CASIA V1 Research Articles

ET: Edge-Enhanced Transformer for Image Splicing Detection

A key challenge of image splicing detection is how to localize integral tampered regions without false alarm. Although current forgery detection approaches have achieved promising performance, the integrality and false alarm are overlooked. In this paper, we argue that the insufficient use of splicing boundary is a main reason for poor accuracy. To tackle this problem, we propose an Edge-enhanced Transformer (ET) for tampered region localization. Specifically, to capture rich tampering traces, a two-branch edge-aware transformer is built to integrate the splicing edge clues into the forgery localization network, generating forgery features and edge features. Furthermore, we design a feature enhancement module to highlight the artifacts of the edge area in forgery features and assign weight values to the resulting tensor in spatial domain for vital signal strengthening and noise suppression. Extensive experimental results on CASIA v1.0, CASIA v2.0 and NC2016 demonstrate that the proposed method can accurately localize tampered regions in both pixel and edge levels and outperforms state-of-the-art methods.

A novel pixel’s fractional mean-based image enhancement algorithm for better image splicing detection

Image manipulation has become widely accessible to the masses over the past years due to the sophisticated image editing tools which are readily-available and easy to use. As a result, image forgery has increased such that it has become infeasible to discriminate authentic from tampered images with the naked eye. Image forgery plays a prominent role in the spread of misinformation, which might be criminalized under certain jurisdictions. Image splicing is a common type of image manipulation and constitutes one of the most widespread image tampering methods on the internet. Efforts have been made to tackle the implications of image forgery by developing computer algorithms that can discriminate tampered images, however, more research is needed to keep up with the advancements of image editing tools. Previously, we have explored fractional calculus in other image processing applications. In this study, we propose a novel pixel’s fractional mean (PFM) algorithm to enhance images prior to classification for better detection of image splicing forgery based on texture features. The proposed PFM enhances each pixel separately depending on the occurrence number of the pixel’s intensity. Two sets of texture algorithms are used to extract essential features from suspected spliced images. These features are then used with the “support vector machine” (SVM) classifier to classify authentic and spliced images. The proposed model demonstrated an accuracy rate of 97% when evaluated with the publicly-available image splicing dataset “CASIA v2.0”. With a relatively low dimension feature vector, the proposed model demonstrates high accuracy and efficiency, which corroborate the benefit of using fractional calculus in image processing algorithms.

Deteksi Serangan Spoofing Wajah Menggunakan Convolutional Neural Network

Facial recognition-based biometric authentication is increasingly frequently employed. However, a facial recognition system should not only recognize an individual's face, but it should also be capable of detecting spoofing attempts using printed faces or digital photographs. There are now various methods for detecting spoofing, including blinking, lip movement, and head tilt detection. However, this approach has limitations when dealing with dynamic video spoofing assaults. On the other hand, these types of motion detection systems can diminish user comfort. As a result, this article presents a method for identifying facial spoofing attacks through Convolutional Neural Networks. The anti-spoofing technique is intended to be used in conjunction with deep learning models without using extra tools or equipment. Our CNN classification dataset can be derived from the NUAA photo imposter and CASIA v2. The collection contains numerous examples of facial spoofing, including those created with posters, masks, and smartphones. In the pre-processing stage, image augmentation is carried out with brightness adjustments and other filters so that the model to adapt to various environmental conditions. We evaluate the number of epochs, optimizer types, and the learning rate during the testing process. The test results show that the proposed model achieves an accuracy value of 91.23% and an F1 score of 92.01%.

Frequency based edge-texture feature using Otsu’s based enhanced local ternary pattern technique for digital image splicing detection

Sharing information through images is a trend nowadays. Advancements in the technology and user-friendly image editing tool make easy to edit the image and spread fake news through different social networking platforms. Forged image has been generated through an advanced image editing tool, so it is very challenging for image forensics to detect the micro discrepancy which distorted the micro pattern. This paper proposes an image forensic detection technique, which implies multi-level discrete wavelet transform to implement digital image filtering. Canny edge detection technique is implemented to detect the edge of the image to implement Otsu’s based enhanced local ternary pattern (OELTP), which can detect forgery-related artifact. DWT is implemented over Cb and Cr components of the image and using edge texture to improve the Otsu global threshold, which is used to extract features using ELTP technique. Support vector machine (SVM) is used for classification to find the image is forged or not. The performance of the work evaluated on three different open available data sets CASIA v1, CASIA v2, and Columbia. Our proposed work gives better results with some of the previous states of the work in terms of detection accuracy.

