Facial Expression Recognition Based on TensorFlow Platform

Xia, Xiaoling; Xu, Chang; Nan, Bing

doi:10.1051/itmconf/20171201005

Cited by 27 publications

(12 citation statements)

References 16 publications

(23 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Together with FaceNet model, we implement Tensorflow framework [14], a machine learning system that can operate at large scale and in different environments. Tensorflow is the second generation of DistBelief.…”

Section: Face Recognitionmentioning

confidence: 99%

iFR: A New Framework for Real-Time Face Recognition with Deep Learning

Sukri

Ruhaiyem

2019

Advances in Visual Informatics

View full text Add to dashboard Cite

This paper investigates the performance of the real-time face recognition system with machine learning, as well as the performance of each haarcascade classifiers that based on accuracy and speed. We employ the subset of machine learning called deep learning to the real-time face recognition system as the deep face recognition technique has improved the state-of-the-art performance. This system uses a pre-trained model named FaceNet and employs triplet loss technique to impose a margin between every pair of faces from the same person to other faces. In other words, it minimizes the distance between the anchor and the positive from the same identity and maximizes the distance between the anchor and the negative from different identity. Furthermore, to further investigate the performance of the system, we implement the Tensorflow framework to improve the system performance by the usage of Graphics Processing Unit (GPU). This system uses Labeled Faces in Wild (LFW) dataset as the benchmark to test the performance of the face recognition system. Apart from that, we conduct a preliminary experiment to evaluate the performance of haarcascade classifiers so that we can choose the best classifier in term of accuracy and speed. Haarcascade_frontalface_default.xml (FD) exhibits best performance compared to haarcascade_frontalface_alt.xml (FA) and haarcas-cade_frontalface_alt2.xml (FA2) with accurate number of faces detected and shortest average time taken to detect faces.

show abstract

Section: Face Recognitionmentioning

confidence: 99%

iFR: A New Framework for Real-Time Face Recognition with Deep Learning

Sukri

Ruhaiyem

2019

Advances in Visual Informatics

View full text Add to dashboard Cite

show abstract

“…TensorFlow has the following features [18][19][20]: 1) High degree of flexibility: TensorFlow supports userdefined data flow diagrams, the user can build a map, and describe the drive to calculate the internal period. By using the rich and practical toolkit provided by TensorFlow, users can assemble their own "subgraph" to achieve a special neural network function.…”

Section: Tensorflow Frame and Its Characteristicsmentioning

confidence: 99%

Simulating and Predicting of Hydrological Time Series Based on TensorFlow Deep Learning

Qin¹,

Liang²,

Chen

et al. 2018

Pol. J. Environ. Stud.

View full text Add to dashboard Cite

Deep learning as an important part of machine learning, and there is a very wide range of application space. TensorFlow as the representative of deep learning the mainstream framework is also increasingly favored by the majority of research workers. The autoregressive model mainly uses the linear combination of stochastic variables at a specific time to describe the random variable at a certain time later [1]. With the development of time, many researchers have expanded the autoregressive model and applied it to many fields such as Bayesian, structural vector, spatial heterogeneous [2-4], and so on. LSTM is a long-and short-memory artificial neural network proposed by Hochreiter et al. and modified and promoted by Alex Graves [5]. LSTM can learn the shortand long-term dependent information of time series. Since the neural network contains a time memory unit, it is suitable for processing and predicting the interval and delay events in the time series [6-9]. In the prediction of hydrological time series, SENF C. and others [10]

show abstract

“…Therefore, an efficient algorithm is required to perform the processing and analysis of the captured image. Several machine learning algorithm has been proposed for traffic sign recognition include the TensorFlow transfer learning algorithm [8]- [10], AdaBoost algorithm [11], convolutional neural networks (CCN) algorithm [12], [13], fuzzy integral algorithm [14], neural network [15], artificial neural network (ANN) [16], deep learning [17], [18], color transformation [19], and texture feature extraction [20]. The types of algorithms used inside TensorFlow, such as transfer learning, increase the efficiency of the traffic sign recognition when compared to traditional machine learning.…”

Section: Introductionmentioning

confidence: 99%

“…The types of algorithms used inside TensorFlow, such as transfer learning, increase the efficiency of the traffic sign recognition when compared to traditional machine learning. Note that transfer learning is developed using information or knowledge from the surrounding environment [8]. The training and test samples are randomly selected, which can be a large amount of data or a small amount of labelled data.…”

Section: Introductionmentioning

confidence: 99%

Real-time traffic sign detection and recognition using Raspberry Pi

Isa

Yeong

Azyze

2022

IJECE

View full text Add to dashboard Cite

Nowadays, the number of road accident in Malaysia is increasing expeditiously. One of the ways to reduce the number of road accident is through the development of the advanced driving assistance system (ADAS) by professional engineers. Several ADAS system has been proposed by taking into consideration the delay tolerance and the accuracy of the system itself. In this work, a traffic sign recognition system has been developed to increase the safety of the road users by installing the system inside the car for driver’s awareness. TensorFlow algorithm has been considered in this work for object recognition through machine learning due to its high accuracy. The algorithm is embedded in the Raspberry Pi 3 for processing and analysis to detect the traffic sign from the real-time video recording from Raspberry Pi camera NoIR. This work aims to study the accuracy, delay and reliability of the developed system using a Raspberry Pi 3 processor considering several scenarios related to the state of the environment and the condition of the traffic signs. A real-time testbed implementation has been conducted considering twenty different traffic signs and the results show that the system has more than 90% accuracy and is reliable with an acceptable delay.

show abstract

Facial Expression Recognition Based on TensorFlow Platform

Cited by 27 publications

References 16 publications

iFR: A New Framework for Real-Time Face Recognition with Deep Learning

iFR: A New Framework for Real-Time Face Recognition with Deep Learning

Simulating and Predicting of Hydrological Time Series Based on TensorFlow Deep Learning

Real-time traffic sign detection and recognition using Raspberry Pi

Contact Info

Product

Resources

About