17 March 2017 Real-time object-to-features vectorisation via Siamese neural networks
Author Affiliations +
Proceedings Volume 10341, Ninth International Conference on Machine Vision (ICMV 2016); 103411R (2017) https://doi.org/10.1117/12.2268703
Event: Ninth International Conference on Machine Vision, 2016, Nice, France
Object-to-features vectorisation is a hard problem to solve for objects that can be hard to distinguish. Siamese and Triplet neural networks are one of the more recent tools used for such task. However, most networks used are very deep networks that prove to be hard to compute in the Internet of Things setting. In this paper, a computationally efficient neural network is proposed for real-time object-to-features vectorisation into a Euclidean metric space. We use L2 distance to reflect feature vector similarity during both training and testing. In this way, feature vectors we develop can be easily classified using K-Nearest Neighbours classifier. Such approach can be used to train networks to vectorise such “problematic” objects like images of human faces, keypoint image patches, like keypoints on Arctic maps and surrounding marine areas.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Fedor Fedorenko, Fedor Fedorenko, Sergey Usilin, Sergey Usilin, } "Real-time object-to-features vectorisation via Siamese neural networks", Proc. SPIE 10341, Ninth International Conference on Machine Vision (ICMV 2016), 103411R (17 March 2017); doi: 10.1117/12.2268703; https://doi.org/10.1117/12.2268703


Learning deep similarity in fundus photography
Proceedings of SPIE (February 23 2017)
Contemporary deep recurrent learning for recognition
Proceedings of SPIE (April 30 2017)
Frequency-based pattern recognition using neural networks
Proceedings of SPIE (September 30 1991)
Local discriminant basis neural network ensembles
Proceedings of SPIE (April 04 2000)
Audio-visual gender recognition
Proceedings of SPIE (November 14 2007)

Back to Top