- Full text PDF available (6)
Data Set Used
—Pixel-wise street segmentation of photographs taken from a drivers perspective is important for self-driving cars and can also support other object recognition tasks. A framework called SST was developed to examine the accuracy and execution time of different neural networks. The best neural network achieved an F1-score of 89.5 % with a simple feedforward… (More)
I declare that I have developed and written the enclosed thesis completely by myself, and have not used sources or means without declaration in the text. Acknowledgement Daniel Kirsch published the data collected with Detexify under the ODbL. 1 This dataset made it possible to evaluate many algorithms. Thank you Daniel! My advisors Kevin Kilgour and… (More)
—This survey gives an overview over different techniques used for pixel-level semantic segmentation. Metrics and datasets for the evaluation of segmenta-tion algorithms and traditional approaches for segmen-tation such as unsupervised methods, Decision Forests and SVMs are described and pointers to the relevant papers are given. Recently published… (More)
—Recent machine learning techniques can be modified to produce creative results. Those results did not exist before; it is not a trivial combination of the data which was fed into the machine learning system. The obtained results come in multiple forms: As images, as text and as audio. This paper gives a high level overview of how they are created and gives… (More)
Inactivated vaccines are commonly produced by incubating pathogens with chemicals such as formaldehyde or β-propiolactone. This is a time-consuming process, the inactivation efficiency displays high variability and extensive downstream procedures are often required. Moreover, application of chemicals alters the antigenic components of the viruses or… (More)
—This paper describes the HASY dataset of handwritten symbols. HASY is a publicly available, 1 free of charge dataset of single symbols similar to MNIST. It contains 168 233 instances of 369 classes. HASY contains two challenges: A classification challenge with 10 pre-defined folds for 10-fold cross-validation and a verification challenge.