Wyniki wyszukiwania - BazTech

1

Comixify : Transform Video Into Comics

Pęśko Maciej, Svystun Adam, Andruszkiewicz Paweł, Rokita Przemysław, Trzciński Tomasz

Fundamenta Informaticae

|

2019

|

Vol. 168, nr 2-4

311--333

EN

In this paper, we propose a solution to transform a video into a comics. We approach this task using a neural style algorithm based on Generative Adversarial Networks (GANs). Several recent works in the field of Neural Style Transfer showed that producing an image in the style of another image is feasible. In this paper, we build up on these works and extend the existing set of style transfer use cases with a working application of video comixification. To that end, we train an end-to-end solution that transforms input video into a comics in two stages. In the first stage, we propose a state-of-the-art keyframes extraction algorithm that selects a subset of frames from the video to provide the most comprehensive video context and we filter those frames using image aesthetic estimation engine. In the second stage, the style of selected keyframes is transferred into a comics. To provide the most aesthetically compelling results, we selected the most state-of-the art style transfer solution and based on that implement our own ComixGAN framework. The final contribution of our work is a Web-based working application of video comixification available at http://comixify.ii.pw.edu.pl.

2

Classifying and Visualizing Emotions with Emotional DAN

Tautkutė Ivona, Trzciński Tomasz

Fundamenta Informaticae

|

2019

|

Vol. 168, nr 2-4

269--285

EN

Classification of human emotions remains an important and challenging task for many computer vision algorithms, especially in the era of humanoid robots which coexist with humans in their everyday life. Currently proposed methods for emotion recognition solve this task using multi-layered convolutional networks that do not explicitly infer any facial features in the classification phase. In this work, we postulate a fundamentally different approach to solve emotion recognition task that relies on incorporating facial landmarks as a part of the classification loss function. To that end, we extend a recently proposed Deep Alignment Network (DAN) with a term related to facial features. Thanks to this simple modification, our model called EmotionalDAN is able to outperform state-of-the-art emotion classification methods on two challenging benchmark dataset by up to 5%. Furthermore, we visualize image regions analyzed by the network when making a decision and the results indicate that our EmotionalDAN model is able to correctly identify facial landmarks responsible for expressing the emotions.

3

Monitoring of the Achilles tendon healing process: can artificial intelligence be helpful?

Kapiński Norbert, Zieliński Jakub, Borucki Bartosz A., Trzciński Tomasz, Ciszkowska-Łysoń Beata, Zdanowicz Urszula, Śmigielski Robert, Nowiński Krzysztof S.

Acta of Bioengineering and Biomechanics

|

2019

|

Vol. 21, no. 1

103--111

EN

The aim of this study was to verify improved, ensemble-based strategy for inferencing with use of our solution for quantitative assessment of tendons and ligaments healing process and to show possible applications of the method. Methods: We chose the problem of the Achilles tendon rupture as an example representing a group of common sport traumas. We derived our dataset from 90 individuals and divided it into two subsets: healthy individuals and patients with complete Achilles tendon ruptures. We computed approx. 160 000 2D axial cross-sections from 3D MRI studies and preprocessed them to create a suitable input for artificial intelligence methods. Finally, we compared different training methods for chosen approaches for quantitative assessment of tendon tissue healing with the use of statistical analysis. Results: We showed improvement in inferencing with use of the ensemble technique that results from achieving comparable accuracy of 99% for our previously published method trained on 500 000 samples and for the new ensemble technique trained on 160 000 samples. We also showed real-life applications of our approach that address several clinical problems: (1) automatic classification of healthy and injured tendons, (2) assessment of the healing process, (3) a pathologic tissue localization. Conclusions: The presented method enables acquiring comparable accuracy with less training samples. The applications of the method presented in the paper as case studies can facilitate evaluation of the healing process and comparing with previous examination of the same patient as well as with other patients. This approach might be probably transferred to other musculoskeletal tissues and joints.