Umang Srivastava, et. al. International Journal of Engineering Research and Applications www.ijera.com ISSN: 2248-9622, Vol. 12, Issue 5, (Series-I) May 2022, pp. 07-10 www.ijera.com DOI: 10.9790/9622-1205010710 7 | Page Smart Fan Using Face Detection and Voice assistant 1. Umang Srivastava 2. Shashwat Tripathi 3. Vipul Gupta 4.Vikash Raghuvanshi Computer Science and Engineering, Inderprastha Engineering College(IPEC)/Aktu, Ghaziabad, India ABSTRACT In the last several years, face detection has been listed as one of the most engaging field in research. Face detection algorithms is used for detection of frontal human faces. Face detection find use is many applications such as face tracking, faces analysis and face recognition. The term Face Recognition and detection is like an ocean of research and innovation with the applications of image analysis and algorithm- based understanding which can be called as computer vision. Voice assistant helps to perform task in quick and real time. The humans give voice command and the system performs tasks. Keywords: Python, Face Detection, Haar cascades classifier, OpenCV, Google Text to Speech, VS code Arduino UNO. --------------------------------------------------------------------------------------------------------------------------------------- Date of Submission: 25-04-2022 Date of Acceptance: 07-05-2022 --------------------------------------------------------------------------------------------------------------------------------------- I. INTRODUCTION The project is mainly targeted on developing a “Smart Fan” using the Face Detection and Voice Assistant by minimizing the human interaction and focusing on more friendly user. Face Detection is seen as an AI based computer technology that can be used to identify and locate the presence of human faces during real time. The applications of these algorithms are in almost every field and industry in today’s time. Face Detection using Haar Cascades classifier is a Machine Learning algorithm which use a cascades function for face detection . Haar cascades classifier is Machine Learning approach in which the cascades function is trained to using a sample containing a lot of positive and negative images. The speed and direction(movement) of the fan will also be controlled using the voice assistant which on passing voice command to the system will control the speed and direction of the fan II. OBJECTIVE The main objective of the project is to built an automated fan system using face detection using OpenCV,Haar Cascades Classifier. We will use voice assistant based system to control the speed as well as the direction of the fan which will lead in reducing human effort. III. METHODOLOGY For the development of the smart Fan , Hardware components were required such as Arduino UNO,Servo motor , ordinary fan, USB cables and other power modules. It used software such as Python,VS studio code,Open CV,GTTS. Python was used to code the face detection application along with Haar cascade classifier which held the information about how to detect the human face. Open CV was used to run the face detection application. Arduino used the Arduino IDE for its coding purposes .Voice Assistant enabled in Fan using google text to speak Library. Smart Fan developed for human- less intervention and making automation in offices,home and various places. IV. TECHNOLOGY Python: Python is an interpreted high-level general-purpose programming language. Its design philosophy emphasizes code readability with its use of significant indentation. Its language constructs as well as its object-oriented approach aim to help programmers write clear, logical code for small and large-scale projects. Face Detection: Face detection can be regarded as a specific case of object-class detection. In object-class detection, the task is to find the locations and sizes of all objects in an image that belong to a given class. Examples include upper torsos, pedestrians, and cars. Face detection simply answers two question, 1. are there any human faces in the collected images or video? 2. where is the located? Face-detection algorithms focus on the RESEARCH ARTICLE OPEN ACCESS