System features of emotion based music player
Posts: 14,118
Threads: 61
Joined: Oct 2014
Music player plays a vital role in everyone's life. Most users of music lovers found themselves in a hectic situation when they did not find songs that matched their mood in the situation. So we have developed a music player based on emotion. The main objective of this work is to design an efficient and precise algorithm that generates a playlist based on the current emotional state and the behavior of the user. Face detection and extraction of facial features of the image is the first step in the music player based on emotion. For face detection to work effectively, we need to provide an input image that should not be blurred and tilted. We have used the Viola-Jones algorithm that is used for face detection and facial feature extraction. We have generated benchmarks for facial features. The next step is the emotion classification for which we have used the multi-class SVM classification. The generated benchmarks are provided to the SVM for training purposes. The emotion classified by SVM is passed to a music player and, as a result, the music will play. 2. Literature Survey A literature survey is a text of an academic article, which includes current knowledge including substantive findings, as well as theoretical and methodological contributions to a particular topic. Bibliographic reviews use secondary sources, and do not report new or original experimental works. Several techniques and approaches have been proposed and developed to classify the human emotional state of behavior. The proposed approaches have focused only on some of the basic emotions. For the purpose of character recognition, facial features have been categorized into two main categories, such as extraction of features based on appearance and extraction of features based on geometry. The geometric extraction technique based on the feature considered only the important shape or prominent points of some important facial features such as mouth and eyes. Renuka R. Londhe proposed a precise and efficient statistical approach to analyze facial expression characteristics extracted. The work focused mainly on the study of the changes in the curvatures in the face and the intensities of the corresponding pixels of the images. Support vector machine (SVM) was used in the classified classification features in 6 major universal emotions like anger, disgust, fear, happy, sad, and surprise.
The human face is an important organ of the body of an individual and plays especially an important role in extracting the behavior and the emotional state of an individual. Manual segregation of the song list and the generation of an appropriate playlist based on an individual's emotional characteristics is a very tedious, laborious and laborious task. Several algorithms have been proposed and developed to automate the process of generating playlists. However, the existing algorithms in use are computationally slow, less accurate and sometimes even require the use of additional hardware such as EEG or sensors. This proposed system based on extracted facial expression will automatically generate a playlist, thus reducing the effort and time required to process the process manually. Therefore, the proposed system tends to reduce the computational time involved in obtaining the results and the total cost of the designed system, thereby increasing the overall accuracy of the system. System tests are performed on both the user-dependent (dynamic) and the user-independent (static) data set. Facial expressions are captured using a built-in camera. The accuracy of the emotion detection algorithm used in the system for real-time images is around 85-90%, while for static images it is around 98- 100%. The algorithm proposed in an average calculated estimate takes about 0.95-1.05 seconds to generate an emotion-based music playlist. Therefore, it produces greater precision in terms of performance and computational time and reduces the cost of design, compared to the algorithms used in the literature survey.
Related video is here :