Hybrid Algorithm for the detection of Pixel-based digital image forgery using Markov and SIFT descriptors

Today, image forgery is common due to the massification of low-cost/high-resolution digital cameras, along with the accessibility of computer programs for image processing. All media is affected by this issue, which makes the public doubt the news. Though image modification is a typical process in entertainment, when images are taken as evidence in a legal process, modification cannot be considered trivial. Digital forensics has the challenge of ensuring the accuracy and integrity of digital images to overcome this issue. This investigation introduces an algorithm to detect the main types of pixel-based alterations such as copy-move forgery, resampling, and splicing in digital images. For the evaluation of the algorithm, CVLAB, CASIA V1, Columbia, and Columbia Uncompressed datasets were used. Of 7100 images evaluated, 3666 were unaltered, 791 had resampling, 2213 had splicing, and 430 had copy-move forgeries. The algorithm detected all proposed forgery pixel methods with an accuracy of 91%. The main novelties of the proposal are the reduced number of features needed for identification and its robustness for the file format and image size.

Multiple Image Splicing Dataset (MISD): A Dataset for Multiple Splicing

Image forgery has grown in popularity due to easy access to abundant image editing software. These forged images are so devious that it is impossible to predict with the naked eye. Such images are used to spread misleading information in society with the help of various social media platforms such as Facebook, Twitter, etc. Hence, there is an urgent need for effective forgery detection techniques. In order to validate the credibility of these techniques, publically available and more credible standard datasets are required. A few datasets are available for image splicing, such as Columbia, Carvalho, and CASIA V1.0. However, these datasets are employed for the detection of image splicing. There are also a few custom datasets available such as Modified CASIA, AbhAS, which are also employed for the detection of image splicing forgeries. A study of existing datasets used for the detection of image splicing reveals that they are limited to only image splicing and do not contain multiple spliced images. This research work presents a Multiple Image Splicing Dataset, which consists of a total of 300 multiple spliced images. We are the pioneer in developing the first publicly available Multiple Image Splicing Dataset containing high-quality, annotated, realistic multiple spliced images. In addition, we are providing a ground truth mask for these images. This dataset will open up opportunities for researchers working in this significant area.

A fuzzy vault development based on iris images

Biometric systems gather information from the person's biometric attributes, used extensively to authorize the individuals. Due to the obvious convenience of using specific individual traits such as face, fingerprints, palm veins, and irises, biometric authentication is becoming more common. In particular, Iris systems are in high demand for high-assurance applications, because they contain a broad feature set and remain stable. Authentication methods based on iris biometrics are now commonly used in a variety of fields. This is due to the fact that iris biometric authentication is both safer and more comfortable than conventional passwords. Template Security is a major concern in biometric systems. The template security mechanism ensures reusable, permanent, and un-linkable models. The Fuzzy Vault strategy is one of the most popular security schemes for Template protection.
 Fuzzy vault has demonstrated to be an effective protection method but lacks revocability and security attacks. This article introduced an improved fuzzy vault system. The improved fuzzy vault system was introduced, which uses more than one key to protect biometric data. Different keys make the search space more detailed. The additional key was used to encrypt vault data, which stopped the intruder from accessing the information on the person's biometry. The system was tested using CASIA.v1 and IITD.v1 datasets, and findings showed that the system ensures the protection and authentication of the iris templates without compromising performance. The proposed modification gave a 0.0 % False Accepted Rate (FAR) for both the dataset and False Rejected Rate (FRR), 0.14 % for CASIA v1 and 0.12 % for ITTD v1 False Rejected rate

