Binarized Statistical Image Features Research Articles

Gender Classification through Fusion of Holistic and Region-based Facial Patterns

In this study, a robust gender prediction system is proposed to fuse global and regional facial representations through score and feature level fusion. In order to extract facial features for gender classification, Binarized Statistical Image Features (BSIF) approach is applied on holistic and regional features of face images. The extracted features are then concatenated to combine the region-based information at feature level fusion. Then the optimized sub-set of features is selected using Particle Swarm Optimization (PSO) method. Finally, the holistic and regional features are combined at score level fusion to produce the final set of scores for gender classification. This study applies Weighted Sum (WS) rule strategy for score level fusion. The experimental results are performed on Multiple Biometric Grand Challenge (MBGC) and CASIA-Iris-Distance databases with consideration of subject-disjoint training and testing evaluation to testify the validity of the proposed gender classification system. The experimental results of the study demonstrate the success of the proposed scheme for gender prediction.

Application of novel DIRF feature selection algorithm for automated brain disease detection

The brain is a complex organ and Magnetic Resonance Imaging (MRI) is the most widely used imaging modality for diagnosing brain diseases due to its superior soft tissue contrast. In clinical practice, interpreting MRI scans is laborious, time-consuming, and error-prone. While most studies focus on detecting brain tumors and multiple sclerosis, there are limited studies on atrophy, ischemia, and white matter intensity (WMI) diseases. Moreover, most studies are complex, time-consuming, computationally intensive, and specific to the detection of a particular brain disease. Our study presents a new deep learning-based ensemble model and also introduces the novel double iterative ReliefF (DIRF) feature selection algorithm to enhance the performance of automatic detection of atrophy, ischemia, and WMI using MRI images. Two pre-trained deep models, namely AlexNet and GoogleNet, and three well-known local texture descriptors, namely pyramid histogram of oriented gradients (PHOG), binary Gabor pattern (BGP), and binarized statistical image features (BSIF), were employed as feature extractors, and the extracted features were merged. The merged features were fed into the proposed double iterative ReliefF (DIRF) feature selection algorithm, and the most important 688 features were selected. Finally, the selected features were classified by support vector machine (SVM). Our proposed DIRF-based ensemble model achieved 98.87 % accuracy using a 10-fold cross-validation strategy. Our proposed model developed using a public brain diseases MRI dataset achieved an accuracy of 95.96 %. This study demonstrates that our proposed model, with DIRF feature selection algorithm can significantly improve the diagnosis of various brain diseases, enhancing the patient care and outcomes.

Ensemble of Local Texture Descriptor for Accurate Breast Cancer Detection from Histopathologic Images

Histopathological analysis is important for detection of the breast cancer (BC). Computer-aided diagnosis and detection systems are developed to assist the radiologist in the diagnosis process and to relieve the patient from unnecessary pain. In this study, a computer-aided diagnosis system for the early detection of benign and malignant breast cancer is proposed. The proposed system consists of feature extraction, feature ensemble, and classification stages. Various preprocessing steps such as grayscale conversion, noise filtering, and image resizing are employed on the input histopathological images. The local texture descriptors namely Local Binary Pattern (LBP), Frequency Decoded LBP (FDLBP), Binary Gabor Pattern (BGP), Local Phase Quantization (LPQ), Binarized Statistical Image Features (BSIF), CENsus TRansform hISTogram (CENTRIST), and Pyramid Histogram of Oriented Gradients (PHOG) are employed for feature extraction from the histopathologic images. The obtained features are then concatenated for the construction of the ensemble of the features. Three classifiers namely Support Vector Machines (SVM), K-nearest neighbor (KNN), and Neural Networks (NN) are used in the detection of the BC and the classification accuracy score is used for performance evaluation. A dataset called BreaKHis is used in the studies. There are 9109 microscopic pictures in BreaKHis, with 2480 benign samples and 5429 malignant samples. During the collection of the data, 82 patients' breast tumor tissues were envisioned using various magnification factors such as 40X, 100X, 200X, and 400X. The accuracy score is used to assess the acquired findings. The results show that the proposed method has the potential to use accurate BC detection.

Contactless Palmprint Recognition Using Binarized Statistical Image Features-Based Multiresolution Analysis.

