scholarly journals Research on Face Recognition Classification Based on Improved GoogleNet

2022 ◽  
Vol 2022 ◽  
pp. 1-6
Author(s):  
Zhigang Yu ◽  
Yunyun Dong ◽  
Jihong Cheng ◽  
Miaomiao Sun ◽  
Feng Su
Keyword(s):  
Face Recognition ◽  
Network Performance ◽  
Recall Rate ◽  
Experimental Results ◽  
Learning Technology ◽  
Learning Method ◽  
Learning Methods ◽  
Improve Accuracy ◽  
And Migration ◽  
Better Than

Face recognition is a relatively mature technology, which has some applications in many aspects, and now there are many networks studying it, which has indeed brought a lot of convenience to mankind in all aspects. This paper proposes a new face recognition technology. First, a new GoogLeNet-M network is proposed, which improves network performance on the basis of streamlining the network. Secondly, regularization and migration learning methods are added to improve accuracy. The experimental results show that the GoogLeNet-M network with regularization using migration learning technology has the best performance, with a recall rate of 0.97 and an accuracy of 0.98. Finally, it is concluded that the performance of the GoogLeNet-M network is better than other networks on the dataset, and the migration learning method and regularization help to improve the network performance.

scholarly journals Pengaruh Metode Pembelajaran Dan Kecerdasan Interpersonal Terhadap Kompetensi Komunikasi Terapeutik Mahasiswa Program DIII Kebidanan Stikes Mitra Ria Husada Cibubur

2018 ◽  
Vol 20 (1) ◽  
pp. 1-12
Author(s):  
Dina Martha ◽  
Hartati Hartati ◽  
Zulfiati Syahrial
Keyword(s):  
Teaching Methods ◽  
Communication Competence ◽  
Learning Method ◽  
Bedside Teaching ◽  
Appropriate Use ◽  
Therapeutic Communication ◽  
Learning Methods ◽  
Coaching Methods ◽  
Level 3 ◽  
Better Than

This study aims to determine the method of learning and interpersonal intelligence to therapeutic communication competence of DIII students Obstetrics STIKes Mitra RIA Husada. Learning methods are placed on bedside teaching methods, coaching methods and demonstrations. The method used in this research is experiment with treatment design level 3 x 2 with sample 48 student. The summary of this research is: 1) Bedside teaching methods can improve therapeutic communication better than coaching methods and methods of demonstration; 2) Coaching learning method can improve therapeutic communication better than demonstration; 3) The existence of interaction between learning method and intelligent interpersonal to therapeutic communication competence; 4) students who have high interpersonal intelligence, more appropriate use of bedside teaching methods; 5) students who have low interpersonal intelligence, more appropriate use of coaching learning methods than the method of demonstration.

scholarly journals Effect Of Direct Learning Method And Problem Solving Learning Method On High Jump Of Skills

2020 ◽  
Vol 3 (2) ◽  
pp. 165-176
Author(s):  
Syahruddin Syahruddin ◽  
Muhammad Syahrul Saleh ◽  
M. Sahib Saleh ◽  
Irmawati Irmawati
Keyword(s):  
Problem Solving ◽  
Jump Process ◽  
Learning Method ◽  
Research Subjects ◽  
Learning Methods ◽  
Skill Test ◽  
Direct Learning ◽  
Better Than

This study aims to determine is there any effect of direct learning methods (MPL) on high jump skills, is there any influence of problem solving learning methods (MPM) on high jump skills, and there are differences in the effect of direct learning methods (MPL) and problem solving learning methods (MPM) on high jump skills. The research subjects were students SMP Negeri 29 Makassar and were randomly selected and 20 people were gathered, and made into two groups consisting of 10 people each group. The research used a pretest-posttest design. This research was conducted during eight meetings. Before treatment, samples were given in a process high jump of skill test, then were treated according to the methods of each group then after treatment were given a posttest. The results showed that there was a significant effect of MPL on high jumping of skills (p <0.05); there was a significant effect of MPM on increasing the high jump process of skills (p <0.05); and MPM significantly improved high jumping  of skills than MPL (p <0.05). The conclusion of this study 1) MPL improves high jumping skills, 2) MPM increases high jumping skills, and 3) MPM is better than MPL.

