IRJET- Music Recommendation through Facial Expression using ML

International Journal for Research in Applied Science and Engineering Technology

IRJET, 2022

Human facial expressions convey a lot of information visually rather than articulately. Facial expression recognition plays a very crucial role in the area of human- machine interaction.Face recognition technology has many applications, but they are generally limited to the understanding of human behavior, the detection of mental disorders, and synthesizing human expressions. This project aims to apply various deep learning methods to identify the seven key emotions: happiness, sadness, disgust, anger, fear, surprise, and neutrality, as well as suggest some mood booster songs

Research Square (Research Square), 2023

Music always has a special connection to our emotions. It is a method of connecting people all over the world through pure emotions. When all of this is considered, it is exceedingly difficult to generalize music and state that everyone would enjoy the same type. Music recommendation based on mood is greatly needed because they will assist humans in relieving stress and listening to soothing music based on their current emotions. Its primary goal is to accurately predict the user's mood, and songs are played by the application based on the user's selection as well as his current mood. This bot recognizes human emotions from facial images using Human-Computer Interaction (HCI). The extraction of facial elements from the user's face is another critical factor. We used the CNN Algorithm to accurately detect the user's face in the live webcam feed and to detect emotion based on facial attributes such as the arrangement of the user's mouth and eyes. There is also a questionnaire where we can directly select a good option.

Journal of Informatics Electrical and Electronics Engineering (JIEEE), A2Z Journals, 2021

We propose a new approach for playing music automatically using facial emotion. Most of the existing approaches involve playing music manually, using wearable computing devices, or classifying based on audio features. Instead, we propose to change the manual sorting and playing. We have used a Convolutional Neural Network for emotion detection. For music recommendations, Pygame & Tkinter are used. Our proposed system tends to reduce the computational time involved in obtaining the results and the overall cost of the designed system, thereby increasing the system's overall accuracy. Testing of the system is done on the FER2013 dataset. Facial expressions are captured using an inbuilt camera. Feature extraction is performed on input face images to detect emotions such as happy, angry, sad, surprise, and neutral. Automatically music playlist is generated by identifying the current emotion of the user. It yields better performance in terms of computational time, as compared to the algorithm in the existing literature.

IRJET, 2021

Recent studies confirm that humans respond and react to music which music encompasses a high impact on person's brain activity. the common American listens up to four hours of music on a daily basis. Everyone wants to pay attention music of their individual taste, mostly supported their mood. Users always face the task of manually browsing the music and to form a playlist supported their current mood. The proposed project is incredibly efficient which generates a music playlist supported this mood of users. Facial expressions are the most effective way of expressing ongoing mood of the person. the target of this project is to suggest songs for users supported their mood by capturing facial expressions. Facial expressions are captured through webcam and such expressions are fed into learning algorithm which provides most probable emotion. Once the emotion is recognized, the system suggests a playlist for that emotion, thus saves plenty of your time for a user. Once the emotion is detected by CNN then the emotion is employed by Spotify API then the Spotify API generates a playlist according the emotion of the user. stock prices accurately. The experiment results show that prediction accuracy is over 80%.

IRJET, 2020

Recent studies ensure that humans respond and react to music which music incorporates a high impact on person brain activity. The common yank listens up to four hours of music daily. Individuals tend to concentrate on music that supported their mood and interests. This project focuses on making Associate in Nursing application to counsel songs for user-supported their mood by capturing facial expressions. Facial features could be a type of nonverbal communication. Pc vision is Associate in Nursing knowledge domain field that helps convey a high-level understanding of digital pictures or videos to computers. In this system, PC vision elements square measure accustomed to verify the user's feeling through facial expressions. Once the feeling is recognized, the system suggests a play-list for that feeling, saving a great deal of your time for a user over choosing and taking part in songs manually. Emotion-Based Music Player additionally keeps track of user's details like the number of plays for every song, types of songs supported class and interest level, and reorganizes the play-list on every occasion. The system additionally notifies user concerning the songs that square measure so that they will be deleted or changed. Listening to music affects the human brain activities. Feeling based mostly music player with the machine-driven listing will facilitate users to take care of a selected emotional state. This analysis proposes Associate in Nursing feeling based mostly music player that creates playlists supported captured photos of the user. This enhances the system's potency, faster and automatic. The most goal is to cut back the general machine time and also the cost of the designed system. It additionally aims at increasing the accuracy of the system. The foremost vital goal is to create an amendment to the mood of a person if it's a negative one like unhappy, depressed. This model is valid by testing the system against user-dependent and user freelance dataset. The methodology of finding this downside is to make a completely useful app (Front End and Back finish) that solves this downside, ranging from the face there a straightforward and understandable interface anyone will use, this interface is connected to the rear finish. On the back finish, the most rule during this project is to make a Convolutional Neural Network help within the goal of achieving high accuracy rate, as a result of the Convolutional Neural Network is the best within the science of building any network that works with pictures, and conjointly their area unit plenty of similar analysis papers that achieved o.k. seen success during this field of analysis. A completely useful app that engineered to unravel this downside (Desktop Only) and conjointly trained nearly 28000 pictures with totally different states of emotions (Happy, Sad, Angry, and Normal) with an high accuracy rate that is, "85%" for coaching and "83%" for testing rate, the application is with success suggesting music by suggesting single songs that match any user's feeling.

