Naturalness

About: Naturalness is a research topic. Over the lifetime, 1305 publications have been published within this topic receiving 31737 citations.

A Multi-Task Convolutional Neural Network For Blind Stereoscopic Image Quality Assessment Using Naturalness Analysis

Abstract: This paper addresses the problem of blind stereoscopic image quality assessment (NR-SIQA) using a new multi-task deep learning based-method. In the field of stereoscopic vision, the information is fairly distributed between the left and right views as well as the binocular phenomenon. In this work, we propose to integrate these characteristics to estimate the quality of stereoscopic images without reference through a convolutional neural network. Our method is based on two main tasks: the first task predicts naturalness analysis based features adapted to stereo images, while the second task predicts the quality of such images. The former, so-called auxiliary task, aims to find more robust and relevant features to improve the quality prediction. To do this, we compute naturalness-based features using a Natural Scene Statistics (NSS) model in the complex wavelet domain. It allows to capture the statistical dependency between pairs of the stereoscopic images. Experiments are conducted on the well known LIVE PHASE I and LIVE PHASE II databases. The results obtained show the relevance of our method when comparing with those of the state-of-the-art. Our code is available online on this https URL.

Colour naturalness metric for evaluating image quality of mobile displays

Abstract: A series of psychophysical experiments using categorical judgment method was carried out to develop a colour naturalness metric (CNM) for evaluating image quality of mobile displays. These experiments included colour naturalness judgment and image-quality difference judgment. Through the former one, CNMs were trained and the latter experiment tested the metrics. Two types of CNMs were newly proposed: nonlinearly decaying CNM and linearly decaying CNM. In the CNMs, it was assumed that one familiar object in an image played a critical role to judge the colour naturalness of the whole image. Through a performance comparison between objects' models, one critical object in a scene was selected and with the critical object's model, the whole scene's colour naturalness was predicted.

Speech Emotion and Naturalness Recognitions With Multitask and Single-Task Learnings

Abstract: This paper evaluates speech emotion and naturalness recognitions by utilizing deep learning models with multitask learning and single-task learning approaches. The emotion model accommodates valence, arousal, and dominance attributes known as dimensional emotion. The naturalness ratings are labeled on a five-point scale as dimensional emotion. Multitask learning predicts both dimensional emotion (as the main task) and naturalness scores (as an auxiliary task) simultaneously. The single-task learning predicts either dimensional emotion (valence, arousal, and dominance) or naturalness score independently. The results with multitask learning show improvement from previous studies on single-task learning for both dimensional emotion recognition and naturalness predictions. Within this study, single-task learning still shows superiority over multitask learning for naturalness recognition. The scatter plots of emotion and naturalness prediction scores against the true labels in multitask learning exhibit the lack of the model; it fails to predict the low and extremely high scores. The low score of naturalness prediction in this study is possibly due to a low number of samples of unnatural speech samples since the MSP-IMPROV dataset promotes the naturalness of speech. The finding that jointly predicting naturalness with emotion helps improve the performance of emotion recognition may be embodied in the emotion recognition model in future work.

Detecting Machine-Translated Paragraphs by Matching Similar Words.

Abstract: Machine-translated text plays an important role in modern life by smoothing communication from various communities using different languages. However, unnatural translation may lead to misunderstanding, a detector is thus needed to avoid the unfortunate mistakes. While a previous method measured the naturalness of continuous words using a N-gram language model, another method matched noncontinuous words across sentences but this method ignores such words in an individual sentence. We have developed a method matching similar words throughout the paragraph and estimating the paragraph-level coherence, that can identify machine-translated text. Experiment evaluates on 2000 English human-generated and 2000 English machine-translated paragraphs from German showing that the coherence-based method achieves high performance (accuracy = 87.0%; equal error rate = 13.0%). It is efficiently better than previous methods (best accuracy = 72.4%; equal error rate = 29.7%). Similar experiments on Dutch and Japanese obtain 89.2% and 97.9% accuracy, respectively. The results demonstrate the persistence of the proposed method in various languages with different resource levels.

Evaluation on the naturalness of human walking motion by animation.

Abstract: The mechanism of natural human walking motion has been studied in terms of walking animation by computer graphics. The dither effect generated by adding an appropriate random noise to the position of the ankle was applied to the synthesis for natural walking animation. Two cases of a line drawing animation based on the analysis of human walking and a line drawing animation drawn by a professional animator were used, and their naturalness was evaluated by the sensory evaluation. In the former case, there was no improvement in naturalness by the dither, and the naturalness of motion decreased by adding the random noise. In the latter, there was significant improvement in naturalness by the dither, that is, adding the appropriate random noise was found to be useful in the case of the synthesis of animation made by a line drawing derivated from the actual motion locus.