Biblio

In order to detect the objects on the water surface, a neural style learning algorithm is proposed in this paper. The algorithm uses the Gram matrix of a pre-trained convolutional neural network to represent the style of the texture in the image, which is originally used for image style transfer. The objects on the water surface can be easily distinguished by the difference in their styles of the image texture. The algorithm is tested on the dataset of the Airbus Ship Detection Challenge on Kaggle. Compared to the other water surface object detection algorithms, the proposed algorithm has a good precision of 0.925 with recall equals to 0.86.

Vehicle-logo location is a crucial step in vehicle-logo recognition system. In this paper, a novel approach of the vehicle-logo location based on edge detection and morphological filter is proposed. Firstly, the approximate location of the vehicle-logo region is determined by the prior knowledge about the position of the vehicle-logo; Secondly, the texture measure is defined to recognize the texture of the vehicle-logo background; Then, vertical edge detection is executed for the vehicle-logo background with the horizontal texture and horizontal edge detection is implemented for the vehicle-logo background with the vertical texture; Finally, position of the vehicle-logo is located accurately by mathematical morphology filter. Experimental results show the proposed method is effective.

Despite the high performance of neural style transfer on stylized pictures, we found that Gatys et al [1] algorithm cannot perfectly reconstruct texture style. Output stylized picture could emerge unsatisfied unexpected textures such like muddiness in local area and insufficient grain expression. Our method bases on original algorithm, adding the Gradient Gram description on style loss, aiming to strengthen texture expression and eliminate muddiness. To some extent our method lengthens the runtime, however, its output stylized pictures get higher performance on texture details, especially in the elimination of muddiness.

The global proliferation of affordable photographing devices and readily-available face image and video editing software has caused a remarkable rise in face manipulations, e.g., altering face skin color using FaceApp. Such synthetic manipulations are becoming a very perilous problem, as altered faces not only can fool human experts but also have detrimental consequences on automated face identification systems (AFIS). Thus, it is vital to formulate techniques to improve the robustness of AFIS against digital face manipulations. The most prominent countermeasure is face manipulation detection, which aims at discriminating genuine samples from manipulated ones. Over the years, analysis of microtextural features using local image descriptors has been successfully used in various applications owing to their flexibility, computational simplicity, and performances. Therefore, in this paper, we study the possibility of identifying manipulated faces via local feature descriptors. The comparative experimental investigation of ten local feature descriptors on a new and publicly available DeepfakeTIMIT database is reported.

With the arrival of several face-swapping applications such as FaceApp, SnapChat, MixBooth, FaceBlender and many more, the authenticity of digital media content is hanging on a very loose thread. On social media platforms, videos are widely circulated often at a high compression factor. In this work, we analyze several deep learning approaches in the context of deepfakes classification in high compression scenarios and demonstrate that a proposed approach based on metric learning can be very effective in performing such a classification. Using less number of frames per video to assess its realism, the metric learning approach using a triplet network architecture proves to be fruitful. It learns to enhance the feature space distance between the cluster of real and fake videos embedding vectors. We validated our approaches on two datasets to analyze the behavior in different environments. We achieved a state-of-the-art AUC score of 99.2% on the Celeb-DF dataset and accuracy of 90.71% on a highly compressed Neural Texture dataset. Our approach is especially helpful on social media platforms where data compression is inevitable.

Since the neural networks are utilized to extract information from an image, Gatys et al. found that they could separate the content and style of images and reconstruct them to another image which called Style Transfer. Moreover, there are many feed-forward neural networks have been suggested to speeding up the original method to make Style Transfer become practical application. However, this takes a price: these feed-forward networks are unchangeable because of their fixed parameters which mean we cannot transfer arbitrary styles but only single one in real-time. Some coordinated approaches have been offered to relieve this dilemma. Such as a style-swap layer and an adaptive normalization layer (AdaIN) and soon. Its worth mentioning that we observed that the AdaIN layer only aligns the means and variance of the content feature maps with those of the style feature maps. Our method is aimed at presenting an operational approach that enables arbitrary style transfer in real-time, reserving more statistical information by histogram matching, providing more reliable texture clarity and more humane user control. We achieve performance more cheerful than existing approaches without adding calculation, complexity. And the speed comparable to the fastest Style Transfer method. Our method provides more flexible user control and trustworthy quality and stability.