International Journal for Research in Applied Science & Engineering Technology (IJRASET), 2022

In today's technological revolving era, everyday new types of technologies are being discovered. Various types of technologies, devices, softwares etc. are being introduced daily. According to the experts the facial expression is derived from the internal biological motions of the muscles that lie under the skin. It also deprives the emotional state of the person. But, in this world where communication has become an important thing, the facial expression is the mean of the non-verbal communication, by which we can understand the current behaviour of the person without even uttering single word. For recognition of an individual's mood, the system uses Facial Expression Recognition (FER) concept and depending on the recognized mood, song is played. This program removes the time-consuming and the hard work of manually searching and playing the songs from internet or any other sources. So, we introduced an application that suggests the songs based on the facial expression or emotions. This application will use the camera feature of any device to read the facial expression of the user and then define a song accordingly. Furthermore, this application will have an additional feature of offline functionality. These are the modules that our application will function on. Our application will imply on various algorithms and packages and application interfaces. We can precisely say our application will use Python package of Tensor Flow (TF) for the facial expression. In this way, the proposed system will contribute towards the healthy emotion building of the humans and will technologically evolve the existing music recommendation system in a new wholesome way.

International Journal of Research and Innovation in Applied Science

Face emotion detection has recently attracted a lot of interest because of its uses in computer vision and the field of human-computer interaction. Various methods and applications were suggested and put into use as a result of the ongoing research in this area. In this study, we present an emotion-recognition recommender system that can identify a user’s feelings and offer a selection of suitable songs that might lift his spirits. To gather information and enable us to give the users a selection of music tracks that are effective at lifting the users’ spirits, a quick search was undertaken to learn how music may impact the user mood in the short term. The suggested system recognizes emotions, and if the individual is feeling down, a special playlist including the best kinds of music will be played to lift his spirits. On the other hand, if a favorable mood is recognized, an appropriate playlist will be offered that contains several genres of music that will amplify the pleasant fee...

IJRASET, 2021

Our world today is driven by machines of various complexities. From a basic one like a computer to a highly complex humanoid robot, everything is a product of human intelligence. A lot of industries are being benefited from such new technologies. Facial Expression Recognition is one of these technologies. It has a wide range of applications and is an area that is constantly evolving. The analogy behind it is, when we gaze at someone, the eyes send signals to the brain. The face patterns of that specific person are carried by these messages. These patterns are then compared to those stored in the brain's memory. Inspired by such innovations, our research collects human expressions and analyses their emotions using our vast dataset, offering some necessary strategies to change their facial expressions. Due to the competitive environment, the youth of our generation has been inclined to a lot of mental health problems such as anxiety and depression. Our generation's youth has been predisposed to a variety of mental health issues. Our idea attempts to provide a relaxing atmosphere to a person based on his or her facial expressions.

JETIR, 2022

Human facial expression recognition is one of the foremost powerful and difficult tasks in social communication yet plays very important role in communicating the emotions and intensions of human beings. Generally, facial expressions are the most unique and natural way of non-verbal communication with emotions. Along with communication we love listening music according to the mood we're in for the moment. For this reason there have been some advancements in technology that integrate emotional intelligence into existing machine learning applications are being studied. This paper is a survey on facial expression recognition (FER) and music classification techniques that embody the 3 major stages like preprocessing, feature extraction and classification. This survey explains the varied kinds of FER and music classification techniques with its major contributions. The performance of varied FER techniques is compared supported to the amount of expressions recognized and complexness of algorithms. Databases like JAFFE, CK, and a few different kind of face expression databases are mentioned during this survey.