發(fā)布時(shí)間：2018-03-01 06:38

  本文關(guān)鍵詞： 表情識(shí)別 深度學(xué)習(xí) 特征提取 人臉檢測(cè) 人臉關(guān)鍵點(diǎn)檢測(cè)　出處：《西南科技大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：人臉表情識(shí)別是機(jī)器視覺(jué)和模式識(shí)別等領(lǐng)域的一大富有挑戰(zhàn)性的研究課題。人臉表情識(shí)別一直作為領(lǐng)域內(nèi)熱門(mén)的研究方向,具有廣泛的應(yīng)用場(chǎng)景,例如人機(jī)交互、安全監(jiān)控,謊言檢測(cè)等等。隨著相關(guān)領(lǐng)域技術(shù)的發(fā)展,特別是自2006年以來(lái)深度學(xué)習(xí)(Deep Learning)技術(shù)的飛速發(fā)展,省去了人工設(shè)計(jì)和提取特征的步驟,換之以大數(shù)據(jù)樣本訓(xùn)練和自動(dòng)學(xué)習(xí)有效特征,從而大幅度提高算法模型準(zhǔn)確度和適應(yīng)性。因此,結(jié)合深度學(xué)習(xí)進(jìn)行人臉表情識(shí)別也成為當(dāng)下熱點(diǎn)之一。本文針對(duì)二維人臉圖像進(jìn)行表情分類識(shí)別研究。提出一種基于降噪自編碼器的人臉表情識(shí)別算法,在提高識(shí)別準(zhǔn)確率的同時(shí)能夠有效降低表情之間的干擾程度;設(shè)計(jì)一種輕量級(jí)的卷積神經(jīng)網(wǎng)絡(luò),能夠快速和較為有效地識(shí)別人臉表情;提出結(jié)合卷積神經(jīng)網(wǎng)絡(luò)和循環(huán)神經(jīng)網(wǎng)絡(luò)的表情識(shí)別方法,針對(duì)人臉圖像序列來(lái)識(shí)別表情。同時(shí),提出一種數(shù)據(jù)篩選框架和兩種較為簡(jiǎn)單的數(shù)據(jù)篩選方法,來(lái)對(duì)數(shù)據(jù)數(shù)據(jù)進(jìn)行預(yù)處理。
[Abstract]:Facial expression recognition is a challenging research topic in the fields of machine vision and pattern recognition. As a hot research direction in the field, facial expression recognition has a wide range of applications, such as human-computer interaction, security monitoring, etc. With the development of technology in related fields, especially the rapid development of deep learning technology since 2006, the steps of artificial design and feature extraction have been eliminated, and big data sample training and automatic learning effective features have been replaced. Thus greatly improving the accuracy and adaptability of the algorithm model. Facial expression recognition based on depth learning has become one of the hotspots. In this paper, facial expression recognition algorithm based on de-noising self-encoder is proposed. At the same time, it can effectively reduce the degree of interference between expressions, and design a lightweight convolution neural network, which can recognize facial expressions quickly and effectively. An expression recognition method based on convolutional neural network and cyclic neural network is proposed to recognize facial expression for face image sequence. At the same time, a data screening framework and two simple data selection methods are proposed. To preprocess the data.
【學(xué)位授予單位】：西南科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王志良,陳鋒軍,薛為民;人臉表情識(shí)別方法綜述[J];計(jì)算機(jī)應(yīng)用與軟件;2003年12期

2 孫蔚;王波;;人臉表情識(shí)別綜述[J];電腦知識(shí)與技術(shù);2012年01期

3 楊梅娟;;人臉表情識(shí)別綜述[J];甘肅科技;2006年04期

4 劉曉e，

本文編號(hào)：1550856