Over the past decade, partially occluded face recognition has been an urgent challenge to computer visionaries due to conditions, which appear unconstrained. The main aim of the facial recognition system is to attain the ability to detect partially occluded regions of an individual’s face and authenticating/verifying that face. There are existing neural networks that are proven to be perfect on analysing the patterns for constrained looks but fail to perform in analysing partially occluded faces that are common in the real world. The paper discusses the trainable Deep Learning Neural Network (DLNN) for partially occluded faces by recognizing all the possible faces in the image, either resting, posing or projecting faces and matching them across the trained datasets of DLNN and encoding the identified faces.

A Survey on Partially Occluded Faces

—The feelings expressed on the face reflect the manner of thinking and provide useful insights of happenings inside the brain. Face Detection enables us to identify a face. Recognizing the facial expressions for different emotions is to familiarize the machine with human like capacity to perceive and identify human feelings, which involves classifying the given input images of the face into one of the seven classes which is achieved by building a multi class classifier. The proposed methodology is based on convolutional neural organizations and works on 48x48 pixel-based grayscale images. The proposed model is tested on various images and gives the best accuracy when compared with existing functionalities. It detects faces in images, recognizes them and identifies emotions and shows improved performance because of data augmentation. The model is experimented with varying depths and pooling layers. The best results are obtained sequential model of six layers of Convolutional Neural Network and softmax activation function applied to last layer. The approach works for real time data taken from videos or photos.

Image Verification and Emotion Detection using Effective Modelling Techniques

The invention discloses a human body three-dimensional reconstruction method and device under the shielding condition and electronic equipment, and the method comprises the steps: obtaining a single-frame RGB-D image of a target human body, and the RGB-D image comprises a color image and a depth image; carrying out instance segmentation on the color image to obtain segmentation pixel masks of thetarget human body part and the occlusion object part, and segmenting the depth image according to the segmentation pixel masks to obtain a target human body depth image and an occlusion object depth image; converting the depth image of the occlusion object into a surface normal image, and estimating the attitude of the occlusion object by using a convolutional neural network; performing three-dimensional reconstruction on the occlusion object based on the attitude estimation of the occlusion object to obtain a three-dimensional model of the occlusion object; and performing three-dimensional human body reconstruction according to the color image, the target human body depth image and the occlusion object three-dimensional model to obtain a three-dimensional human body model. By means of three-dimensional reconstruction of the shielded object, the accuracy and reliability of single-view-angle human body three-dimensional reconstruction under the shielded condition are improved.

Human body three-dimensional reconstruction method and device under shielding condition and electronic equipment

The crime rate has been rising at an unprecedented rate, and security has become a big concern in ATM machines. Face detection is the most common biometric technique due to its non-invasive nature. It's been used in a variety of fields, including camera auto focus, attendance, crowd monitoring, object tracking, security, system, etc. Face detection systems uses image processing techniques that are being learned to operate reliably in a variety of conditions, including changes in posture, lighting, skin color, occlusion, and face spoofing. The face detection system has become increasingly vulnerable to occlusion. Occlusion refers to the deliberate shielding of one's face with a helmet, sunglasses, scarves, or other items in order to avoid being caught. These issues have a significant impact on the development of image processing techniques and system's performance. In this paper the Haar Cascade Classifier (HCC) scheme is projected for face detection where precision as well as minimal processing time are important factors for ATM. The proposed scheme uses deep learning models such as Convolutional Neural Networks to enhance the reliability in feature extraction plus classification of images. Face biometric access control devices are becoming more common in everyday lives, but they remain vulnerable to spoofing attacks. This paper also proposes face spoofing identification using Local Binary Pattern (LBP) that has useful features for face detection. The proposed spoofing attack detection technique has yielded encouraging results. 

Occlusion and spoof attack detection using Haar Cascade classifier and local binary pattern for human face detection for ATM

Face detection is the power to identify a face and recognition is the ability to recognize whose face it is by means of facial characteristics. Face is multivariate and requires a lot of mathematical summation. Almost all imperative applications use a face recognition system. There are many methods that have been already proposed which provides low recognition rate. Hence, the main task of research is to develop a face recognition system with higher recognition capability and better accuracy. This paper proposes Face recognition system by combining two techniques Viola Jones and Principal Component Analysis. An approach of Eigen faces is employed in Principle Component Analysis(PCA). The face recognition system is implemented in MATLAB.

Identification and Recognition of facial images

Face recognition is one of the most important problems of verifying or identifying a face from query image or input image. This system has emerged as an important field in case of surveillance systems. Face detection is a very powerful tool for video surveillance, human computer interface, face recognition, and image database management. Occlusion means extraneous objects that hinder face recognition, e.g., face covered with scarf, wearing glasses, beard, cap etc., is one of the greatest challenges in face recognition systems. Other issues are illumination, pose, expressions etc. An efficient method is used for detection of occlusions, which specifies the missing information in the occluded face. Method used for face detection is Viola-Jones algorithm, for occlusion detection and reconstruction of face fast weighted PCA is used are Neural Network (NN) is used for face recognition. Other appropriate methods are Principal Component Analysis (PCA), Local Binary Pattern (LBP), Eigenfaces. Propose method which is used will detect occluded face and recognize the face with the help of given same faces from the database.

Tanvi B. Patel

Papers

Occlusion detection and recognizing human face using neural network