General
Catalyst Zia Services includes a wide set of AI/ML powered components used for processing, analyzing, and fetching valuable insights from both textual and visual content such as documents and images. It includes the Face Analytics, Optical Character Recognition, Identity Scanner, Image Moderation, Object Recognition, Barcode Scanner, AutoML and Text Analytics. You can integrate the functionalities of the Zia components in your application seamlessly by incorporating the readily available sample SDK code templates in Java, Node.js and Python. You can also access these components through their API endpoints.
No, your data will not used for ML model training purposes. Catalyst does not store any of the files you upload in its systems. The files you upload are used for one-time processing only. Catalyst components are fully compliant with all applicable data protection and privacy laws.
OCR
Optical Character Recognition supports 9 International languages and 10 Indian languages. You can learn more about the entire list of supported languages from this page.
AutoML
You can train the powerful Zia AI using your own dataset and analyze a set of training data to predict the outcome of a subset of that data. You can build and train Binary Classification, Multi-Class Classification, and Regression Models, and obtain insightful evaluation reports.
AutoML enables you to easily analyse a set of training data and generate predictive analytics on the dataset without requiring you to be involved in the complex ML training process that involves selecting the right ML algorithms to train the model, preprocessing or profiling the data, or managing the models. Catalyst implements the required model training, and automates the entire process for you.
QuickML on the other hand provides you more control in managing ML and data operations, and lets you build, test, deploy, and monitor effective ML models end-to-end. You will be able to perform a host of data preprocessing and transformation operations, pick the ML algorithms for training, and design the pipeline exactly as you need, all with no coding involved.
Identity Scanner
Identity Scanner is currently not available to users accessing from the EU, AU, or US data centres. This document processing feature is only relevant to Indian users and is only available in the IN DC (Indian Data Center). Users outside of India from the other DCs can access the general OCR component to read and process textual content.
Text Analytics
You can make use of our Catalyst Zia Text analysis to identify the sentiment on a given text. You can access it via Catalyst API’s or through our SDK methods by passing the text as input. The AI will identify the emotion and gives the sentiment with an accuracy level.
Facial Comparison
You can use our facial comparison API and provide your source and identity image to check the results of the face comparison. you will get the response of the prediction with a confidence score.
Image Moderation
You can try our image moderation API or SDK method in order to identify the category of the content in the image. It recognizes the following inappropriate content in images and returns them in the response. The response also contains the probability of each criteria(racy, weapon, nudity, gore, drug) with their confidence scores, and the prediction of the image being safe_to_use or unsafe_to_use.
Barcode Scanner
You can make use of the zia barcode scanner SDK method or catalyst API in order to extract the content embedded in the barcode image.