In recent years, palmprint recognition has gained increased interest and has been a focus of significant research as a trustworthy personal identification method. The performance of any palmprint recognition system mainly depends on the effectiveness of the utilized feature extraction approach. In this paper, we propose a three-step approach to address the challenging problem of contactless palmprint recognition: (1) a pre-processing, based on median filtering and contrast limited adaptive histogram equalization (CLAHE), is used to remove potential noise and equalize the images' lighting; (2) a multiresolution analysis is applied to extract binarized statistical image features (BSIF) at several discrete wavelet transform (DWT) resolutions; (3) a classification stage is performed to categorize the extracted features into the corresponding class using a K-nearest neighbors (K-NN)-based classifier. The feature extraction strategy is the main contribution of this work; we used the multiresolution analysis to extract the pertinent information from several image resolutions as an alternative to the classical method based on multi-patch decomposition. The proposed approach was thoroughly assessed using two contactless palmprint databases: the Indian Institute of Technology-Delhi (IITD) and the Chinese Academy of Sciences Institute of Automatisation (CASIA). The results are impressive compared to the current state-of-the-art methods: the Rank-1 recognition rates are 98.77% and 98.10% for the IITD and CASIA databases, respectively.

Age Estimation on Human Face Image Using Support Vector Regression and Texture-Based Features

This paper proposed a framework for estimating human age using facial features. These features exploit facial region information, such as wrinkles on the eye and cheek, which are then represented as a texture-based feature. Our proposed framework has several steps: preprocessing, feature extraction, and age estimation. In this research, three feature extraction methods and their combination are performed, such as Local Binary Pattern (LBP), Local Phrase Quantization (LPQ), and Binarized Statistical Image Feature (BSIF). After extracting the feature, Principle Component Analysis (PCA) was performed to reduce the feature size. Finally, the Support Vector Regression (SVR) method was used to predict age. In evaluation, the estimation error will be based on mean average error (MAE). In the experiment, we utilized the well-known public dataset, face-age.zip, and UTK Face datasets, containing 15,202 facial image data. The data were divided into the training of 12,162 images and the testing of 3,040 images. Our experiments found that combining BSIF and LPQ with PCA achieved the lowest MAE of 9.766 and 9.754. The results show that the texture-based feature could be utilized for estimating the age on facial image.

A comparative study of shallow learning and deep transfer learning techniques for accurate fingerprints vitality detection

• Deep Transfer Learning architectures are compared against shallow learning image descriptors under the same conditions. • Deep transfer learning for fingerprint liveness detection is a viable way. • XAI shows that deep transfer learning extracts complex nonlinear patterns able to discern minutiae for liveness detection. This work inspects deep learning architectures and shallow learning techniques to determine whether the image of a fingerprint is real (Live) or not (Fake). It is known that Deep Learning techniques deliver, in general, good accuracies being able to automatically extract relevant patterns, at the same time, it is also known that these algorithms require large amounts of data. For this reason, transfer learning aims to transfer the knowledge learnt over a huge dataset to a new, smaller dataset. In this work, because of the limited size of the LivDet2019 dataset, three well known deep learning architectures such as Inception V3, ResNet50 and NASNet Large have been modified to perform transfer learning from the huge imagenet dataset to the smaller LivDet2019. The hypothesis at the very basis of this work is that the deep learning architectures trained on the huge imagenet dataset would learn to extract relevant patterns like lines, shapes, curves, jump between curves, etc… Later, the extracted knowledge, is fine-tuned on the LivDet2019 dataset to recognize fingerprint minuities as a non-linear combination of the previously learned patterns. For sake of completeness, state of art shallow learning image descriptors, finetuned for fingerprint recognition, such as Binarized Statistical Image Features (BSIF), Local Phase Quantization (LPQ) and Weber Local Descriptor (WLD) are used for extracting features from the LivDet2019 dataset. The classification on each of these extracted features is performed both with a linear and non-linear (gaussian) support vector machine. Accuracies suggest that both shallow learning and deep learning techniques are on par with the accuracies of reviewed works and thus transfer learning in fingerprint liveness detection is a feasible strategy that deserve attention and future research with the aim of increasing fingerprint detection accuracies.

A Novel Multi-Level Pyramid Co-Variance Operators for Estimation of Personality Traits and Job Screening Scores

Recently, automatic personality analysis is becoming an interesting topic for computer vision. Many attempts have been proposed to solve this problem using time-based sequence information. In this paper, we present a new framework for estimating the Big-Five personality traits and job candidate screening variable from video sequences. The framework consists of two parts: (1) the use of Pyramid Multi-level (PML) to extract raw facial textures at different scales and levels; (2) the extension of the Covariance Descriptor (COV) to fuse different local texture features of the face image such as Local Binary Patterns (LBP), Local Directional Pattern (LDP), Binarized Statistical Image Features (BSIF), and Local Phase Quantization (LPQ). Therefore, the COV descriptor uses the textures of PML face parts to generate rich low-level face features that are encoded using concatenation of all PML blocks in a feature vector. Finally, the entire video sequence is represented by aggregating these frame vectors and extracting the most relevant features. The exploratory results on the ChaLearn LAP APA2016 dataset compare well with state-of-the-art methods including deep learning-based methods.

