A fast face detection method via convolutional neural network

Guo, Guanjun; Wang, Hanzi; Yan, Yan; Zheng, Jiangbin; Li, Bo

doi:10.1016/j.neucom.2018.02.110

Cited by 44 publications

(21 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Banyak algoritme yang telah diusulkan untuk melakukan proses deteksi wajah pada video. Referensi [3] menggunakan Convolutional Neural Network (CNN) untuk melakukan proses deteksi wajah. Hasil yang diperoleh menunjukkan bahwa algoritme yang digunakan mampu untuk mendeteksi wajah.…”

Section: Pendahuluanunclassified

Deteksi Spoofing Wajah Menggunakan Faster R-CNN dengan Arsitektur Resnet50 pada Video

Megawan¹,

Lestari²

2020

JNTETI

View full text Add to dashboard Cite

Deteksi wajah merupakan proses mendasar dan penting dalam bidang pengenalan wajah yang sudah diteliti secara luas. Tujuan deteksi wajah adalah menentukan keberadaan dan menandai posisi wajah, baik pada gambar maupun video, yang disebut dengan bounding box. Salah satu masalah penting dalam deteksi wajah adalah membedakan wajah spoof dan non-spoof yang disebut sebagai deteksi spoofing wajah. Deteksi spoofing wajah merupakan pekerjaan penting yang digunakan untuk menjamin keamanan otentikasi berbasis wajah dan sistem analisis wajah. Oleh karena itu, dibutuhkan sebuah model yang dapat mendeteksi spoofing wajah. Pada makalah ini dilakukan proses membangun model yang dapat digunakan untuk mendeteksi wajah spoof dan non-spoof pada video menggunakan algoritme Faster R-CNN dengan arsitektur Resnet50. Faster R-CNN merupakan salah satu algoritme yang unggul dalam menyelesaikan berbagai persoalan deteksi objek. Dataset yang digunakan adalah Replay-Attack Database yang disediakan oleh Idiap Dataset Distribution Portal. Pada tahap training digunakan 360 video spoof dan non-spoof. Rata-rata nilai akurasi yang dihasilkan pada tahap training adalah 97,07%, dengan jumlah epoch sebanyak 21. Hasil pengujian menunjukkan bahwa model yang dihasilkan berhasil menentukan bounding box dengan akurat dan mendeteksi spoof dan non-spoof wajah pada video dengan efektif.

show abstract

Section: Pendahuluanunclassified

Deteksi Spoofing Wajah Menggunakan Faster R-CNN dengan Arsitektur Resnet50 pada Video

Megawan¹,

Lestari²

2020

JNTETI

View full text Add to dashboard Cite

show abstract

“…vector of fixed-length from the feature map is extracted for each and every object proposal by the pooling layer [7]. All possible feature vector is then fed to series of fully connected layers which in due course branches into sibling output layers, one amongst this layer generates softmax probability estimation over K classes of the object along with a catch-all background, class and the second layer, for each of the K object classes outputs four real-valued numbers.…”

Section: Evaluation and Evolution Of Object Detection Techniques Yolomentioning

confidence: 99%

“…The convolutional neural network architecture comprises prominently of three parts: the convolution layer, the pooling layer, and the fully connected layer. The pooling layer [7] extracts a fixed-length function matrix from the function chart for each and every item proposition. All function vectors are then supplied to the sequence of fully connected layers that branch into sibling input layers in due course, one of these layers produces softmax likelihood estimates over object groups along with a catch-all background, class and second layer for each of the object groups produces four real-valued numbers.…”

Section: Evaluation and Evolution Of Object Detection Techniques Yolomentioning

confidence: 99%

Evaluation and Evolution of Object Detection Techniques YOLO and R-CNN

2019

ijrte

View full text Add to dashboard Cite

Object detection has boomed in areas like image processing in accordance with the unparalleled development of CNN (Convolutional Neural Networks) over the last decade. The CNN family which includes R-CNN has advanced to much faster versions like Fast-RCNN which have mean average precision(Map) of up to 76.4 but their frames per second(fps) still remain between 5 to 18 and that is comparatively moderate to problem-solving time. Therefore, there is an urgent need to increase speed in the advancements of object detection. In accordance with the broad initiation of CNN and its features, this paper discusses YOLO (You only look once), a strong representative of CNN which comes up with an entirely different method of interpreting the task of detecting the objects. YOLO has attained fast speeds with fps of 155 and map of about 78.6, thereby surpassing the performances of other CNN versions appreciably. Furthermore, in comparison with the latest advancements, YOLOv2 attains an outstanding trade-off between accuracy and speed and also as a detector possessing powerful generalization capabilities of representing an entire image

show abstract

“…In 2017, Huang et al [ 9 ] proposed DenseNet, which made it possible for feature reusing and provided another way for feature fusion, which is realized by the concatenation of different feature maps. In recent years, the above mentioned two feature fusion methods, which are proposed in ResNet and DenseNet, that have been widely used in the tasks of image classification [ 10 , 11 ], semantic segmentation [ 12 , 13 ], object detection [ 14 , 15 ], etc. Additionally, they are served as the standard patterns of feature extraction based on CNN.…”

Section: Introductionmentioning

confidence: 99%

Spatial–Spectral Feature Refinement for Hyperspectral Image Classification Based on Attention-Dense 3D-2D-CNN

Zhang

Feng-yuan

Feng

et al. 2020

Sensors

View full text Add to dashboard Cite

Convolutional neural networks provide an ideal solution for hyperspectral image (HSI) classification. However, the classification effect is not satisfactory when limited training samples are available. Focused on “small sample” hyperspectral classification, we proposed a novel 3D-2D-convolutional neural network (CNN) model named AD-HybridSN (Attention-Dense-HybridSN). In our proposed model, a dense block was used to reuse shallow features and aimed at better exploiting hierarchical spatial–spectral features. Subsequent depth separable convolutional layers were used to discriminate the spatial information. Further refinement of spatial–spectral features was realized by the channel attention method and spatial attention method, which were performed behind every 3D convolutional layer and every 2D convolutional layer, respectively. Experiment results indicate that our proposed model can learn more discriminative spatial–spectral features using very few training data. In Indian Pines, Salinas and the University of Pavia, AD-HybridSN obtain 97.02%, 99.59% and 98.32% overall accuracy using only 5%, 1% and 1% labeled data for training, respectively, which are far better than all the contrast models.

show abstract

A fast face detection method via convolutional neural network

Cited by 44 publications

References 57 publications

Deteksi Spoofing Wajah Menggunakan Faster R-CNN dengan Arsitektur Resnet50 pada Video

Deteksi Spoofing Wajah Menggunakan Faster R-CNN dengan Arsitektur Resnet50 pada Video

Evaluation and Evolution of Object Detection Techniques YOLO and R-CNN

Spatial–Spectral Feature Refinement for Hyperspectral Image Classification Based on Attention-Dense 3D-2D-CNN

Contact Info

Product

Resources

About