AN EVALUATION ON PERFORMANCE OF PCA IN FACE RECOGNITION WITH EXPRESSION VARIATIONS

2018 ◽  
Vol 1 (30) ◽  
pp. 61-66
Author(s):  
Khanh Ngoc Van Duong ◽  
An Bao Nguyen
Keyword(s):  
Face Recognition ◽  
Facial Expression ◽  
Mouth Opening ◽  
Experimental Results ◽  
Classification Algorithms ◽  
Test Cases ◽  
Wide Mouth ◽  
Better Than

Appearance-based recognition methods often encounter difficulties when the input images contain facial expression variations such as laughing, crying or wide mouth opening. In these cases, holistic methods give better performance than appearance-based methods. This paper presents some evaluation on face recognition under variation of facial expression  using the combination of PCA and classification algorithms. The experimental results showed that the best accuracy can be obtained with very few eigenvectors and KNN algorithm (with k=1) performs better than SVM in most test cases.

scholarly journals Unsupervised Trademark Retrieval Method Based on Attention Mechanism

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1894
Author(s):  
Jiangzhong Cao ◽  
Yunfei Huang ◽  
Qingyun Dai ◽  
Wing-Kuen Ling
Keyword(s):  
Supervised Learning ◽  
Attention Mechanism ◽  
Feature Representation ◽  
Experimental Results ◽  
Learning Methods ◽  
Retrieval Method ◽  
Average Rank ◽  
Good Feature ◽  
Key Features ◽  
Better Than

Aiming at the high cost of data labeling and ignoring the internal relevance of features in existing trademark retrieval methods, this paper proposes an unsupervised trademark retrieval method based on attention mechanism. In the proposed method, the instance discrimination framework is adopted and a lightweight attention mechanism is introduced to allocate a more reasonable learning weight to key features. With an unsupervised way, this proposed method can obtain good feature representation of trademarks and improve the performance of trademark retrieval. Extensive comparative experiments on the METU trademark dataset are conducted. The experimental results show that the proposed method is significantly better than traditional trademark retrieval methods and most existing supervised learning methods. The proposed method obtained a smaller value of NAR (Normalized Average Rank) at 0.051, which verifies the effectiveness of the proposed method in trademark retrieval.

Discriminative Low-Rank Subspace Learning with Nonconvex Penalty

2019 ◽  
Vol 33 (10) ◽  
pp. 1951006
Author(s):  
Kan Xie ◽  
Wei Liu ◽  
Yue Lai ◽  
Weijun Li
Keyword(s):  
Face Recognition ◽  
State Of The Art ◽  
Subspace Learning ◽  
Experimental Results ◽  
Low Rank ◽  
Learning Method ◽  
Original Solution ◽  
Discriminative Subspace ◽  
Low Rank Representation ◽  
Facial Images

Subspace learning has been widely utilized to extract discriminative features for classification task, such as face recognition, even when facial images are occluded or corrupted. However, the performance of most existing methods would be degraded significantly in the scenario of that data being contaminated with severe noise, especially when the magnitude of the gross corruption can be arbitrarily large. To this end, in this paper, a novel discriminative subspace learning method is proposed based on the well-known low-rank representation (LRR). Specifically, a discriminant low-rank representation and the projecting subspace are learned simultaneously, in a supervised way. To avoid the deviation from the original solution by using some relaxation, we adopt the Schatten [Formula: see text]-norm and [Formula: see text]-norm, instead of the nuclear norm and [Formula: see text]-norm, respectively. Experimental results on two famous databases, i.e. PIE and ORL, demonstrate that the proposed method achieves better classification scores than the state-of-the-art approaches.

scholarly journals Speech enhancement methods based on binaural cue coding

2019 ◽  
Vol 2019 (1) ◽  
Author(s):  
Xianyun Wang ◽  
Changchun Bao
Keyword(s):  
Neural Network ◽  
Speech Enhancement ◽  
Speech Signal ◽  
Deep Neural Network ◽  
Experimental Results ◽  
Channel Correlation ◽  
Noisy Speech ◽  
Time Frequency ◽  
Improve Accuracy ◽  
Better Than

AbstractAccording to the encoding and decoding mechanism of binaural cue coding (BCC), in this paper, the speech and noise are considered as left channel signal and right channel signal of the BCC framework, respectively. Subsequently, the speech signal is estimated from noisy speech when the inter-channel level difference (ICLD) and inter-channel correlation (ICC) between speech and noise are given. In this paper, exact inter-channel cues and the pre-enhanced inter-channel cues are used for speech restoration. The exact inter-channel cues are extracted from clean speech and noise, and the pre-enhanced inter-channel cues are extracted from the pre-enhanced speech and estimated noise. After that, they are combined one by one to form a codebook. Once the pre-enhanced cues are extracted from noisy speech, the exact cues are estimated by a mapping between the pre-enhanced cues and a prior codebook. Next, the estimated exact cues are used to obtain a time-frequency (T-F) mask for enhancing noisy speech based on the decoding of BCC. In addition, in order to further improve accuracy of the T-F mask based on the inter-channel cues, the deep neural network (DNN)-based method is proposed to learn the mapping relationship between input features of noisy speech and the T-F masks. Experimental results show that the codebook-driven method can achieve better performance than conventional methods, and the DNN-based method performs better than the codebook-driven method.

