Deep Sketch-Photo Face Recognition Assisted by Facial Attributes

Iranmanesh, Seyed Mehdi; Kazemi, Hadi; Soleymani, Sobhan; Dabouei, Ali; Nasrabadi, Nasser M.

doi:10.1109/btas.2018.8698564

Cited by 18 publications

(13 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Deep coupled framework to address the challenge of matching sketch picture to a gallery of mugshots, as reported by Seyed Mehdi et al [3]. Face drawings contain all of the necessary information about the spatial topology and geometric aspects of faces, but they lack critical facial characteristics like ethnicity, hair, eye, and skin color.…”

Section: Open Accessmentioning

confidence: 99%

Interactive Attendance System for Modern Education Using Computational Intelligence

Kumar¹,

Alam²,

Polat³

2021

JIEC

View full text Add to dashboard Cite

The modern age is marked exclusively by advancements in digital technology. Modern education is not untouched by this advancement. However, there are few systems at present, which use computational intelligence in modern education. Currently, digital technology is bounded by commercial uses. In particular, face recognition is mainly used in criminal identification, security, payment, advertising, and healthcare. This project, Interactive Attendance System For Modern Education Using Computational Intelligence, is an attempt to combine modern education with modern computing. It uses the concept of Face Recognition to identify the person and to create an attendance file. The coding is done in the Python language on a Raspberry Pi 3B+ kit with Raspbian. Image pre-processing is used to convert captured images into grayscale and to extract areas of interest, i.e., faces. Machine learning is used to train the system to recognize faces using the LBPH Face Recognizer. This system can be installed in any modern educational institute for smart attendance.

show abstract

Section: Open Accessmentioning

confidence: 99%

Interactive Attendance System for Modern Education Using Computational Intelligence

Kumar¹,

Alam²,

Polat³

2021

JIEC

View full text Add to dashboard Cite

show abstract

“…DNN models for 3D human pose estimation focus on a single view, with a complex background setting [14,19]. Machine learning models using Logistic Regression [20], Artificial Neural Networks (ANN) [21], K-Star [22], Random Forest [23], K-nearest neighbors (KNN) [24] and Support Vector Machines (SVM) [25] can identify and classify patterns of gait, thus provide valuable insight into medical conditions [16].…”

Section: Machine Learningmentioning

confidence: 99%

“…As deep learning approaches emerge and advance, DNN-based techniques are the standard in visions tasks such as human motion tracking and pose estimation [16], human activity recognition [17] and face recognition [18]. Several hidden layers between the output and input layers, and the ones that can learn semantic and high-level features from the data to model complex non-linear relationships, make up DNNs.…”

Section: Machine Learningmentioning

confidence: 99%

Computer Vision and Abnormal Patient Gait: A Comparison of Methods

Hundal¹,

Babu²

2020

TOAIJ

View full text Add to dashboard Cite

Abnormal gait, falls and its associated complications have high morbidity and mortality. Computer vision detects, predicts gait abnormalities, assesses fall risk, and serves as a clinical decision support tool for physicians. This paper performs a systematic review of computer vision, machine learning techniques to analyse abnormal gait. This literature outlines the use of different machine learning and poses estimation algorithms in gait analysis that includes partial affinity fields, pictorial structures model, hierarchical models, sequential-prediction-framework-based approaches, convolutional pose machines, gait energy image, 2-Directional 2-dimensional principles component analysis ((2D) 2PCA) and 2G (2D) 2PCA) Enhanced Gait Energy Image (EGEI), SVM, ANN, K-Star, Random Forest, KNN, to perform the image classification of the features extracted inpatient gait abnormalities.

show abstract

“…In addition, to prevent over-fitting, a three-dimensional morphable software was used to synthesize new images and artificially expand the training data. Iranmanesh et al [21] proposed a coupled deep neural network architecture which utilizes ethnicity, hair, eye, and skin color. They also introduced a joint loss function which is based on an identification-verification model to identify facial attributes and verify a common embedding subspace between sketch and photo.…”

Section: Related Workmentioning

confidence: 99%

SP-Net: A Novel Framework to Identify Composite Sketch

Cheraghi

Lee

2019

IEEE Access

View full text Add to dashboard Cite

Identifying composite sketches with digital face photos is an important and challenging task for law enforcement agencies. It has attracted a wide research interest in the face recognition area. In this paper, we present a novel framework that identifies the photo corresponding to a given composite face sketch. A coupled deep convolutional neural network, named Sketch-Photo Net (SP-Net) is proposed, which is fed with a positive or negative photo-sketch pair. In the proposed SP-Net, the customized VGG-Face network is adopted as base model and is followed by two branches, namely S-Net and P-Net, for sketch and photo, respectively. The S-Net and the P-Net are able to learn discriminative features between the sketches and the photos, regardless of the appearance gap by introducing the concept of elastic learning. In other words, to extract the most important features from the input, the network needs to learn the relevant features along with the irrelevant ones. To do so, higher dimension layers are used after the three 512 layers from VGG-FaceNet. Since the network learns representative features, we decrease the dimension of the layers to produce the most representative features. In addition, contrastive loss is employed to discover the coherent visual structures between sketch and photo. Experimental results on E-PRIP face sketch dataset indicate that the proposed network significantly outperforms the state-of-the-art composite sketch identification methods. INDEX TERMSComposite sketch, hand-drawn sketches, convolutional neural network, contrastive loss.

show abstract

Deep Sketch-Photo Face Recognition Assisted by Facial Attributes

Cited by 18 publications

References 43 publications

Interactive Attendance System for Modern Education Using Computational Intelligence

Interactive Attendance System for Modern Education Using Computational Intelligence

Computer Vision and Abnormal Patient Gait: A Comparison of Methods

SP-Net: A Novel Framework to Identify Composite Sketch

Contact Info

Product

Resources

About