Iris Identification Based on the Fusion of Multiple Methods

Iris recognition occupies an important rank among the biometric types of approaches as a result of its accuracy and efficiency. The aim of this paper is to suggest a developed system for iris identification based on the fusion of scale invariant feature transforms (SIFT) along with local binary patterns of features extraction. Several steps have been applied. Firstly, any image type was converted to grayscale. Secondly, localization of the iris was achieved using circular Hough transform. Thirdly, the normalization to convert the polar value to Cartesian using Daugman’s rubber sheet models, followed by histogram equalization to enhance the iris region. Finally, the features were extracted by utilizing the scale invariant feature transformation and local binary pattern. Some sigma and threshold values were used for feature extraction, which achieved the highest rate of recognition. The programming was implemented by using MATLAB 2013. The matching was performed by applying the city block distance. The iris recognition system was built with the use of iris images for 30 individuals in the CASIA v4. 0 database. Every individual has 20 captures for left and right, with a total of 600 pictures. The main findings showed that the values of recognition rates in the proposed system are 98.67% for left eyes and 96.66% for right eyes, among thirty subjects.

An efficient CNN based encrypted Iris recognition approach in cognitive-IoT system

Recently, biometric-based security plays a vital role in the success of the Cognitive Internet of Things (C-IoT) based security framework. The iris trait solves a lot of security issues, especially in smart IoT-based applications. It increases the resistance of these systems against severe authentication attacks. In this paper, an efficient iris recognition model based on chaotic encryption and deep Convolutional Neural Networks (CNNs) is proposed for C-IoT applications. CNN is used to extract the deep iris features from the left and right eyes, which will be used as input features to a fully connected neural network with a Softmax classifier. CASIA V4 Interval dataset and Phoenix dataset are used to train the CNN model; to get the best tuning of network parameters. In this paper, the effect of adding different kinds of noise to iris images, due to noise interference related to sensing IoT devices, bad acquisition of iris images by system users, or other system assaults, is discussed. This strategy of noisy encrypted iris images is evaluated over the internet environment. Chaotic encryption is utilized to secure the transmission of iris templates in the proposed model. The results showed that the proposed approach attains supreme accuracy compared to the existing approaches, it is obtained up to 99.24% and 100% with CASIA V4 and Phoenix datasets, respectively. The proposed model achieves satisfied and competitive results regard accuracy, and robustness among existing methods. Regards to recognition accuracy rate, this methodology shows low degradation of recognition accuracy rates in the case of using noised iris images. Likewise, the proposed method has a relatively low training time, which is a useful parameter in critical IoT based uses such as Tele-Medicine application.

Comparative analysis of feature extraction and fusion for blind authentication of digital images using chroma channels

Blind authentication is one of the challenging techniques which has attracted considerable attention with the increasing security hacks on digital images. This paper evaluates different models based on feature extraction to detect digitally-altered images. Various feature-extraction methods have been investigated and compared including LBP, MSLBP, CSLBP, SLBP, WLD, LPQ, MSLPQ and DCT. Moreover, we propose a number of ways to combine a variety of features utilizing single and multi-scale representations of images. For classification, SVM is employed with different kernels to identify forged and authentic images. To evaluate the effectiveness of the investigated models, several experiments have been conducted using k-fold cross-validation and computed performance measures for two benchmark image tampering datasets (CASIA v1.0 and CASIA v2.0). Additionally, we have conducted statistical analysis for the top-ten models and the results confirmed that the best models for CASIA v1.0 and CASIA v2.0 are MSLBP-DCT and MSLPQ, respectively. Further improvements have been achieved by integrating features from the three color channels (Y, Cb and Cr) with and without feature reduction using PCA and LLP. In this case, the results show that MSLPQ-DCT achieved a better accuracy of 98.56% on CASIA v1.0 with 1020 features and MSLPQ achieved a slightly better accuracy of 97.4% on CASIA v2.0 with 1536 features.

