| DC Field | Value | Language |
|---|
| dc.contributor.author | edy, victor haryanto | - |
| dc.date.accessioned | 2020-07-10T08:28:59Z | - |
| dc.date.available | 2020-07-10T08:28:59Z | - |
| dc.date.issued | 2020-05-11 | - |
| dc.identifier.issn | 1693-6930 | - |
| dc.identifier.uri | http://repository.potensi-utama.ac.id/jspui/jspui/handle/123456789/3569 | - |
| dc.description | In the past few years, emotion recognition has become one of the leading topics in the field of machine
learning and artificial intelligence. The tremendous increase in the development of sophisticated
human-computer interaction technologies has further boosted the pace of progress in this field. Facial actions
convey the emotions, which, in turn, convey a person’s personality, mood, and intentions. Emotions usually
depend upon the facial features of an individual along with the voice. Nevertheless, there are some other
features as well, namely physiological features, social features, physical features of the body, and many more.
More and more work has been done to recognize emotions with more accuracy and precision. The target of
emotion recognition can be achieved broadly using visual-based techniques or sound-based techniques.
Artificial intelligence has revolutionized the field of human-computer interaction and provides many machine
learning techniques to reach our aim. There are many machine learning techniques to recognize the emotion,
but this paper will mostly focus on video-based emotion recognition using deep learning. Video-based emotion
recognition is multidisciplinary and includes fields like psychology, affective computing, and human-computer interaction. The fundamental piece of the message is the facial expression, which establishes 55% of the general
impression [1].
To make a well-fitted model for video-based emotion recognition, there must be proper feature frames
of the facial expression within the scope. Instead of using conventional techniques, deep learning provides
a variety in terms of accuracy, learning rate, and prediction. convolutional neural networks (CNN) is one of
the deep learning techniques which have provided support and platform for analyzing visual imagery.
Convolution is the fundamental use of a filter to an input that outcome in an actuation. Rehashed use of
a similar filter to an input brings about a map of enactments called a feature map, showing the areas and quality
of a recognized element in input, for example, a picture. The development of convolution neural systems is
the capacity to consequently gain proficiency with an enormous number of filters in equal explicit to a training
dataset under the requirements of a particular prescient displaying issue, for example, picture characterization.
The outcome is profoundly explicit highlights that can be distinguished anywhere on input pictures. Deep
learning has achieved great success in recognizing emotions, and CNN is the well-known deep learning method
that has achieved remarkable performance in image processing.
There has been a great deal of work in visual pattern recognition for facial emotional expression
recognition, just as in signal processing for sound-based recognition of feelings. Numerous multimodal
approaches are joining these prompts [2]. Over the past decades, there has been extensive research in computer
vision on facial expression analysis [3]. The objective of this paper is to develop video-based emotion
recognition using deep learning with Google collab. | en_US |
| dc.description.abstract | Emotion recognition using images, videos, or speech as input is considered as
a hot topic in the field of research over some years. With the introduction of
Deep learning techniques, e.g., convolutional neural networks (CNN), applied
in emotion recognition, has produced promising results. Human facial
expressions are considered as critical components in understanding one's
emotions. This paper sheds light on recognizing the emotions using deep
learning techniques from the videos. The methodology of the recognition
process, along with its description, is provided in this paper. Some of
the video-based datasets used in many scholarly works are also examined.
Results obtained from different emotion recognition models are presented
along with their performance parameters. An experiment was carried out on
the fer2013 dataset in Google Colab for depression detection, which came out
to be 97% accurate on the training set and 57.4% accurate on the testing set. | en_US |
| dc.publisher | TELKOMNIKA Telecommunication, Computing, Electronics and Control | en_US |
| dc.relation.ispartofseries | th5;2463-2471 | - |
| dc.subject | Convolutional neural networks | en_US |
| dc.subject | Deep learning | en_US |
| dc.subject | Emotion recognition | en_US |
| dc.subject | Google Colab | en_US |
| dc.subject | Machine learning | en_US |
| dc.title | Development of video-based emotion recognition using deep learning with Google Colab | en_US |
| dc.type | Article | en_US |
| Appears in Collections: |
|
