“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Sensors play a crucial role in factory automation in making the system intellectual. Different types of sensors are available as per the suitability and applications; some of them are produced in mass and available in the market at affordable costs. The standard sensor types available are position sensors, pressure sensors, flow sensors, temperature sensors, and force sensors. They are used in many sectors, such as motorsport, medical, industry, aerospace, agriculture, and daily life. The objective of Industry 4.0 is to increase efficiency through automation. Sensors are vital components of Industry 4.0, allowing several transitions such as changes in positions, length, height, external and dislocations in industrial production facilities to be detected, measured, analysed, and processed. Smart factories will also enhance sustainability by tracking real-time output, and automated control systems will minimise potential factory maintenance costs. It can also be seen that digitalisation can improve production mobility, which gives advanced manufacturing firms a competitive advantage. This paper discusses sensors and their various types, along with significant capabilities for manufacturing. The step-by-step working Blocks and Quality Services of Sensors during implementation in Industry 4.0 are elaborated diagrammatically. Finally, we identified thirteen significant applications of sensors for Industry 4.0. Industry 4.0 provides an excellent opportunity for the development of the sensor market across the globe. In Industry 4.0, sensors will enjoy higher acceptance rates and benefit from a fully enabled connecting and data exchange and logistics integration. In the coming years, sensor installations may grow in process management, automated production lines, and digital supply chains.

Significance of sensors for industry 4.0: Roles, capabilities, and applications

Facial expression recognition with grid-wise attention and visual transformer

Human emotional states can be detected by various ways such as analysingthe brain signals (EEG), speech, skin responses, facial expressions, body gestures etc. But facial expressions recognition is one of the popular techniquesand easy to detect with computers using various computer visions techniques. In this work, we have proposed a new approach to detect basic facial expressions from textural images using deep learning model Convolution neural network (CNN). In the proposed approach textural images of human faces are generated using Local binary pattern(LBP) method and trained the CNN model with the LBPimages. In the proposed approach all the images of extended Cohn-Kanade(CK+)dataset are converted into LBP images that are used to train the CNN model. The performance of proposed facial expression recognition system has been validated on modifiedCK+dataset. Facial emotionRecognition Accuracy of conventional CNN model with CK+ dataset and proposed method on modified CK+ dataset is also compared.

Facial emotion recognition based on Textural pattern and Convolutional Neural Network

Emotion Recognition is attracting the attention of the research community due to the multiple areas where it can be applied, such as in healthcare or in road safety systems. In this paper, we propose a multimodal emotion recognition system that relies on speech and facial information. For the speech-based modality, we evaluated several transfer-learning techniques, more specifically, embedding extraction and Fine-Tuning. The best accuracy results were achieved when we fine-tuned the CNN-14 of the PANNs framework, confirming that the training was more robust when it did not start from scratch and the tasks were similar. Regarding the facial emotion recognizers, we propose a framework that consists of a pre-trained Spatial Transformer Network on saliency maps and facial images followed by a bi-LSTM with an attention mechanism. The error analysis reported that the frame-based systems could present some problems when they were used directly to solve a video-based task despite the domain adaptation, which opens a new line of research to discover new ways to correct this mismatch and take advantage of the embedded knowledge of these pre-trained models. Finally, from the combination of these two modalities with a late fusion strategy, we achieved 80.08% accuracy on the RAVDESS dataset on a subject-wise 5-CV evaluation, classifying eight emotions. The results revealed that these modalities carry relevant information to detect users' emotional state and their combination enables improvement of system performance.

Multimodal Emotion Recognition on RAVDESS Dataset Using Transfer Learning.

Facial expression recognition has been an active area of research over the past few decades, and it is still challenging due to the high intra-class variation. Traditional approaches for this problem rely on hand-crafted features such as SIFT, HOG, and LBP, followed by a classifier trained on a database of images or videos. Most of these works perform reasonably well on datasets of images captured in a controlled condition but fail to perform as well on more challenging datasets with more image variation and partial faces. In recent years, several works proposed an end-to-end framework for facial expression recognition using deep learning models. Despite the better performance of these works, there are still much room for improvement. In this work, we propose a deep learning approach based on attentional convolutional network that is able to focus on important parts of the face and achieves significant improvement over previous models on multiple datasets, including FER-2013, CK+, FERG, and JAFFE. We also use a visualization technique that is able to find important facial regions to detect different emotions based on the classifier’s output. Through experimental results, we show that different emotions are sensitive to different parts of the face.

Deep-Emotion: Facial Expression Recognition Using Attentional Convolutional Network.

Automatic prediction of age and gender from face images has drawn a lot of attention recently, due it is wide applications in various facial analysis problems. However, due to the large intra-class variation of face images (such as variation in lighting, pose, scale, occlusion), the existing models are still behind the desired accuracy level, which is necessary for the use of these models in real-world applications. In this work, we propose a deep learning framework, based on the ensemble of attentional and residual convolutional networks, to predict gender and age group of facial images with high accuracy rate. Using attention mechanism enables our model to focus on the important and informative parts of the face, which can help it to make a more accurate prediction. We train our model in a multi-task learning fashion, and augment the feature embedding of the age classifier, with the predicted gender, and show that doing so can further increase the accuracy of age prediction. Our model is trained on a popular face age and gender dataset, and achieved promising results. Through visualization of the attention maps of the train model, we show that our model has learned to become sensitive to the right regions of the face.

Age and Gender Prediction From Face Images Using Attentional Convolutional Network.

Generating realistic palmprint (more generally biometric) images has always been an interesting and, at the same time, challenging problem. Classical statistical models fail to generate realistic-looking palmprint images, as they are not powerful enough to capture the complicated texture representation of palmprint images. In this work, we present a deep learning framework based on generative adversarial networks (GAN), which is able to generate realistic palmprint images. To help the model learn more realistic images, we proposed to add a suitable regularization to the loss function, which imposes the line connectivity of generated palmprint images. This is very desirable for palmprints, as the principal lines in palm are usually connected. We apply this framework to a popular palmprint databases, and generate images which look very realistic, and similar to the samples in this database. Through experimental results, we show that the generated palmprint images look very realistic, have a good diversity, and are able to capture different parts of the prior distribution. We also report the Frechet Inception distance (FID) of the proposed model, and show that our model is able to achieve really good quantitative performance in terms of FID score.

Mehdi Minaei

Papers

Deep-Emotion: Facial Expression Recognition Using Attentional Convolutional Network.

Age and Gender Prediction From Face Images Using Attentional Convolutional Network.

Palm-GAN: Generating Realistic Palmprint Images Using Total-Variation Regularized GAN.