scholarly journals Face Recognition Using Complex Valued Backpropagation

2018 ◽  
Vol 11 (2) ◽  
pp. 103
Author(s):  
Zumrotun Nafisah ◽  
Febrian Rachmadi ◽  
Elly Matul Imah
Keyword(s):  
Face Recognition ◽  
Research Area ◽  
Experimental Results ◽  
Activation Functions ◽  
Backpropagation Algorithm ◽  
Complex Valued ◽  
Better Than

Face recognition is one of biometrical research area that is still interesting. This study discusses the Complex-Valued Backpropagation algorithm for face recognition. Complex-Valued Backpropagation is an algorithm modified from Real-Valued Backpropagation algorithm where the weights and activation functions used are complex. The dataset used in this study consist of 250 images that is classified in 5 classes. The performance of face recognition using Complex-Valued Backpropagation is also compared with Real-Valued Backpropagation algorithm. Experimental results have shown that Complex-Valued Backpropagation performance is better than Real-Valued Backpropagation.

scholarly journals Hide and seek in pathology- A research on game-based histopathology learning

2019 ◽  
Vol 10 (2) ◽  
pp. 1410-1414
Author(s):  
Brundha MP ◽  
Deepak Nallaswamy
Keyword(s):  
Undergraduate Students ◽  
Questionnaire Survey ◽  
Dental Students ◽  
Morphological Features ◽  
Learning Method ◽  
Game Based Learning ◽  
Learning Methods ◽  
Significant Difference ◽  
Diagnostic Capacity ◽  
Better Than

To know the effectiveness of a Game-Based Histopathology learning method.  To create a new Image oriented Game Based Histopathology slide reading method. To know the usefulness of the new method. To compare the conventional learning and game-based learning methods. Two groups of undergraduate students were tested with two different learning methods to identify pathology slide sections of four lesions. For each group, sixteen Undergraduate dental students were selected randomly. A game was created by using histopathology images of those four lesions, and circulated among the group one. The conventional method of slide reading was given to the group two. Both the group was tested for diagnosing the four pathology lesions through light microscopy spotter identification. Results were calculated accordingly. A questionnaire survey was done based on the pattern and pathology features oriented diagnostic capacity. Results of the questionnaire survey were also analyzed. Statistically, the results of both the two groups were analyzed. An Independent t-test was done and found out there was no significant difference between the two learning methods. The questionnaire survey revealed that the group learned through game-based pathology slide learning method learned the morphological features better than that of the conventional slide learning method. The image oriented game based pathology slide learning helps the undergraduate students to diagnose the pathology lesions with proper knowledge of morphological features than the conventional slide learning method, which is mainly pattern oriented. Though it is a very complicated procedure, the game based slide learning method is fun, creative and involves a majority of the student’s attention towards morphological features of any pathological lesions.

scholarly journals Celebrity Face Recognition using Deep Learning

2018 ◽  
Vol 12 (2) ◽  
pp. 476 ◽  
Author(s):  
Nur Ateqah Binti Mat Kasim ◽  
Nur Hidayah Binti Abd Rahman ◽  
Zaidah Ibrahim ◽  
Nur Nabilah Abu Mangshor
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Deep Learning ◽  
Face Recognition ◽  
Convolutional Neural Network ◽  
Facial Expressions ◽  
Experimental Results ◽  
Learning Technique ◽  
Excellent Accuracy ◽  
Better Than

Face recognition is one of the well studied problems by researchers in computer visions.  Among the challenges of this task are the occurrence of different facial expressions like happy or sad, and different views of the images such as front and side views.  This paper experiments a publicly available dataset that consists of 200,000 images of celebrity faces. Deep Learning technique is gaining its popularity in computer vision and this paper applies this technique for face recognition problem.  One of the techniques under deep learning is Convolutional Neural Network (CNN).  There is also pre-trained CNN models that are AlexNet and GoogLeNet, which produce excellent accuracy results.  The experimental results indicate that AlexNet is better than basic CNN and GoogLeNet for face recognition.

Contribution of Color to Face Recognition

Perception ◽  
10.1068/p3376 ◽  
2002 ◽  
Vol 31 (8) ◽  
pp. 995-1003 ◽  
Author(s):  
Andrew W Yip ◽  
Pawan Sinha
Keyword(s):  
Image Analysis ◽  
Face Recognition ◽  
Recognition Performance ◽  
Past Research ◽  
Color Images ◽  
Experimental Results ◽  
Facial Attributes ◽  
Color Cues ◽  
Better Than

One of the key challenges in face perception lies in determining how different facial attributes contribute to judgments of identity. In this study, we focus on the role of color cues. Although color appears to be a salient attribute of faces, past research has suggested that it confers little recognition advantage for identifying people. Here we report experimental results suggesting that color cues do play a role in face recognition and their contribution becomes evident when shape cues are degraded. Under such conditions, recognition performance with color images is significantly better than that with gray-scale images. Our experimental results also indicate that the contribution of color may lie not so much in providing diagnostic cues to identity as in aiding low-level image-analysis processes such as segmentation.

Sign in / Sign up

Export Citation Format

Share Document