The progress of deep convolutional neural networks has been successfully exploited in various real-time computer vision tasks such as image classification and segmentation. Owing to the development of computational units, availability of digital datasets, and improved performance of deep learning models, fully automatic and accurate tracking of tongue contours in real-time ultrasound data became practical only in recent years. Recent studies have shown that the performance of deep learning techniques is significant in the tracking of ultrasound tongue contours in real-time applications such as pronunciation training using multimodal ultrasound-enhanced approaches. Due to the high correlation between ultrasound tongue datasets, it is feasible to have a general model that accomplishes automatic tongue tracking for almost all datasets. In this paper, we proposed a deep learning model comprises of a convolutional module mimicking the peripheral vision ability of the human eye to handle real-time, accurate, and fully automatic tongue contour tracking tasks, applicable for almost all primary ultrasound tongue datasets. Qualitative and quantitative assessment of IrisNet on different ultrasound tongue datasets and PASCAL VOC2012 revealed its outstanding generalization achievement in compare with similar techniques.

The visualization of complex data sets is of essential importance in communicating your data products. Beyond pie charts, histograms, line graphs and other common forms of visual communication begins the reign of data sets that encompass too much information to be easily captured by these simple data displays. A typical context that abounds with complexity is found in the areas of text mining, natural language processing, and cognitive computing in general; such a complex context for data presentation is pervasive in an attempt to build a visual interface for products like semantic search engines or recommendation engines. For example, statistical models like LDA (Latent Dirichlet Allocation) enable for a thorough insight into the similarity structure across textual documents or vocabulary terms used to describe them. But as the number of pairwise similarities between terms of documents to be presented to the end users increases, the problem of effective data visualization becomes harder.