Low-shot Face Recognition using Hierarchical Deep Convolutional Neural Networks
碩士 === 國立中央大學 === 資訊工程學系 === 105 === In recent years, machine learning has flourishingly developed in face detection and face recognition which are widely used in variety applications, such as access control, monitoring, identity authentication, smart devices, etc. However, face detection and face r...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2017
|
Online Access: | http://ndltd.ncl.edu.tw/handle/smezmg |
id |
ndltd-TW-105NCU05392095 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-105NCU053920952019-05-15T23:39:52Z http://ndltd.ncl.edu.tw/handle/smezmg Low-shot Face Recognition using Hierarchical Deep Convolutional Neural Networks 以階層式深度卷積網路實現少樣本的人臉辨識系統 Ming-Hsin Shen 沈明訢 碩士 國立中央大學 資訊工程學系 105 In recent years, machine learning has flourishingly developed in face detection and face recognition which are widely used in variety applications, such as access control, monitoring, identity authentication, smart devices, etc. However, face detection and face recognition are always encountered difficult factors, such as different lighting conditions, different facial expressions, facial rotation, occlusion, and small number of samples. Based on the traditional methods, the detected and recognized result are not accepted. Thus, in this study, we use convolutional neural networks to overcome the problems, and improve the recognition rate in face recognition system. The proposed system consists of two parts. In the first part, we use the faster R-CNN (Faster Region Convolutional Neural Network) with sufficient samples to recognize faces with overcoming the various lighting conditions, blurred, and various views of faces. In the second part, we use the Siamese neural network to recognize faces in the minor classes with a few samples. In the experiments, we use our own videos to test the face detection and recognition in various environments such as different lighting conditions, face sizes, and face directions. In the detection stage, the detection rate can reach 96.84%, false positive rate (Misjudgment Ratio) is almost 0%. In the case of face recognition of 1920×1080 images, the recognition rate is 99.65% with 12.76 frames per second (FPS). In the other case of 960×540 images, the FPS is 24.03. With the Siamese network, we distinguish two face images to achieve the recognition rate being 92.4%. 曾定章 2017 學位論文 ; thesis 60 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立中央大學 === 資訊工程學系 === 105 === In recent years, machine learning has flourishingly developed in face detection and face recognition which are widely used in variety applications, such as access control, monitoring, identity authentication, smart devices, etc. However, face detection and face recognition are always encountered difficult factors, such as different lighting conditions, different facial expressions, facial rotation, occlusion, and small number of samples. Based on the traditional methods, the detected and recognized result are not accepted. Thus, in this study, we use convolutional neural networks to overcome the problems, and improve the recognition rate in face recognition system.
The proposed system consists of two parts. In the first part, we use the faster R-CNN (Faster Region Convolutional Neural Network) with sufficient samples to recognize faces with overcoming the various lighting conditions, blurred, and various views of faces. In the second part, we use the Siamese neural network to recognize faces in the minor classes with a few samples.
In the experiments, we use our own videos to test the face detection and recognition in various environments such as different lighting conditions, face sizes, and face directions. In the detection stage, the detection rate can reach 96.84%, false positive rate (Misjudgment Ratio) is almost 0%. In the case of face recognition of 1920×1080 images, the recognition rate is 99.65% with 12.76 frames per second (FPS). In the other case of 960×540 images, the FPS is 24.03. With the Siamese network, we distinguish two face images to achieve the recognition rate being 92.4%.
|
author2 |
曾定章 |
author_facet |
曾定章 Ming-Hsin Shen 沈明訢 |
author |
Ming-Hsin Shen 沈明訢 |
spellingShingle |
Ming-Hsin Shen 沈明訢 Low-shot Face Recognition using Hierarchical Deep Convolutional Neural Networks |
author_sort |
Ming-Hsin Shen |
title |
Low-shot Face Recognition using Hierarchical Deep Convolutional Neural Networks |
title_short |
Low-shot Face Recognition using Hierarchical Deep Convolutional Neural Networks |
title_full |
Low-shot Face Recognition using Hierarchical Deep Convolutional Neural Networks |
title_fullStr |
Low-shot Face Recognition using Hierarchical Deep Convolutional Neural Networks |
title_full_unstemmed |
Low-shot Face Recognition using Hierarchical Deep Convolutional Neural Networks |
title_sort |
low-shot face recognition using hierarchical deep convolutional neural networks |
publishDate |
2017 |
url |
http://ndltd.ncl.edu.tw/handle/smezmg |
work_keys_str_mv |
AT minghsinshen lowshotfacerecognitionusinghierarchicaldeepconvolutionalneuralnetworks AT chénmíngxīn lowshotfacerecognitionusinghierarchicaldeepconvolutionalneuralnetworks AT minghsinshen yǐjiēcéngshìshēndùjuǎnjīwǎnglùshíxiànshǎoyàngběnderénliǎnbiànshíxìtǒng AT chénmíngxīn yǐjiēcéngshìshēndùjuǎnjīwǎnglùshíxiànshǎoyàngběnderénliǎnbiànshíxìtǒng |
_version_ |
1719152686164606976 |