Using residual images with BSIF for iris liveness detection

Deploying iris recognition systems in several security areas emphasized the importance of developing iris liveness methods. These methods verify if the iris sample acquired for authentication is fake or real. Recently, Binarized Statistical Image Features (BSIF) descriptor was successfully applied for that purpose. As BSIF is a powerful descriptor based on Local Binary Pattern (LBP) descriptor, we have supposed that enhancements that have worked before with LBP could work with BSIF as well. Widening a previous work, four public datasets representing printed, plastic, synthetic, and contact lens attacks were evaluated using 8-bit BSIF in both modes segmented and unsegmented eye images. Contact lens attack was the most challenging attack, especially in the unsegmented scenario. In this paper, a new method is proposed using residual images with BSIF to enhance the results of contact lens databases. Three high pass filters were applied separately before the feature extraction phase to improve the discrimination ability of BSIF. Clarkson contact lens database was used for evaluation in both modes segmented and unsegmented eye images. The results were promising in the unsegmented scenario and the three filters enhanced in the results with 8.6667%, 10%, and 18.3333%. The application of these filters with BSIF could be useful for other computer vision tasks like face liveness detection.

Artificial Neural Networks Framework for Detection of Defects in 3D-Printed Fiber Reinforcement Composites

One of the major challenges in applying tomography methods for detecting defects in composite materials is the large image datasets generated during imaging, which require significant effort for the detection of damage. Machine-learning (ML) methods require a large training dataset and can be efficient in processing tomography datasets for defect detection. Methods need to be developed for processing images to train the ML algorithms, which is the focus of the present work. An additive manufactured fiber reinforced composite material is imaged using a micro-CT scan to generate an image set for defect detection. The microstructures are processed using the binarized statistical image features (BSIF) method for compression without compromising the desired information about defects. The result shows that the convolutional neural network model has a mean square error of 0.001 in fiber orientation prediction, and a scheme has been developed for defect detection based on the predictions obtained from the ML models.

Contactless Multi-biometric System Using Fingerprint and Palmprint Selfies

Due to the COVID-19 pandemic, automated contactless person identification based on the human hand has become very vital and an appealing biometric trait. Since, people are expected to cover their faces with masks, and advised avoiding touching surfaces. It is well-known that usually contact-based hand biometrics suffer from issues like deformation due to uneven distribution of pressure or improper placement on sensor, and hygienic concerns. Whereas, to mitigate such problems, contactless imaging is expected to collect the hand biometrics information without any deformation and leading to higher person recognition accuracy; besides maintaining hygienic and pandemic concerns. Towards this aim, in this paper, an effective multi-biometric scheme for person authentication based on contactless fingerprint and palmprint selfies has been proposed. In this study, for simplicity and efficiency, three local descriptors, i.e., local phase quantization (LPQ), local Ternary patterns (LTP), and binarized statistical image features (BSIF), have been employed to extract salient features from contactless fingerprint and palmprint selfies. The score level fusion based multi-biometric system developed in this work combines the matching scores using two different fusion techniques, i.e., transformation based-rules like triangular norms and classifier based-rules like SVM. Experimental results on two publicly available databases (i.e., PolyU contactless to contact-based fingerprint database and IIT-Delhi touchless palmprint dataset) show that the proposed contactless multi-biometric selfie system can easily outperform uni-biometrics.

A comparative study of handcrafted local texture descriptors for fingerprint liveness detection under real world scenarios

