Fig 1 - uploaded by Jia Uddin
Content may be subject to copyright.
Source publication
Context in source publication
Context 1
... rest of the paper, in section II presents the proposed model, experimental results and analysis are in chapter III and finally conclude the paper is in Section IV. Fig. 1 demonstrates the work flow of our proposed model. It demonstrates how our proposed model is going to work step by step. First, it's going take human picture as input. Then, we are going to identify the face, lips and eyes from given pictures using Haar-Cascade Classifier. Our proposed model used RGB Histogram on those different parts ...
Similar publications
In face recognition, distinguishing identical twins faces is a challenging task because of the high level of correlation in facial appearance.Generally, facial recognition is easy to make mistakes when it comes to twins or similar faces. To deal with the high level of correlation in similar faces, we proposed a deep convolutional neural network (CN...
Citations
... Nafees and Uddin [47] presented a gray-level cooccurrence matrix that measured the texture of images to predict twins. To match the initial stage, the best criteria are identified using the histogram and RGB colors in this framework. ...
Recognizing a face is a remarkable process that humans naturally use. Computer vision has tried to resemble this ability of human vision as a biometric tool to identify humans. Commercial and law enforcement applications are increasingly using face recognition technology to identify people. Currently, it is one of the most sought-after detection methods used in forensics for criminal identification purposes. Owing to similarities in the appearance of certain faces, especially in criminal cases, this problem poses a great challenge in forensic investigation and detection. The novelty of this work lies in the development of a framework for face recognition using 2D facial images gathered from various sources to generate a 3D face mesh using 468 MediaPipe landmarks which detects multiple faces in real-time. This leads to the generation of input feature vectors being formulated utilizing Euclidean/Geodesic distances and their ratios between the landmarks. These feature vectors are then trained into various classifiers that can provide the correct matching decision in an unrestricted environment such as large pose, expression, and occlusion variations. These quantitative similarity measures can then be presented as statistical evidence to identify criminals in forensic investigations. This two-dimensional to three-dimensional annotation provides a higher quality of three-dimensional reconstructed face models without the need for any additional three-dimensional morphable models. The proposed methods were validated and tested to achieve comparable recognition performance using hyperparameter optimization. Regarding accuracy, the statistical results show that Extreme gradient boosting is the best classification model that provides the best accuracy (78%) for predicting facial images compared with Adaptive Boosting (77%), Random Forest (75%), Bernoulli Naive Bayes (68%), Decision Tree (57%), Logistic Regression (71%), Light Gradient Boosting Model (58%), Extra Tree Classifier (57%), Support Vector Machine (58%), and Nearest Centroid (62%) classifiers which can be further increased by considering a greater number of images in the dataset implying at the potential of further research for scale-up implementation.
... Although the similarities in the faces can be due to the use of tools such as makeup, the resemblance of identical twin faces is natural and intrinsic [9]. Identifying similar people by their face image becomes even more important in some sensitive situations such as entry and exit of country, entrance exams for universities, entry and exit of security centers, and the issuance of identity documents like driving certificates and passports, especially when other biometrics may not be available [1,10]. ...
... In these studies, common features, which have been previously validated for identifying ordinary people, were extracted from facial images of identical twins. Furthermore, in some studies, the performance of commercial face recognition algorithms has been tested for identical twins images [1,4,6,10,[16][17][18][19]. The results of these studies show that robust and efficient algorithms for recognizing ordinary faces without similarities, do not necessarily work well for similar faces such as identical twins. ...
... 9. Perform steps 1 through 8 for the second image (Fig. 9b). 10. We now have two binary images at the output where the mismatch points located on the face curve are plotted for each individual. ...
High similarity in facial appearances of twins has complicated the facial feature-based recognition task. This paper introduces a Distinctive Landmark-based Face Recognition (DLFR) system to mitigate the problem. Novel features are proposed based on the number of key points obtained from a modified scale-invariant feature transform algorithm and also the most distinctive landmark region of the face. A slightly altered genetic algorithm is used to optimize weights for the features. The weighted features are classified using a support vector machine classifier. Extensive experiments on 440 face images of identical twins and non-twin individuals show the higher performance of the DLFR system in comparison to a previous work in distinguishing between identical twins and individuals with similar facial images. Because of substantial differences of the DLFR system with most conventional face recognition systems, the work could motivate the research community to push forward the embodied novel idea further.
