AI-SORTER: Advanced inspection using vision and AI
Advanced inspection equipment using vision and artificial intelligence
Classification of products in slaughter houses
Deep Learning is one of the branches of artificial intelligence that is increasingly present in automated manufacturing processes.
AI-based computer vision offers a multitude of solutions to easily solve the most complex vision and classification challenges.
This technique manages to analyze images in a way very similar to that of a human being by training convolutional neural networks, an image segmentation system that quickly adapts to new samples without the need to reprogram algorithms, simply by retraining the system.
Among the most notable applications of Deep Learning are:
- Product classification and identification
- Product quality verification
- Locating, counting and checking the correct placement of parts and products in their package
- Reading alphanumeric characters on complex surfaces such as transparent films with variable backgrounds, printing errors or lack of flatness.
Easy AI ® technology
INSPECTRA offers optional image processing using artificial intelligence across its entire range of equipment. To facilitate the creation of inspection programs with AI, we have a set of tools that give customers autonomy when creating new inspection programs and putting them into production.
IMAGE CAPTURE AND LABELING
AI SORTER equipment allows you to record the set of images necessary for training neural networks using the following tools:
- (ISS) Scheduler System: ISS application operating interface allows the option of saving 100% of images in different directories for classification during capture.
- (IPB) Production Browser: IPB allows the copy of images from the equipment to the training PC, being able to save them individually or in batches in different directories.
- Labeling Software: We also have different work tools for labeling images, so that batches of images can be reviewed and labeled easily in a very short time.
NEURONAL NETWORKS TRAINING
INSPECTRA provides, together with its equipment, a deep learning tool for training and validating the neural networks.
Our DEEP LEARNING software allows anyone with basic computer skills to train neural networks.
The software has the following functionalities:
- Intuitive, easy-to-use user interface
- Image bank augmentation through image pre-processing
- Selection of pre-trained neural networks of different complexity and number of layers
- Quick workouts
- Unlimited learning.
- Visualization of results with heat maps to validate neural networks
- Automatic generation of reports
IMPLEMENTATION OF ARTIFICIAL INTELLIGENCE PROGRAMS
INSPECTRA equipment allows the rapid start-up of a neural network, allowing the start-up of new inspection programs in a few hours, providing the following advantages:
- Loading new trained networks in two steps (copy and click)
- Processed in REAL TIME LOCALLY without the need for a cloud connection
- Full control over your own data, it is not shared with external servers
- No inference/training costs or annual license
- Supervision of production operation using INSPECTRA PRODUCTION BROWSER software
Classification of products in slaughterhouse cutting rooms
In certain food processes in the meat sector where food is processed in line, it is common that at the end of the cutting lines it is the operators who identify the products and decide which further processing line they should go to.
This task is tedious and costly and can be replaced by a trained vision system for automatic sorting of the products, which allows the automation of the following processes. AI-SORTER is an automatic product classification equipment in real time by Deep Learning. It is used to classify different product references or categories. The equipment allows the classification process to be automated, reducing the error rate and significantly increasing effectiveness.
At the same time as classifying, the system detects quality defects, as once the product category has been identified, a specific quality inspection algorithm is executed, being able to detect contamination and defects in the slaughtering process.
This automation of the classification process in real time is achieved by training a neural network from thousands of images. Images are introduced and labelled indicating the reference with which we want the system to identify the product. In other words, the more images the system receives, the more this neural network is trained, until the system “learns” to identify the different product categories on its own.
Detection of foreign bodies and other quality failures
AI-SORTER allows the simultaneous processing of several neural networks, which allows different checks to be carried out on the same equipment, such as classification and quality inspection.
The AI-SORTER is suitable for inspecting trays with the product before sealing the container, detecting quality defects distinguishable in the upper image of the tray (contamination, improper disposal of the product,…).
The AI-SORTER also allows the inspection of bulk product on a conveyor, detecting foreign bodies with high efficiency.
The equipment also allows the inspection of sealed trays, detecting noticeable quality defects on the upper face of the container as it passes through the inspection point.
What are its advantages?
High inspection yields
No reprogramming of algorithms necessary for introduction of new product categoriess
Reduction in labour costs
Functionalities
- Automatic product identification
- Detection of quality defects
- Product count
- Anomaly detection
- Several inspection points with the same equipment*
*Depending on application - Simultaneous processing of several neural networks
- Unlimited learning
- Local processing
- Communication with other systems
- Production monitoring
Specifications
MEAT AI-SORTER
The AI-Sorter equipment has an image capture system composed of high-resolution RGB matrix cameras and LED lighting system, which allow to adopt optimal conditions for in-line image capture of the products contained in the cartons.
The monitoring and control module is integrated by a touch screen and an electrical cabinet, allowing maximum control of the process and of the inspection and sorting programmes.
The equipment can include a roller conveyor that is coupled to the conveyor belt already installed in the plant. The products are placed on plastic boxes, and are moved along the belt until they are analysed by the camera and then classified by the Deep Learning system according to their category or type of product.
For the implementation of the Deep Learning software, in charge of classifying the different types of products, INNDEO&INSPECTRA’s technical service, together with the client, uses the Deep Learning tool, by means of which the classification of the products will be created and trained.
DO YOU NEED MORE INFORMATION?
If you want more information about the AI-Sorter equipment, fill in your details and receive the catalogue by email