Authentication using fingerprints is widely deployed in various applications to ensure a secure and efficient method for access control. However, fingerprint recognition systems can be deceived by spoofing attacks. Therefore, it is necessary to ensure the security of fingerprint-based recognition system using liveness detection. The work presented in this paper evaluates the potential of various handcrafted texture features under cross-dataset, cross-sensor, cross-material, unknown-material, and combined datasets experimental scenarios. We have considered Binarized Statistical Image Features (BSIF), Local Phase Quantization (LPQ), Weber Local Descriptor (WLD), Local Contrast Phase Descriptor (LCPD), and Rotation Invariant Co-occurrence among adjacent Local Binary Pattern (RicLBP) for liveness detection of fingerprint images. The performance of these descriptors against novel spoof materials, different sensors, and different acquisition environments reflect their robustness under real world attack scenarios. The experimental evaluations are performed on LivDet 2011, 2013, and 2015 databases using Support Vector Machine (SVM) classifier. The experimental evaluation shows that LCPD and WLD are the most effective descriptors for liveness detection under diverse testing conditions. The comparative performance evaluation of these handcrafted texture features with learning based features also indicate their effectiveness in real world attack scenarios. Experimental evaluation using the combination of best performing LCPD and WLD features further improve the performance of fingerprint liveness detection. The experimental outcome of the current research clearly indicates the superiority of handcrafted local texture descriptor in the real world presentation attack scenarios. Also, it is advantageous to use local texture descriptor as they provide a simple and faster approach for fingerprint liveness detection in real world applications of fingerprint recognition systems.

Feature-level fusion of major and minor dorsal finger knuckle patterns for person authentication

The identification of individuals by their finger dorsal patterns has become a very active area of research in recent years. In this paper, we present a multimodal biometric personal identification system that combines the information extracted from the finger dorsal surface image with the major and minor knuckle pattern regions. In particular, first the features are extracted from each single region by BSIF (binarized statistical image features) technique. Then, extracted information is fused at feature level. Fusion is followed by dimensionality reduction step using PCA (principal component analysis) + LDA (linear discriminant analysis) scheme in order to improve its discriminatory power. Finally, in the matching stage, the cosine Mahalanobis distance has been employed. Experiments were conducted on publicly available database for minor and major finger knuckle images, which was collected from 503 different subjects. Reported experimental results show that feature-level fusion leads to improved performance over single modality approaches, as well as over previously proposed methods in the literature.

Steel Strip Surface Defect Identification using Multiresolution Binarized Image Features

The shaped steel strip, in the hot rolling process, may exhibit some surface flaws. Their origin could be the internal discontinuities in the input product or the thermomechanical transformation of the material, during the shaping process. Such defects are of a random occurrence and may lead to costly rework operations or to a downgrading of the final product. So, they should be detected and identified as soon as possible, to allow a timely decision-making. For such a quality monitoring, the used vision systems are mainly based on an image description and a reliable classification. In this paper, we explore pre-defined image filters and work on a procedure to extract a discriminant image feature, while realizing the best trade-off between the improved recognition rate of the surface defects and the computing time. The proposed method is a multiresolution approach, based on the Binarized Statistical Image Features method, employed to date in biometrics. The filters, pre-learnt from natural images, are applied to steel defect images as a new surface structure indicator. They provide a quite discriminating image description. A relevant data reduction is used together with a classifier to allow an efficient recognition rate of the defective hot rolled products.

Palm vein recognition through fusion of texture-based and CNN-based methods

In this paper, we propose a palm vein recognition system that combines two approaches using a decision-level fusion strategy. The first approach employs Binarized Statistical Image Features (BSIF) descriptor method on five overlapping sub-regions of palm vein images and the second approach uses a convolutional neural networks (CNN) model on each palm vein image. In the first approach, texture-based features of five overlapping sub-regions on the palm vein image are extracted using the powerful BSIF method and the scores obtained by the matching step of the system are fused with score-level fusion strategy. In the second approach, a CNN model is used to train the system using the whole image. Afterwards, the decisions of two approaches are gathered separately and a final decision is obtained by fusing the two decisions. Experimental results on CASIA, FYO, PUT, VERA and Tongji Contactless Palm Vein databases showed that the proposed method compared favorably against other similar systems.

Iris Liveness Detection Using Fusion of Domain-Specific Multiple BSIF and DenseNet Features.

In the past few years, some fusion-based approaches have been proposed to constitute discriminatory features for iris liveness detection. However, several methods exist in the literature for iris feature extraction and, thus, identifying an optimal composite of such features is still a vital challenge. This article also proposes a score-level fusion of two distinct domain-specific features, i.e., multiple binarized statistical image feature (BSIF) and DenseNet-based features. However, instead of randomly scrutinizing such features, statistical tests are executed on six predominant iris features to identify the optimal feature set to combine. Particularly, this work emphasizes textured-lens-based presentation attacks and aims to identify the type of contact lenses within the iris samples. The experimental analysis depicts that the domain-specific features substantially outperform the generic features while discriminating live iris from the artifacts. Furthermore, the proposed fusion-based approach is assessed on three iris datasets and the outcomes are compared with various state of the arts using three validation protocols in terms of equal error rate (EER). The comparative analysis perceived that the proposed method obtains a significant performance gain over the existing approaches and offers an improved benchmark for both, iris liveness detection and contact lens identification.

