No abstract

Evaluating the style of handwriting generation is a challenging problem, since it is not well defined. It is a key component in order to develop in developing systems with more personalized experiences with humans. In this paper, we propose baseline benchmarks, in order to set anchors to estimate the relative quality of different handwriting style methods. This will be done using deep learning techniques, which have shown remarkable results in different machine learning tasks, learning classification, regression, and most relevant to our work, generating temporal sequences. We discuss the challenges associated with evaluating our methods, which is related to evaluation of generative models in general. We then propose evaluation metrics, which we find relevant to this problem, and we discuss how we evaluate the evaluation metrics. In this study, we use IRON-OFF dataset [1]. To the best of our knowledge, there is no work done before in generating handwriting (either in terms of methodology or the performance metrics), our in exploring styles using this dataset.

The work presented in this paper focuses on the environmental monitoring of underwater areas using acoustic signals. In particular, we propose to compare the effectiveness of various feature sets used to represent the underwater acoustic data for the automatic processing of fish sounds We focus on the detection and classification tasks. Specifically, we compare the use of features issued from signal processing presented and validated in [15], [16] to the use of features obtained through deep convolutional neural networks. Experimental results show that the use of signal processing features outperform the deep features in terms of classification accuracy.

How can we learn, transfer and extract handwriting styles using deep neural networks? This paper explores these questions using a deep conditioned autoencoder on the IRON-OFF handwriting data-set. We perform three experiments that systematically explore the quality of our style extraction procedure. First, We compare our model to handwriting benchmarks using multidimensional performance metrics. Second, we explore the quality of style transfer, i.e. how the model performs on new, unseen writers. In both experiments, we improve the metrics of state of the art methods by a large margin. Lastly, we analyze the latent space of our model, and we see that it separates consistently writing styles.