scholarly journals Face Recognition on a Smart Image Sensor Using Local Gradients

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 2901
Author(s):  
Wladimir Valenzuela ◽  
Javier E. Soto ◽  
Payman Zarkesh-Ha ◽  
Miguel Figueroa
Keyword(s):  
Face Recognition ◽  
Nearest Neighbor ◽  
Local Binary Patterns ◽  
Image Sensor ◽  
Image Features ◽  
Cmos Process ◽  
Parasitic Extraction ◽  
Spatial Gradients ◽  
Field Programmable ◽  
Smart Pixel

In this paper, we present the architecture of a smart imaging sensor (SIS) for face recognition, based on a custom-design smart pixel capable of computing local spatial gradients in the analog domain, and a digital coprocessor that performs image classification. The SIS uses spatial gradients to compute a lightweight version of local binary patterns (LBP), which we term ringed LBP (RLBP). Our face recognition method, which is based on Ahonen’s algorithm, operates in three stages: (1) it extracts local image features using RLBP, (2) it computes a feature vector using RLBP histograms, (3) it projects the vector onto a subspace that maximizes class separation and classifies the image using a nearest neighbor criterion. We designed the smart pixel using the TSMC 0.35 μm mixed-signal CMOS process, and evaluated its performance using postlayout parasitic extraction. We also designed and implemented the digital coprocessor on a Xilinx XC7Z020 field-programmable gate array. The smart pixel achieves a fill factor of 34% on the 0.35 μm process and 76% on a 0.18 μm process with 32 μm × 32 μm pixels. The pixel array operates at up to 556 frames per second. The digital coprocessor achieves 96.5% classification accuracy on a database of infrared face images, can classify a 150×80-pixel image in 94 μs, and consumes 71 mW of power.

scholarly journals Identifikasi Tanda Tangan menggunakan Metode Fitur Ekstrasi Biner dan K Nearest Neighbor

2020 ◽  
Vol 12 (3) ◽  
pp. 191
Author(s):  
MUTIARA SARAHWATY SIMANJUNTAK
Keyword(s):  
Error Rate ◽  
Nearest Neighbor ◽  
Local Binary Patterns ◽  
Image Features ◽  
K Nearest Neighbor ◽  
Equal Error Rate

<em>Tanda tangan mempunya pola yang unik berdasarkan fitur yang ditinjau. Penelitian ini mengindentifikasi tanda tangan secara otomatis dengan menggunakan fitur biner dari hasil tanda tangan scanner. Identifikasi tanda tangan penting dilakukan otentifikasi dokumen administrasi dan resmi dimana nilai akurasi hal yang diperlukan. Dalam pendekatan yang dilakukan, fitur tanda tangan diekstrak dengan menggunakan dua descriptor yaitu binary statistical image features (BSIF) dan </em><em>local binary patterns (LBP). Penilaian menggunakan metode ini dengan melakukan percobaan dengan dua dataset yang sudah tersedia untuk umum yaitu database MCYT-75 dan GPDS-100. Dengan menggunakan metode klasifikasi KNN, mendapatkan nilai tertinggi masing-masing 96,7% dan 93,9%. Dalam verifikasi identifikasi tanda tangan akurasi klasifikasi diukur berdasarkan equal error rate (EER)yaitu 4.2% dan 5.33% pada GPDS-200 dan GPSD-150. Sehingga EER untuk database MCYT-75 sudah mencapau 7,78%. Nilai akurasi tersebut sudah dapat diketegorikan unggul.</em>

Pose and Illumination Invariance with Compound Image Transforms

2010 ◽  
pp. 301-315 ◽  
Author(s):  
Lior Shamir ◽  
Lior Shamir
Keyword(s):  
Face Recognition ◽  
Nearest Neighbor ◽  
Parameter Tuning ◽  
Image Features ◽  
Image Feature ◽  
Fisher Score ◽  
Image Transforms ◽  
The Face ◽  
Nearest Neighbor Rule ◽  
Compound Image