Digital Image Tampering Detection Using Multilevel Local Binary Pattern Texture Descriptor

Digital images can be manipulated using the latest tools and techniques without leaving any visible traces. Image tampering detection is required to authenticate image validation. It is concluded from previous research that image tampering modifies the texture micropattern in a digital image. Therefore, texture descriptors can be applied to highlight these changes. A texture descriptor–based technique is proposed for detecting both copy-move and splicing forgery. In the proposed method, an RGB image is converted into a YCbCr image and Cb and Cr image components are extracted, as these components are more sensitive to tampering artifacts. Further, a standard deviation (STD) filter and higher-order texture descriptors are applied on Cb and Cr components. The STD filter is used to highlight important details of objects in the image. A support vector machine classifier is used to classify forged and tampered images. Support vector machine (SVM) classifier gives good results on both large- and small-image data sets. The performance is appraised in three online-available, widely used data sets: CASIA v1.0, CASIA v2.0, and Columbia. The proposed method outperforms most of the state-of-the-art methods.

Automated image splicing detection using deep CNN-learned features and ANN-based classifier

With the present-day rapid evolution of digital technology, images have become one of the most important means of communication and information carrier in our society. Since the last decade, with the emergence of social networking sites like Facebook, Instagram, Twitter, etc., there has been a huge increase in the amount of information exchanged in the form of digital images, on a regular basis. While traditionally we might have had faith in the credibility of these images, today’s digital technology has begun to erode that faith. Before sharing an image over social networks, editing it with relevant software application has become one of the simplest things to do today. While not many people do this with any sinister intent behind, there has been a significant increase in cybercrimes related to malicious image manipulation and sharing. To this end, image splicing has emerged as one of the major forms of image manipulation attacks, among others today. This demands investigation of intrinsic differences between authentic and forged images and hence development of automated splicing detection tools. Here, we propose a blind image splicing detection technique that employs a deep convolutional residual network architecture as a backbone, followed by a fully connected classifier network, that classifies between authentic and spliced images. The classifier networks have been evaluated using the CASIA v2.0 dataset. Both are proven to yield accuracies more than 96% on an average, having surpassed the state-of-the-art results.

Efficient hybrid passive method for the detection and localization of copy-move and spliced images

Digital passive image forgery methods are extensively used to verify the authenticity and integrity of images.Splicing and copy-move are the most common types of passive digital image forgeries. Several approaches have beenproposed to detect these forgeries separately, but very few approaches are available that can detect them simultaneously.However, a more e?icient method is still in demand to meet the day-to-day challenges to detect these forgeries at thesame time. So, a passive hybrid approach based on discrete fractional cosine transform (DFrCT) and local binarypattern (LBP) is proposed to detect copy-move and splicing forgeries simultaneously. The extra parameter i.e. fractionalparameter of DFrCT is utilized to enhance the accuracy and LBP is used to highlight the tampering artifacts effectively.Then, a support vector machine (SVM) is employed to categorize the images into authentic, copy-move, and splicedimages. Next, localization is performed on both the copy-move and spliced images to localize the duplicated areas inthe image. Experiments on six benchmark datasets, namely, CASIA v1.0, GRIP, CASIA v2.0, IMD, COVERAGE,and Columbia, attain accuracy rates of 99.67%, 99.23%, 99.76%, 98.81%, 95%, and 98.17%, respectively. To validatethe effectiveness of the proposed method, comparative analysis has been performed with existing methods in terms ofROC, precision, recall,F1score,F2score, and accuracy. Moreover, the robustness of the proposed work is tested underrotation attack and better results are attained in comparison to the existing techniques.

