo Location: allows developers to add location metadata (longitude, latitude) to inputs, and perform a search within a bounding geographic region. See our docs for full details.
Focus Model: launched a new model that analyzes an image and returns 1) the overall focus value (probability that there is an in-focus region within the image), and 2) a bounding box and focus density for every in-focus region within the image.
Demographics Model: launched a new model that analyzes images and returns information on age, gender, and multicultural appearance for each detected face based on facial characteristics.
Logo Model: launched a new model that analyzes images and returns probability scores on the likelihood that the media contains the logos of over 500 recognized brand names.
Model Gallery: introduced a new gallery to showcase all of our visual recognition models. You’ll find information about each of our models, view code documentation, and try them out through our demo.
Multi-language Support in v2 API: all of the languages that were available in our v1 API are now available in our v2 API! We support 22 languages other than English for our Predict calls.
Face Detection Model: launched a new model that returns the probability that an image contains faces as well as bounding box location coordinates.
Apparel Model: this model understands various fashion and accessory items and is best for identifying clothing against a white backdrop like in your favorite e-commerce stores.
Celebrity Model: recognizes a wide assortment of famous people and public figures.
Custom Training (GA): finalized Custom Training and fixed any bugs that came up for testers.
Visual Search (GA): finalized Visual Search and fixed any bugs that came up for testers.
Custom Metadata: allows developers to add any custom information (for example, price or SKU) to data inputs. This custom information is also fully searchable, just like your images!
Custom Training (Beta): allowed concepts to be added/removed from models, after a model is created; allowed models to be created without providing a list of concepts.
Custom Training (Alpha): allows developers to build a visual recognition model in a matter of seconds using only a handful of data examples. Developers can tailor our visual recognition technology for their specific needs, with a few clicks.
Visual Search (Alpha): Visual Search lets developers easily perform search by tag, search by image, and search by a combination of images and tags.
Food Model: you can start building incredible (and tasty) apps that recognize over a thousand types of food down to the ingredient level!
Upgraded Demo: we launched a new demo to give people an easy and eye-pleasing way to test the tags on any image or video!
Forevery integration with Google Drive: sync your photos stored on Google Drive with the Forevery app, so you can search and view all your photos in one place!
Travel Model: Our new Travel image recognition model automatically identifies travel-related concepts in pictures and video and can be used to build and improve apps in the travel, leisure, and hospitality industries.
Forevery integration with Dropbox: sync your photos stored in Dropbox with the Forevery app, and add our image recognition capabilities to your personal photos!
There were many awesome features that were added prior to May 2016 that haven’t been logged here.