While current face recognition algorithms have provided convincing performance on frontal face poses, recognition is far less effective when the pose and illumination conditions vary. Here the authors show how compound image transforms can be used for face recognition in various poses and illumination conditions. The method works by first dividing each image into four equal-sized tiles. Then, image features are extracted from the face images, transforms of the images, and transforms of transforms of the images. Finally, each image feature is assigned with a Fisher score, and test images are classified by using a simple Weighted Nearest Neighbor rule such that the Fisher scores are used as weights. Experimental results using the full color FERET dataset show that with no parameter tuning, the accuracy of rank-10 recognition for frontal, quarter-profile, and half-profile images is ~98%, ~94% and ~91%, respectively. The proposed method also achieves perfect accuracy on several other face recognition datasets such as Yale B, ORL and JAFFE. An important feature of this method is that the recognition accuracy improves as the number of subjects in the dataset gets larger.

scholarly journals An Integrated Technique for Face Sketch Recognition Using DCNN

2019 ◽  
Vol 8 (10) ◽  
pp. 3133-3140
Keyword(s):  
Face Recognition ◽  
Principal Component ◽  
Local Binary Patterns ◽  
Image Features ◽  
Local Descriptor ◽  
Multi Scale ◽  
Face Sketch Recognition ◽  
Tchebichef Moments ◽  
The Face ◽  
Integrated Technique

Face Recognition (FR) is considered as one of the chief use in the investigation of criminals. In the majority of the cases, information about the criminal is not available. In such situations, sketch artist draw the sketch of the guess with the oral explanation provided by the eyewitness. These sketches can then be matched manually against mug shot photos. This process is time-consuming. Hence there require a method that efficiently goes with composite sketches to the gallery of mug shot databases. Thus the proposed system uses a scheme for matching composite sketch and photo images, photo image features are extracted and fused to train the system. Composite Sketch feature is matched with face photo images. Feature extraction (FE) is done using Multi-Scale Local Binary Patterns (MLBP) Tchebichef Moments and Multiscale Circular Weber Local Descriptor (MCWLD), Principal Component Analysis (PCA) is used for fusion of extracted features, DCNN used as a classifier to recognize the face. The experiments are conducted using PRIP-HDC dataset and the proposed system gives good accuracy in face recognition.

Sketch Face Recognition: P-HOG Multi-Features Fusion

2019 ◽  
Vol 33 (04) ◽  
pp. 1956003
Author(s):  
Zhenxue Chen ◽  
Saisai Yao ◽  
Chengyun Liu ◽  
Lei Cai
Keyword(s):  
Face Recognition ◽  
Nearest Neighbor ◽  
Image Features ◽  
Face Image ◽  
Biometric Recognition ◽  
Features Fusion ◽  
Weighted Fusion ◽  
Criminal Suspect ◽  
The Face ◽  
Global And Local

With the development of biometric recognition technology, sketch face recognition has been widely applied to assist the police to confirm the identity of the criminal suspect. Most of the present recognition methods use the image features directly, in which the key parts can’t be used sufficiently. This paper presents a sketch face recognition method based on P-HOG multi-features weighted fusion. Firstly, the global face image and the local face image which contains key components of the face are divided into patches based on spatial scale pyramid, and then the global P-HOG features and local P-HOG features are extracted, respectively. After that, the dimensions of global and local features are reduced using PCA and NLDA. Finally, the features are weighted based on sensitivity and fused. The nearest neighbor classifier is used to complete the final recognition. The experimental results on different databases show that the proposed method outperforms state-of-the-art methods.

scholarly journals The Design of a 2D Graphics Accelerator for Embedded Systems

Electronics ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 469
Author(s):  
Hyun Woo Oh ◽  
Ji Kwang Kim ◽  
Gwan Beom Hwang ◽  
Seung Eun Lee
Keyword(s):  
Embedded Systems ◽  
Embedded System ◽  
Real Time ◽  
Line Drawing ◽  
Cmos Process ◽  
Embedded Processor ◽  
Processor Core ◽  
Field Programmable ◽  
The Embedded System ◽  
Graphics Processing

Recently, advances in technology have enabled embedded systems to be adopted for a variety of applications. Some of these applications require real-time 2D graphics processing running on limited design specifications such as low power consumption and a small area. In order to satisfy such conditions, including a specific 2D graphics accelerator in the embedded system is an effective method. This method reduces the workload of the processor in the embedded system by exploiting the accelerator. The accelerator assists the system to perform 2D graphics processing in real-time. Therefore, a variety of applications that require 2D graphics processing can be implemented with an embedded processor. In this paper, we present a 2D graphics accelerator for tiny embedded systems. The accelerator includes an optimized line-drawing operation based on Bresenham’s algorithm. The optimized operation enables the accelerator to deal with various kinds of 2D graphics processing and to perform the line-drawing instead of the system processor. Moreover, the accelerator also distributes the workload of the processor core by removing the need for the core to access the frame buffer memory. We measure the performance of the accelerator by implementing the processor, including the accelerator, on a field-programmable gate array (FPGA), and ascertaining the possibility of realization by synthesizing using the 180 nm CMOS process.

