English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 46833/50693 (92%)
造訪人次 : 11855901      線上人數 : 206
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜尋範圍 查詢小技巧:
  • 您可在西文檢索詞彙前後加上"雙引號",以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋,建議至進階搜尋限定作者欄位,可獲得較完整資料
  • 進階搜尋
    主頁登入上傳說明關於CCUR管理 到手機版


    請使用永久網址來引用或連結此文件: https://irlib.pccu.edu.tw/handle/987654321/51157


    題名: 情緒辨識系統之開發及其在互動式機器人之應用
    Development of emotion recognition system and its application for interactive robots
    作者: 馮雅棠
    貢獻者: 機械工程學系數位機電碩士班
    關鍵詞: 卷積神經網路
    長短期記憶
    倒傳遞類神經網路
    體溫與脈搏感測器
    互動式機器人
    樹莓派微控制器
    Convolutional Neural Networks
    Long Short-Term Memory
    Backpropagation Neural Network
    Body temperature and heartbeat sensors
    Interactive robots
    Raspberry Pi
    日期: 2022
    上傳時間: 2023-02-23 14:30:41 (UTC+8)
    摘要: 科技日新月異的現代,許多技術與產品接踵而來,深深地影響人類現在及未來的生活。台灣的驕傲台積電作為全球半導體技術的先驅,其製程傲視全球無人能及,製程的優劣反映在IC產業上,這點從晶片運算能力就可窺知一二。近幾年CPU與GPU的強大,讓深度學習越來越貼近人類的生活,深度學習的開發方向也越多元;其中,深度學習被應用在辨識圖形的例子不勝枚舉,除了辨識車牌、物品樣貌,應用在辨識人臉以及辨識情緒更是近年來非常熱門的主題,已經有眾多成功案例顯示即便在不同的開發平台設計出辨識模型,只要搭配適合之輔助軟體都能達到相同的辨識目的,可見深度學習開發方向相當多元;影像辨識是以龐大訓練資料為基礎進而提高辨識率,沒有數量可觀的訓練資料支援,出現錯誤概率是相當高的;本論文為了改善這個問題,計畫結合影像情緒辨識與人體生理數據,匯入神經網路模型計算後,提升辨識率與辨識種類。本論文的第一部分,是建立卷積神經網路的影像情緒辨識模型用來辨識喜(Happiness)、怒(Anger)、哀(Sadness)的人臉圖形偵測,選用Googlenet作為影像辨識模型主體;為提升第一部分的辨識率並提高辨識種類,本論文第二部分為收集脈搏與體溫感測器的生理數據,建立生理數據輔助心理數據辨識模型,藉由導入第一模型辨識結果與生理數據後,評估出六種情緒—幸福(Happiness)、憤怒(Anger)、恐懼(Fear)、悲傷(Sadness)、驚訝(Surprise)、厭惡(Disgust)。為使系統智能化、輕巧化,本論文將兩個辨識模型嵌入樹莓派系統,樹莓派透過GPIO連接兩個生理感測器,專用接孔連接樹莓派相機,USB插入加速運算處理元件,將連接完所需硬體的樹莓派控制板結合電池控制模組後,進入第三部分以樹莓派為控制器的機器人,機器人靠著8個伺服馬達與連桿機構產生動作變化,其動作變化是依據生理數據輔助心理數據辨識模型執行結果;第三部分的機器人採用外型為四組連桿的機器狗,藉由辨識結果改變其動作,透露出受測者的心理狀態,本論文對於偵測到的情緒反饋十分重視,因此將機器狗設定為會隨著偵測到的六種情緒辨識結果採取預設動作,做出與受測者當下情緒相呼應的動作。

    The ever-changing technology of modernity, lots of technologies and products come one after another, profoundly affect human life now and in the future. TSMC, the pride of Taiwan, as a pioneer in global semiconductor technology, its manufacturing process is unparalleled in the world, the pros and cons of the process are reflected in the IC industry, this can be seen from the computing power of the chip. In recent years, the power of CPU and GPU has made deep learning closer and closer to human life, and the development direction of deep learning has become more diverse; among them, there are countless examples of deep learning being applied to recognizing patterns, in addition to identifying of the license plate and the items appearance, it used to recognize of the facial emotion has become a very popular topic in recent years in particular. There have been many successful cases showing that identification models are designed even in different development platforms,,as long as it is matched with suitable software, the same identification purpose can be achieved, it can be seen that the development direction of deep learning is quite diverse; the image recognition is based on huge training data to improve the recognition accuracy, without the support of big data, the probability of error is still quite high. This research aims to improve this problem, planning to combine the image emotion recognition and human physiological data made from training data, and import it into the neural network model for calculation to improve the recognition accuracy and recognition types. The first part of this research, establishing a convolutional neural network-based image emotion recognition model to identify the face image detection of “Happiness”, “Anger”, and “Sadness”, and choosing Googlenet as the main body of the image recognition model. In order to improve the recognition accuracy of the first part and improve the identification types, the second part of this research is to collect the physiological data of the pulse and body temperature sensors, and establish a physiological data-assisted psychological data recognition model. By importing the recognition results of the first model and the physiological data, assessing six emotions—Happiness, Anger, Fear, Sadness, Surprise, and Disgust. In order to make the system intelligent and lightweight, this research embeds these two identification models into the Raspberry Pi system. The Raspberry Pi is connected to two physiological sensors through GPIO, and the dedicated socket is connected to the Raspberry Pi camera, USB plug-in accelerated computing processing element, after connecting the Raspberry Pi control board with the required hardware and the battery module, then is the third part of the robot with the Raspberry Pi as the controller. The robot relies on 8 servo motors and linkages to generate movement changes, and its movement changes are based on the results of the execution of the physiological data-assisted psychological data identification model.;The robot in the third part, uses a robot dog with four sets of connecting rod, and changes its movements through the recognition results, revealing the psychological state of the subjects. This research attaches great importance to the detected emotional feedback. The robot dog is set to take preset actions according to the detected six kinds of emotion recognition results, and make proper actions that correspond to the current emotions of the subjects.
    顯示於類別:[機械工程系暨機械工程學系數位機電研究所] 博碩士論文

    文件中的檔案:

    檔案 描述 大小格式瀏覽次數
    index.html0KbHTML182檢視/開啟


    在CCUR中所有的資料項目都受到原著作權保護.


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回饋