Second-Order Statistical Methods GLCM for Authentication Systems

For many uses, biometric systems have gained considerable attention. Iris identification was One of the most powerful sophisticated biometrical techniques for effective and confident authentication. The current iris identification system offers accurate and reliable results based on near-infrared light (NIR) images when images are taken in a restricted area with fixed-distance user cooperation. However, for the color eye images obtained under visible wavelength (VW) without collaboration among the users, the efficiency of iris recognition degrades because of noise such as eye blurring images, eye lashing, occlusion, and reflection. This work aims to use the Gray-Level Co- occurrence Matrix (GLCM) to retrieve the iris's characteristics in both NIR iris images and visible spectrum. GLCM is second-order Statistical-Based Methods for Texture Analysis. The GLCM-based extraction technology was applied after the preprocessing method to extract the pure iris region's characteristics. The Energy, Entropy, Correlation, homogeneity, and Contrast collection of second-order statistical features are determined from the generated co-occurrence matrix, Stored as a vector for numerical features. This approach is used and evaluated on the CASIA v1and ITTD v1 databases as NIR iris image and UBIRIS v1 as a color image. The results showed a high accuracy rate (99.2 %) on CASIA v1, (99.4) on ITTD v1, and (87%) on UBIRIS v1 evaluated by comparing to the other methods

Fusion of Handcrafted and Deep Features for Forgery Detection in Digital Images

Content authentication of digital images has captured the attention of forensic experts and security researchers due to a multi-fold increase in the dissemination of multimedia data through the open and vulnerable Internet. Shrewd attackers successfully devise novel ways to challenge state-of-art forensic tools used for forgery detection in digital images. Feature engineering approaches have yielded up to 97% accuracy on benchmarked datasets. Deep learning approaches have shown promising results in various image classification problems but cannot find hidden patterns in digital images, which can reliably detect image forgeries. State-of-art accuracy of deep learning approaches for forgery detection is up to 98% on benchmarked datasets. The objective of the proposed approach is to further escalate the detection accuracy, pushing it near 100%. In this paper, a synergy of handcrafted features based on color characteristics and deep features using the image’s luminance channel is employed to mine patterns responsible for accurate forgery detection. In the first Stream, 648-D Markov-based features are computed from the quaternion discrete cosine transform of the image. In the second Stream, the luminance channel of YCbCr colorspace is used to extract the Local Binary Pattern of the image. Further, local binary feature maps are fed to the pre-trained ResNet-18 model to obtain a 512-D feature vector called ’ResFeats’ from the last layer of the model’s convolutional base portion. The handcrafted features from Stream I and ResFeats from Stream II are combined to form an 1160-D feature vector. Further, classification is performed using a shallow neural network, and the method is tested on CASIA v1 and CASIA v2 datasets. The accuracy of the proposed fusion-based approach is 99.3% on benchmark datasets.

Performance analysis of iris biometric system using GKPCA and SVM

Among all biometric technologies, iris recognition is the most accurate and high confidence authentication system. Due to the limitations in PCA-based system, modified principal component analysis (PCA)-based feature extraction is proposed in iris recognition system. In the proposed system, features are extracted using Gaussian kernel PCA (GKPCA) and classified using support vector machine (SVM). GKPCA and SVM algorithms are evaluated using CASIA V3 iris database. The performances are compared with the existing PCA-based system. The proposed system achieves 96.67% of accuracy for 256 features using GKPCA linear SVM. False acceptance rate (FAR) and false rejection rate (FRR) are 0 and 3 respectively for linear SVM. The results show that the proposed system performs accurate localisation of patterns even in non-ideal conditions.

Image splicing detection technique based on Illumination-Reflectance model and LBP

A Copy-create digital image forgery is image tampering that merges two or more areas of images from different sources into one composite image; it is also known as image splicing. Excellent forgeries are so tricky that they are not noticeable to the naked eye and don’t reveal traces of tampering to traditional image tamper detection techniques. To tackle this image splicing detection problem, machines learning-based techniques are used to instantly discriminate between the authentic and forged image. Numerous image forgery detection methods to detect and localize spliced areas in the composite image have been proposed. However, the existing methods with high detection accuracy are computationally expensive since most of them are based on hybrid feature set or rely on the complex deep learning models, which are very expensive to train, run on expensive GPUs, and require a very large amount of data to perform better. In this paper, we propose a simple and computationally efficient image splicing forgery detection that considers a trade-off between performance and the cost to the users. Our method involves the following steps: first, luminance and chrominance are found from the input image; second, illumination is estimated from Luminance using Illumination-Reflectance model; third, Local Binary Patterns normalized histogram for illumination and Chrominance is computed and used as the feature vector for classification using the following machine learning algorithms: Support Vector Machine, Linear Discriminant Analysis, Logistic Regression, K-Nearest Neighbors, Decision Tree, and Naive Bayes. Extensive experiments on the public dataset CASIA v2.0 show that the new algorithm is computationally efficient and effective for image splicing tampering detection.

