Company Filing History:
Years Active: 2024
Title: Ivan Sosnovik: Innovator in Machine Learning and Object Recognition
Introduction
Ivan Sosnovik is a prominent inventor based in Amsterdam, Netherlands. He has made significant contributions to the field of machine learning and object recognition, holding 2 patents that showcase his innovative approach to technology.
Latest Patents
One of Ivan's latest patents is titled "Training a machine learnable model to estimate relative object scale." This patent describes a system and method for training a machine learnable model to estimate the relative scale of objects in an image. The feature extractor may be pretrained, while the scale estimator is trained to transform feature maps into relative scale estimates. This method allows for the generation of a scene geometry map that indicates the geometry of the scene depicted in the image.
Another notable patent is "Recognition of objects in images with equivariance or invariance in relation to the object size." This method involves processing a template image of an object through a convolutional neural network (CNN) to create a template feature map. The input image is similarly processed, and the resulting feature maps are compared to evaluate the presence and position of the object in the input image. This innovative approach utilizes multiple convolutional layers and filters that can be converted through scaling operations.
Career Highlights
Ivan Sosnovik is currently employed at Robert Bosch GmbH, where he continues to develop cutting-edge technologies in machine learning and image processing. His work has positioned him as a key figure in the advancement of these fields.
Collaborations
Ivan has collaborated with notable colleagues, including Arnold Smeulders and Konrad Groh. Their combined expertise has contributed to the success of various projects and innovations in the realm of machine learning.
Conclusion
Ivan Sosnovik is a distinguished inventor whose work in machine learning and object recognition has led to significant advancements in technology. His patents reflect a deep understanding of complex systems and a commitment to innovation.