... Because, there is a significant difference in the faces of ordinary people compared to twins, and it is easier to recognize their faces than twins [32]. The second reason is the necessity of accurately recognizing a pair of identical twins for judicial and security purposes [31]. The third reason is that the birth rate of twins is increasing, which makes the problem of recognizing their identity more important over time [5]. ...
... Nafees and Uddin [31] attempted to predict and compare identical twins by applying RGB histograms on the face, eyes, and lips. They used a Gray-level co-occurrence matrix and Haar-Cascade classifier. ...
Face recognition domain has been well advanced and has achieved high accuracies in identification of individuals in recent years. But in practice, distinguishing similar faces such as an identical twin still is a great challenge for face recognition systems. It happens due to very small differences in the facial features of them. Therefore, extracting common face features is not proper for differentiating identical twins. A solution to this problem is to find the most distinctive regions in the face of identical twins. In this paper, two procedures used to find these specific regions: 1) Machine Processing: A Modified SIFT (M-SIFT) algorithm has been implemented on Identical twins’ face images. Each face image has been segmented into five regions contain eyes, eyebrows, nose, mouth, and face curve. The location and number of mismatched keypoints represented the most distinctive face region in the face of identical twins. 2) Crowdsourcing: We have recognized differences between identical twins faces from human criteria viewpoint by enlisting crowd intelligence. Several questionnaires were designed and completed by 120 participants. The dataset of this study collected by ourselves and include 650 images for 115 pairs of identical twins and 120 non-twin individuals. The results of Machine Processing and Crowdsourcing methods showed that the face curve is the most discriminant region among every five regions in most of identical twins. Several features proposed and extracted based on the keypoints of the M-SIFT algorithm and face landmarks. The experimental results demonstrated the lowest equal error rate of identical twins recognition as 7.8, 8.1 and 10.1% for using the whole images, only frontal images and only images with PAN motions, respectively.
Face recognition system contains lots of challenges due to various environmental factors, background variations, poor quality of camera, different illumination and others. Since twins are involved with criminal activities, twin identification becomes an essential task. The proposed system is focused on identifying the identical twins for the still images. The fusion based approach has been implemented in the proposed system. It combines the features extracted by using Principal Component Analysis (PCA), Histogram Oriented of Gradients (HOG), Local Binary Pattern (LBP), Gabor and distance between the facial components. Three types of fusion such as Decision Level Fusion, Feature Level Fusion and Score Level Fusion are used in the proposed approach. Based on these fusion generated scores, the twin has been identified. In the proposed system, Particle Swarm Optimization is used for the best feature selection and SVM classifier is used for training and testing the image. The proposed system provides better results when compared with the other twin detection techniques.
Biometrics is one of the major techniques which is used to identify a person’s exclusive physical characteristics. Studying the biological traits of a human physique by extracting a feature set from the obtained data, and matching the sets with the database is known as Biometrics. Consistent and accurate verification and identification of a person are extremely significant in various business transactions, Law Enforcement, Surveillance and access to privileged information. Though there is a high progression in the Biometric Modality, identifying Monozygotic Twins seems to be a very challenging task as identical twins are highly analogous to each other and differentiating them is practically impossible. As Monozygotic Twins are composed of a single embryo they cannot be distinguished by considering their DNA results. Hence, the lack of appropriate identification system may lead to many critical scenarios. The increase in twin births has led to an up gradation of the present biometric system that may accurately regulate the uniqueness of a person by comparing their corporal fields. The current biometric method which is used for verification is sufficient to differentiate one person from another. In this paper, we study about distinguishing identical twins or monozygotic twins by different multimodal biometric technologies such as facial marks, facial features, hair-whorls by means of PCA Algorithm.