Iris Segmentation Using Feature Channel Optimization for Noisy Environments

In recent years, iris recognition has been widely used in various fields. As the first step of iris recognition, segmentation accuracy is of great significance to the final recognition. However, iris images exhibit a variety of noise in the real world, which leads to lower segmentation accuracy than the ideal case. To address this problem, this paper proposes an iris segmentation method using feature channel optimization for noisy images. The method for non-ideal environments with noise is more suitable for practical applications. We add dense blocks and dilated convolutional layers to the encoder so that the information gradient flow obtained by different layers can be reused, and the receptive field can be expanded. In the decoder, based on Jensen-Shannon (JS) divergence, we first recalculate the weight of the feature channels obtained from each layer, which enhances the useful information and suppresses the interference information in the noisy environments to boost the segmentation accuracy. The proposed architecture is validated in the CASIA v4.0 interval (CASIA) and IIT Delhi v1.0 datasets (IITD). For CASIA, the mean error rate is 0.78%, and the F-measure value is 98.21%. For IITD, the mean error rate is 0.97%, and the F-measure value is 97.87%. Experimental results show that the proposed method outperforms other state-of-art methods under noisy environments, such as Gaussian blur, Gaussian noise, and salt and pepper noise.

A passive approach for the detection of splicing forgery in digital images

With the technology progress, a plethora of freely accessible software has questioned the authenticity of digital images. This field is continuously creating challenges for researchers to ascertain the integrity of images. Hence, there is a need to improve the performance of forgery detection algorithms from time to time. This paper is focused on the detection of splicing forgery because it is one of the most frequently used image manipulation techniques. In the proposed scheme, Markov features in both Discrete Wavelet Transform (DWT) and Local Binary Pattern (LBP) domains are extracted and combined for the detection of image splicing. Three-level DWT is applied to the source image by the means of discrete Haar wavelet. The image is split in to high and low-frequency sub-bands after applying one level DWT. Furthermore, low-frequency sub-band is decomposed twice to obtain three-level DWT, which leads to more information and less amount of noise. The efficacy of the proposed scheme has been appraised on six benchmark datasets i.e. CASIA v2.0, DVMM, IFS-TC, CASIA v1.0, Columbia, and DSO-1. Moreover, the SVM classifier is trained to classify the images as tampered or authentic. The effectiveness of the proposed scheme is evaluated based on various performance parameters such as accuracy, sensitivity, specificity, and informedness. The proposed results show improved accuracy i.e. 99.69%, 99.76%, 97.80%, 98.61%, 96.90%, and 92.50% on CASIA v1.0, CASIA v2.0, DVMM, Columbia, IFS-TC, and DSO-1, respectively, in comparison to other existing approaches.

Image Splicing Forgery Detection Scheme Using New Local Binary Pattern Varient

In this research develop passive image splicing detection method based on a new descriptor called Adaptive Threshold Mean Ternary Pattern (ATMTP). It was developed based on strength and weaknesses of both Local Binary Pattern (LBP) and Local Ternary Pattern (LTP). ATMTP extraction feature is normally achieved by using proposed mean based thresholding and adaptive ternary thresholding, the former is robust to noise while the latter is robust to noise and other photometric attacks. It is designed to withstand against photometric manipulations, be it single or double attacks. In this research the ATMTP color features extracted from R, G, and B channels have revealed that the present method achieved higher accuracy on standard datasets CASIA V2.0 out of 99.03%, Sensitivity 99.6%, and specificity 98.1%. Finally, in terms of accuracy, the proposed SFD scheme outperformed the best recent works in this area.