If you want to start using Artificial Intelligence or create your own digital inspector the sentin EXPLORER is your tool – from data to deployment.
To get your digital inspector you need these steps:
The sentin EXPLORER helps you to find the best configuration for your project. It will hide complex features, if you do not need it so that you can focus on the important tasks, and offers preconfigured projects.
The training of your digital inspector needs data. You can use a remote connection to easily share your images, because the training needs special hardware for AI. Using the cloud connection is the fastest and most cost effective. If you want to keep your data local, you can later export your project e.g. as a .zip file.
The training data needs to be organized. You can use sorting and filtering to find certain images or clean up your data. The project view will also give you an overview of how many images are labeled (e.g. defects).
The sentin EXPLORER allows you to prepare and label your data in the Desktop App. This is needed to show the artificial intelligence what you are searching for and what the digital inspector should learn. There are many annotation types so that you can mark defects with boxes, polygons or label a complete image.
Some images have more details than a monitor can view at once e.g. 16 bit .dcm or tiff files. The sentin EXPLORER offers multiple filters, contrast and color features to enhance images and make things visible for the human eye,.
Sometimes certain areas need to get checked or you need some statistics to evaluate the image quality. The sentin EXPLORER offers special features to focus on certain areas or view statistics like the median, the signal to noise ratio (SNR) and others.
The sentin EXPLORER allows you to calibrate the view for dimensions, so that you can measure sizes. You can also view the line profile of areas to evaluate image quality indicators (IQIs).
The sentin EXPLORER allows you to do all the required steps preparing for training.
For most cases the training is individual – just in a few cases it may rely on predefined models and data.
If your dataset is ready, we will train your inspector and integrate it. You can use the sentin EXPLORER to view and test the results.
This table shows different AI tasks and inspector types. The project template you used should be configured to correctly prepare the data for training.
|AI Type||Effort & Data Requirements||Evaluation time||Localization|
Before you deploy your AI model into a productive environment you should test it and validate the results. You can send a stack of images to the model and view the results.
Often detecting something is not enough. Sometimes you have to check for special conditions and combinations of defects e.g. the size of flaw or the number of flaws.
Sometimes you need to compare models and their performance. The sentin EXPLORER offers a model overview and shows you detailed information about the updated AI models.
When your dataset is AI ready and a model has been trained, you can run the evaluation with a single button click within the Desktop App – even for a stack of images. If your model has been integrated into a machine, this process is silent or even fully automated in the Evaluation Engine.
The algorithms can give you a confidence in their decision – this helps you to detect critical cases. If you have multiple use cases or inspectors trained & deployed, you can choose between them.
Sometimes you need to show the results to someone e.g. if you create a report. The export feature labels the image and copies it to your clipboard, so that you can copy & paste it everywhere you want to.
When your system has run for sometime you may want to improve the accuracy in certain edge cases (e.g. rare defects). With the retrain feature you can easily improve your digital inspector with new data.
If you have used the retrain feature, you can update the digital inspector running in the Evaluation Engine and deploy it to production from your Desktop App.
Is your company ready for AI & Machine Vision projects?
We prepare your image data together with the sentin EXPLORER and our experts.
Together, we take a look at your use case and decide whether we are the right partner for you.
If your use case is suitable for using the full potential of AI for image analysis, you structure and annotate your data with us.
Goal: a data set optimized for AI.
We adapt our AI models & interfaces to your use case.
Your requirements may include specifications regarding error types, evaluation speed or accuracy. We select the appropriate AI models and architectures and train them for you using your data set.
Likewise, interfaces can be adapted (workflows) so that you can make optimal use of the evaluation with sentin EXPLORER.
Goal: A validated AI model for your use case.
Use the sentin EXPLORER in your production/process environment.
After the necessary adjustments have been made, you can use the sentin EXPLORER in your process/productive environment.
You will receive a license key for the use of all necessary sentin EXPLORER components.
Goal: Your automatic inspection or evaluation system.
You benefit from new features, performance updates and first-class support.
Plus, you can recalibrate your models should anything change.
Use the software as long as you need it. You benefit from all the advantages of a Software as a Service solution. Due to the continuous payment model for the license, you receive new features and performance updates as well as first-class support.
Likewise, you can use sentin EXPLORER to adapt your AI models retrospectively if something changes in your process.
Configure the sentin EXPLORER together with us as you need it. Create projects for evaluations and select existing models or have your own created. All you need are sample images.
Artificial intelligence requires special hardware. Depending on what equipment you have or prefer, you can run the software in different ways.
No, sentin gives the user the possibility to train, manage and export the AI himself with the sentin EXPLORER.
No. The advantage of Deep Learning models is that it can be improved with new data. With the help of the sentin EXPLORER you can easily import and retrain them yourself. You remain independent.
Yes, after a model has been exported, you can use it on a calculation unit. You decide where you want to train and evaluate the models. However, hardware costs may be incurred for local operation. (LINK to top)
sentin uses modern technologies to make the evaluation and training as fast and convenient as possible for you. The user interface is mainly based on an Electron application. The management routines and the machine learning algorithms primarily use Python and the frameworks PyTorch and TensorFlow.
sentin offers you the possibility to automate your evaluation with software and to manage your AI models. The advantage over rule-based approaches and classical providers is the lower calibration effort, more accurate/robust detection and your independence, e.g. in recalibration.
Compared to other AI software vendors, sentin can use its own models for industrial use cases. Likewise, the ability for you to manage and calibrate your own models is a unique selling point. The customer-oriented approach and the striving for the best possible usability are always in the center of attention.
sentin is a software provider, i.e. you pay us in the form of a license model for a fully developed product.