Exploring the Uncertainty Space of Ensemble Classifiers in Face Recognition

2015 ◽  
Vol 29 (03) ◽  
pp. 1556002 ◽  
Author(s):  
Juan Luis Fernández-Martínez ◽  
Ana Cernea
Keyword(s):  
Face Recognition ◽  
Nearest Neighbor ◽  
Learning Algorithm ◽  
Majority Voting ◽  
Borda Count ◽  
Discrete Wavelet ◽  
Final Decision ◽  
Ensemble Classifiers ◽  
Classification Problems ◽  
Uncertainty Space

In this paper, we present a supervised ensemble learning algorithm, called SCAV1, and its application to face recognition. This algorithm exploits the uncertainty space of the ensemble classifiers. Its design includes six different nearest-neighbor (NN) classifiers that are based on different and diverse image attributes: histogram, variogram, texture analysis, edges, bidimensional discrete wavelet transform and Zernike moments. In this approach each attribute, together with its corresponding type of the analysis (local or global), and the distance criterion (p-norm) induces a different individual NN classifier. The ensemble classifier SCAV1 depends on a set of parameters: the number of candidate images used by each individual method to perform the final classification and the individual weights given to each individual classifier. SCAV1 parameters are optimized/sampled using a supervised approach via the regressive particle swarm optimization algorithm (RR-PSO). The final classifier exploits the uncertainty space of SCAV1 and uses majority voting (Borda Count) as a final decision rule. We show the application of this algorithm to the ORL and PUT image databases, obtaining very high and stable accuracies (100% median accuracy and almost null interquartile range). In conclusion, exploring the uncertainty space of ensemble classifiers provides optimum results and seems to be the appropriate strategy to adopt for face recognition and other classification problems.

Face Recognition Based on Local Binary Patterns with Threshold

2010 ◽  
Author(s):  
Jun Meng ◽  
Yumao Gao ◽  
Xiukun Wang ◽  
Tsauyoung Lin ◽  
Jianying Zhang
Keyword(s):  
Face Recognition ◽  
Local Binary Patterns

scholarly journals Patch-Based Principal Component Analysis for Face Recognition

2017 ◽  
Vol 2017 ◽  
pp. 1-9 ◽  
Author(s):  
Tai-Xiang Jiang ◽  
Ting-Zhu Huang ◽  
Xi-Le Zhao ◽  
Tian-Hui Ma
Keyword(s):  
Principal Component Analysis ◽  
Face Recognition ◽  
Nearest Neighbor ◽  
Spatial Information ◽  
Principal Component ◽  
Component Analysis ◽  
Two Dimensional ◽  
Face Images ◽  
Pca Method ◽  
Local Spatial Information

We have proposed a patch-based principal component analysis (PCA) method to deal with face recognition. Many PCA-based methods for face recognition utilize the correlation between pixels, columns, or rows. But the local spatial information is not utilized or not fully utilized in these methods. We believe that patches are more meaningful basic units for face recognition than pixels, columns, or rows, since faces are discerned by patches containing eyes and noses. To calculate the correlation between patches, face images are divided into patches and then these patches are converted to column vectors which would be combined into a new “image matrix.” By replacing the images with the new “image matrix” in the two-dimensional PCA framework, we directly calculate the correlation of the divided patches by computing the total scatter. By optimizing the total scatter of the projected samples, we obtain the projection matrix for feature extraction. Finally, we use the nearest neighbor classifier. Extensive experiments on the ORL and FERET face database are reported to illustrate the performance of the patch-based PCA. Our method promotes the accuracy compared to one-dimensional PCA, two-dimensional PCA, and two-directional two-dimensional PCA.

Sign in / Sign up

Export Citation Format

Share Document