18284484. ESTIMATING PROPERTIES OF PHYSICAL OBJECTS, BY PROCESSING IMAGE DATA WITH NEURAL NETWORKS simplified abstract (BASF SE)

ESTIMATING PROPERTIES OF PHYSICAL OBJECTS, BY PROCESSING IMAGE DATA WITH NEURAL NETWORKS

Organization Name

BASF SE

Inventor(s)

Rahul Taneja of Darmstadt (DE)

Kamran Sial of Limburgerhof (DE)

Till Eggers of Ludwifshafen (DE)

Margret Keuper of Homburg (DE)

Ramon Navarra-mestre of Limburgerhof (DE)

Sebastian Fischer of Limburgerhof (DE)

Mike Scharner of Limburgerhof (DE)

Javier Romero Rodriguez of Utrera (ES)

Francisco Manuel Polo Lopez of Utrera (ES)

Andres Martin Palma of Utrera (ES)

ESTIMATING PROPERTIES OF PHYSICAL OBJECTS, BY PROCESSING IMAGE DATA WITH NEURAL NETWORKS - A simplified explanation of the abstract

This abstract first appeared for US patent application 18284484 titled 'ESTIMATING PROPERTIES OF PHYSICAL OBJECTS, BY PROCESSING IMAGE DATA WITH NEURAL NETWORKS

Simplified Explanation

The present disclosure relates to image processing or computer vision techniques. A computer-implemented method is provided for determining a damage status of a physical object, the method comprising the steps of receiving a surface image of the physical object; and providing a pre-trained machine learning model to derive property values from the received surface map, wherein each property value is indicative of a damage index at a respective location, wherein the property values are preferably usable for monitoring and/or controlling a production process of the physical object. In this way, it is possible to reliably identify local defects and ensure that it is accurate enough to apply the chemical products in suitable amounts.

• The patent application describes a method for determining the damage status of a physical object using image processing techniques and machine learning models.
• The method involves receiving a surface image of the object and using a pre-trained model to derive property values indicative of damage indexes at different locations on the object.
• The property values obtained can be used for monitoring and controlling the production process of the physical object, ensuring accurate application of chemical products.

Potential Applications

This technology can be applied in various industries such as manufacturing, automotive, aerospace, and construction for quality control and defect detection in physical objects.

Problems Solved

1. Efficient and accurate identification of local defects in physical objects. 2. Ensuring precise application of chemical products based on damage status.

Benefits

1. Improved quality control processes. 2. Enhanced production efficiency. 3. Cost savings through accurate application of chemical products.

Potential Commercial Applications

Optimizing production processes in manufacturing plants. Improving quality control in automotive and aerospace industries. Enhancing safety measures in construction sites.

Possible Prior Art

One possible prior art could be the use of traditional visual inspection methods in quality control processes, which may not be as accurate or efficient as the method described in the patent application.

Unanswered Questions

1. What specific types of physical objects can this method be applied to? 2. How does the accuracy of damage detection compare to traditional inspection methods?

Original Abstract Submitted

The present disclosure relates to image processing or computer vision techniques. A computer-implemented method is provided for determining a damage status of a physical object, the method comprising the steps of receiving a surface image of the physical object; and providing a pre-trained machine learning model to derive property values from the received surface map, wherein each property value is indicative of a damage index at a respective location, wherein the property values are preferably usable for monitoring and/or controlling a production process of the physical object. In this way, it is possible to reliably identify local defects and ensure that it is accurate enough to apply the chemical products in suitable amounts.