近年來(lái)深度學(xué)習(xí)逐漸成為信息科學(xué)領(lǐng)域的研究熱點(diǎn),而隨著基于深度學(xué)習(xí)方法的研究技術(shù)的不斷推進(jìn),數(shù)據(jù)特征信息的提取和處理效率獲得了極大的提升,同時(shí)也推動(dòng)了深度學(xué)習(xí)在計(jì)算機(jī)視覺(jué)、語(yǔ)音處理和自然語(yǔ)言處理等相關(guān)領(lǐng)域的迅猛發(fā)展。作為計(jì)算機(jī)視覺(jué)領(lǐng)域中一個(gè)比較重要的研究子方向,人臉表情識(shí)別可以廣泛地應(yīng)用到多個(gè)領(lǐng)域如人機(jī)交互、不良狀態(tài)檢測(cè)等。通常來(lái)說(shuō),表情不僅是一種非語(yǔ)言交際的方式,可以傳遞用于交流的輔助信息,也是人類(lèi)情緒精神狀態(tài)的潛在反映。通過(guò)表情輔助消息傳遞,可以讓消息的信息量更為豐富,而消息接收者也能更為準(zhǔn)確地把握信息的特征。所以在人機(jī)交互方面,表情識(shí)別可以用于讓機(jī)器更準(zhǔn)確地獲取用戶(hù)傳遞的消息內(nèi)容;而在一些需要判斷用戶(hù)狀態(tài)的場(chǎng)景,也可以利用表情識(shí)別完成不良狀態(tài)的識(shí)別,比如判斷駕駛員是否處于疲勞駕駛狀態(tài)。通常非深度學(xué)習(xí)方法的表情識(shí)別主要是利用人工選取的表情特征,包括幾何特征、統(tǒng)計(jì)特征和運(yùn)動(dòng)特征等,以及分類(lèi)判別器的決策分類(lèi)進(jìn)行表情識(shí)別。這些方法都取得了一定的效果,但是過(guò)度依賴(lài)于特征的人工選取,魯棒性較差,同時(shí)計(jì)算量非常大。深度學(xué)習(xí)方法則避免了特征的人工選取,同時(shí)其數(shù)據(jù)冗余度也保證了表情識(shí)別系統(tǒng)的魯棒性。... 

【文章來(lái)源】：哈爾濱工業(yè)大學(xué)黑龍江省 211工程院校 985工程院校

【文章頁(yè)數(shù)】：113 頁(yè)

【學(xué)位級(jí)別】：碩士

【文章目錄】：
詳細(xì)中文摘要
ABSTRACT
CHAPTER 1. INTRODUCTION
    1.1 RESEARCH BACKGROUND AND SIGNIFICANCE
    1.2 RESEARCH STATUS OF RELATED FIELDS
    1.3 MAIN RESEARCH CONTENTS OF THIS SUBJECT
CHAPTER 2. FOUNDATIONS OF CONVOLUTIONAL NEURAL NETWORK ANDOPTIMIZATION
    2.1 INTRODUCTION
    2.2 COMPUTATIONS IN CONVOLUTIONAL NEURAL NETWORK
    2.3 GENERAL MATRIX MULTIPLICATION ALGORITHM FOR CNNACCELERATION
    2.4 WINOGRAD ALGORITHM FOR CONVOLUTIONAL LAYERACCELERATION
    2.5 BRIEF SUMMARY
CHAPTER 3. COMPRESSION AND OPTIMIZATION FOR LONG SHORT-TERMMEMORY
    3.1 INTRODUCTION
    3.2 COMPUTATIONS IN LONG SHORT-TERM MEMORY
    3.3 CLASSICAL DECOMPOSITION METHODS
        3.3.1 Tensor basics
        3.3.2 Singular value decomposition
        3.3.3 Tucker decomposition
    3.4 TENSORIZED COMPRESSION FOR LSTM ACCELERATION
        3.4.1 Tensor train tensor decomposition
        3.4.2 Tensorized compression for LSTM
    3.5 BRIEF SUMMARY
CHAPTER 4. SPATIOTEMPORAL MODEL FOR VIDEO FACIAL EXPRESSIONRECOGNITION
    4.1 INTRODUCTION
    4.2 FEATURE EXTRACTION WITH CNN
    4.3 SPATIOTEMPORAL LSTM MODEL
    4.4 OUR PROPOSED FRAMEWORK FOR FER
    4.5 BRIEF SUMMARY
CHAPTER 5. IMPLEMENTATION ON EDGE DEVICES
    5.1 INTRODUCTION
    5.2 IMPLEMENTATION ON ARM CPU
        5.2.1 ARM architecture and NEON technology
        5.2.2 ARM intrinsic programming
        5.2.3 Workflow overview on ARM CPU
    5.3 IMPLEMENTATION ON EDGE DEVICE 1
        5.3.1 Introduction to RK3399 Pro board
        5.3.2 Neural process unit and systolic arrays
        5.3.3 Workflow overview on RK3399 Pro board
    5.4 IMPLEMENTATION ON EDGE DEVICE 2
        5.4.1 Introduction to Atlas 200 Developer Kit
        5.4.2 Ascend 310 chipset and Da Vinci core
        5.4.3 Workflow overview on Atlas 200 DK board
CHAPTER 6. EXPERIMENTAL RESULTS AND PERFORMANCEANALYSIS
    6.1 INTRODUCTION
    6.2 EVALUATION ON FACIAL EXPRESSION RECOGNITIONDATASETS
    6.3 PERFORMANCE ANALYSIS
CHAPTER 7. CONCLUSIONS
結(jié)論
REFERENCES
PAPERS PUBLISHED IN THE PERIOD OF MASTER EDUCATION
ACKNOWLEDGEMENT



本文編號(hào)：3555752