Identification of various image retargeting techniques using hybrid features

Image retargeting refers to manipulating an input image to adapt its display on diverse screens with distinct spatial resolutions and aspect ratios. However, it might also be used for malicious image forgeries such as object removal. There exist several types of image retargeting techniques, yet most existing image retargeting detection approaches expose only single type of image retargeting. This paper proposes a blind forensics approach to identify three image retargeting techniques including seam carving, scaling and scale-and-stretch. Since image retargeting usually leads to local texture distortion and global structure deformation, a 512-dimensional feature set, which is made up of LBPCO (co-occurrence of local binary pattern) and BSIF (binarized statistical image features), is designed to expose image retargeting artifacts. Support vector machine (SVM) is exploited as pattern classifier to identify three image retargeting techniques. Compared with existing works, the proposed approach not only detects image retargeting forgery, but also identifies specific image retargeting technique.

FYO: A Novel Multimodal Vein Database With Palmar, Dorsal and Wrist Biometrics

Multimodal biometric systems are preferred as a defense compared to unimodal systems. This study introduces an open access multimodal vein database named FYO with each letter dedicated to each author's name. The database involves three biometric traits; palm vein, dorsal vein and wrist vein of the same individuals, to explore and enhance research in the area of using these traits to create a spoof-proof multimodal authentication system. The vein images of FYO are acquired using medical vein finder in a controlled environment. Comparisons are performed to show the differences with the existing well known databases and the state-of-the-art recognition algorithms. Hand-crafted feature extractors such as Binarized Statistical Image Features (BSIF), Gabor filter and Histogram of Oriented Gradients (HOG) are applied to show the viability of the vein datasets. Additionally, a deep learning based Convolutional Neural Networks (CNN) architecture is proposed with two models using decision-level fusion of palmar, dorsal and wrist biometric traits on vein images. Unimodal systems, multimodal systems and the proposed architecture are tested on several vein datasets including palmar, dorsal and wrist vein images. Experimental results based on accuracy and computation time on our FYO datasets showed competitive output with that of other databases such as Tongji Contactless Palm Vein database, VERA, PUT, Badawi and Bosphorus hand vein databases. Moreover, the proposed CNN architecture on three vein biometric traits show superior performance compared to hand-crafted methods.

Image quality assessment using BSIF, CLBP, LCP, and LPQ operators

The pervasiveness of digital devices like mobile phones, tablets, and personal computers established the presence of image contents as an essential media in several communication applications. In this scenario, the quality of the displayed images is directly correlated with the sense of communication excellence experienced by the users of these applications. Therefore, the development of techniques for assessing the quality of images, as perceived by human observers, is crucial for current multimedia applications. These techniques can either utilize the full prior information from a reference image (full-reference metrics), partial features of the reference (reduced-reference metrics) or exclusively the test image (no-reference metrics). In this paper, an effective no-reference image quality assessment approach is proposed based on the binarized statistical image features (BSIF), the completed local binary patterns (CLBP), the local configuration patterns (LCP), and the local phase quantization (LPQ) descriptors. The statistics of these descriptors is thoroughly evaluated using three popular databases: LIVE, TID2013, and CSIQ. Experimental results evince the correlation of quality scores provided by the observer with the proposed metrics, that indicate a fine performance when compared with several state-of-the-art image quality assessment methods.

Palmprint identification performance improvement via patch-based binarized statistical image features (Erratum)

Palmprint identification performance improvement via patch-based binarized statistical image features (Erratum)

Palmprint identification performance improvement via patch-based binarized statistical image features

In the last few years, most works on palmprint recognition systems have been focused on developing a practical system that should have high performance in term of recognition accuracy, matching speed, and storage requirement. However, they have certain shortcomings, such as long computational time and sensitiveness to translation, illumination, and rotation. To handle these limitations, we present a simple and effective scheme to produce a meaningful local palmprint representation called patch binarized statistical image features descriptor (PBSIFD) for palmprint identification. The PBSIFD representation significantly exploits the power of the BSIF texture descriptor. In addition, the reduced version of PBSIFD called RPBSIFD is also obtained using whitened linear discriminant analysis. The proposed schemes are successfully applied to four widely used palmprint databases, including PolyU2D, PolyU2D/3D, IITD, and CASIA, and they are compared with recent approaches. It is shown that they outperform the existing methods.