FPGA Implementation of Multi-scale Face Detection Using HOG Features and SVM Classifier

Drożdż, Michał; Kryjak, Tomasz

doi:10.1515/ipc-2016-0014

Cited by 18 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Inspired by the sliding window method [37], we gather the sub-images (11 × 11 pixels) with stride equal 1 pixel horizontally and vertically from each UVI image. Since the auroral images used in this work have a fixed size of 228 × 200 as shown in Figure 6a, 45,600 sub-images with the size of 11 × 11 can be obtained after padding zeros at the border of each image.…”

Section: Constructing the Global Energy Termmentioning

confidence: 99%

UVI Image Segmentation of Auroral Oval: Dual Level Set and Convolutional Neural Network Based Approach

Tian

Yang

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

The auroral ovals around the Earth’s magnetic poles are produced by the collisions between energetic particles precipitating from solar wind and atoms or molecules in the upper atmosphere. The morphology of auroral oval acts as an important mirror reflecting the solar wind-magnetosphere-ionosphere coupling process and its intrinsic mechanism. However, the classical level set based segmentation methods often fail to extract an accurate auroral oval from the ultraviolet imager (UVI) image with intensity inhomogeneity. The existing methods designed specifically for auroral oval extraction are extremely sensitive to the contour initializations. In this paper, a novel deep feature-based adaptive level set model (DFALS) is proposed to tackle these issues. First, we extract the deep feature from the UVI image with the newly designed convolutional neural network (CNN). Second, with the deep feature, the global energy term and the adaptive time-step are constructed and incorporated into the local information based dual level set auroral oval segmentation method (LIDLSM). Third, we extract the contour of the auroral oval through the minimization of the proposed energy functional. The experiments on the UVI image data set validate the strong robustness of DFALS to different contour initializations. In addition, with the help of deep feature-based global energy term, the proposed method also obtains higher segmentation accuracy in comparison with the state-of-the-art level set based methods.

show abstract

Section: Constructing the Global Energy Termmentioning

confidence: 99%

UVI Image Segmentation of Auroral Oval: Dual Level Set and Convolutional Neural Network Based Approach

Tian

Yang

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Inspired by the sliding window technique (Drożdż & Kryjak, 2017), we gather the subimages (11 × 11) centered on each pixel in the test UVI images, which have a fixed frame of 228 × 200 pixels. Therefore, 45,600 subimages can be gathered from each image after padding zeros at the border.…”

Section: Algorithm Descriptionmentioning

confidence: 99%

Automatic Auroral Boundary Determination Algorithm With Deep Feature and Dual Level Set

Tian

Yang

et al. 2020

JGR Space Physics

View full text Add to dashboard Cite

The morphology of the auroral oval is an important geophysical parameter that helps to further understand the solar wind-magnetosphere-ionosphere coupling process. However, it is still a challenging task to automatically obtain auroral poleward and equatorward boundaries completely and accurately. In this paper, a new model based on the deep feature and dual level set method is proposed to extract the auroral oval boundaries in the images acquired by the Ultraviolet Imager (UVI) onboard the Polar spacecraft. With the deep feature extracted by the convolutional neural network (CNN), the corresponding deep feature energy functional is constructed and incorporated into the variational segmentation framework. The dual level set method is implemented to extract the accurate poleward and equatorward boundaries with the gradient descent flow. The experimental results on the test data set demonstrate that this model can extract complete auroral oval contours that are consistent well with annotations and owns higher accuracy compared with the previously proposed methods. Comparison between the extracted auroral boundaries and the precipitating boundaries determined by Defense Meteorological Satellite Program (DMSP) SSJ precipitating particle data validates that the proposed method is trustworthy to capture the global morphology of the auroral ovals.

show abstract

“…Among popular face recognition models which have been developed by universities and companies, there are VGGFace [3], DeepFace [4], [5], OpenFace [6], and FaceNet [7]. In [8], a face recognition model based on the histogram of oriented gradients (HOG) and support vector machine (SVM) classifier was investigated. Besides, in [9], a method based on the AdaBoost algorithm was used to train cascade classifiers with feature types such as the HOG and the Haar-like.…”

Section: Introductionmentioning

confidence: 99%

Implementation of FaceNet and support vector machine in a real-time web-based timekeeping application

Trieu

Nguyen

2022

IJ-AI

View full text Add to dashboard Cite

This paper presents in detail how to build up and implement a real-time web-based face recognition application. The system works so that images of people are recorded and compared with the references on the database. If they match, the information about their presence will be recorded. As for the system architecture, the multi-task cascaded neural network was deployed for face detection. Followingly, for the recognizing tasks, we conducted a study to compare the accuracy level of three different face recognizing methods on three different public datasets by means of both the literature review and our simulation. From the comparison, it can be drawn that the FaceNet algorithm in-used with the support vector machine (SVM) classifier performs the best among others and is the most suitable candidate for the practical deployment. Eventually, the proposed system can deliver a highly satisfactory result, proving its potentials not only for the research but also the commercial purposes.

show abstract

FPGA Implementation of Multi-scale Face Detection Using HOG Features and SVM Classifier

Cited by 18 publications

References 22 publications

UVI Image Segmentation of Auroral Oval: Dual Level Set and Convolutional Neural Network Based Approach

UVI Image Segmentation of Auroral Oval: Dual Level Set and Convolutional Neural Network Based Approach

Automatic Auroral Boundary Determination Algorithm With Deep Feature and Dual Level Set

Implementation of FaceNet and support vector machine in a real-time web-based timekeeping application

Contact Info

Product

Resources

About