In this paper, the layer choices of the image style transfer method using the VGG-19 neural network are studied. The VGG-19 network is used to extract the feature maps which have their implicit meaning as a learning basis. If the layers for stylistic learning are not suitably chosen, the quality of style transferred image may not look good. After making experiments, it can be observed that the color information is concentrated on lower layers from conv1-1 to conv2-2, and texture information is concentrated on the middle layers from conv3-1 to conv4-4. As to the higher layers from conv5-1 to conv5-4, they seem to be able to depict image content well. Based on these observations, the methods of color transfer, texture transfer and style transfer are presented and make comparisons with conventional methods.

Humans have created many pioneers of art from the beginning of time. There are not many notable achievements by an artificial intelligence to create something visually captivating in the field of art. However, some breakthroughs were made in the past few years by learning the differences between the content and style of an image using convolution neural networks and texture synthesis. But most of the approaches have the limitations on either processing time, choosing a certain style image or altering the weight ratio of style image. Therefore, we are to address these restrictions and provide a system which allows any style image selection with a user defined style weight ratio in minimum time possible.

With the emergence of cloud, content-based image retrieval (CBIR) on encrypted domain gain enormous importance due to the ever increasing need for ensuring confidentiality, authentication, integrity and privacy of data. CBIR on outsourced encrypted images can be done by extracting features from unencrypted images and generating searchable encrypted index based on it. Visual descriptors like color descriptors, shape and texture descriptors, etc. are employed for similarity search. Since visual descriptors used to represent an image have crucial role in retrieving most similar results, an attempt to combine them has been made in this paper. The effect of combining different visual descriptors on retrieval precision in secure CBIR scheme proposed by Xia et al. is analyzed. Experimental results show that combining visual descriptors can significantly enhance retrieval precision of the secure CBIR scheme.

Information security has developed rapidly over the recent years with a key being the emergence of social media. To standardize this discipline, security of an individual becomes an urgent concern. In 2019, it is estimated that there will be over 2.5 billion social media users around the globe. Unfortunately, anonymous identity has become a major concern for the security advisors. Due to the technological advancements, the phishers are able to access the confidential information. To resolve these issues numerous solutions have been proposed, such as biometric identification, facial and audio recognition etc prior access to any highly secure forum on the web. Generating digital signatures is the recent trend being incorporated in the field of digital security. We have designed an algorithm that after generating 68 point facial landmark, converts the image to a highly compressed and secure digital signature. The proposed algorithm generates a unique signature for an individual which when stored in the user account information database will limit the creation of fake or multiple accounts. At the same time the algorithm reduces the database storage overhead as it stores the facial identity of an individual in the form of a compressed textual signature rather than the traditional method where the image file was being stored, occupying lesser amount of space and making it more efficient in terms of searching, fetching and manipulation. A unique new analysis of the features produced at intermediate layers has been applied. Here, we opt to use the normal and two opposites' angular measures of the triangle as the invariance. It simply acts as the real-time optimized encryption procedure to achieve the reliable security goals explained in detail in the later sections.

Biometric system security requires cryptographic protection of sample data under certain circumstances. We assess low complexity selective encryption schemes applied to JPEG2000 compressed iris data by conducting iris recognition on the selectively encrypted data. This paper specifically compares the effects of a recently proposed approach, i.e. applying selective encryption to normalised texture data, to encrypting classical sample data. We assess achieved protection level as well as computational cost of the considered schemes, and particularly highlight the role of segmentation in obtaining surprising results.

Super-resolution (SR) of hyperspectral images (HSIs) aims to enhance the spatial/spectral resolution of hyperspectral imagery and the super-resolved results will benefit many remote sensing applications. A generative adversarial network for HSIs super-resolution (HSRGAN) is proposed in this paper. Specifically, HSRGAN constructs spectral and spatial blocks with residual network in generator to effectively learn spectral and spatial features from HSIs. Furthermore, a new loss function which combines the pixel-wise loss and adversarial loss together is designed to guide the generator to recover images approximating the original HSIs and with finer texture details. Quantitative and qualitative results demonstrate that the proposed HSRGAN is superior to the state of the art methods like SRCNN and SRGAN for HSIs spatial SR.

Biometry is often used as a part of the multi-factor authentication in order to improve the security of IT systems. In this paper, we propose the palmprint-based solution for user identity verification. In particular, we present a new approach to feature extraction. The proposed method is based both on texture and color information. Our experiments show that using the proposed hybrid features allows for achieving satisfactory accuracy without increasing requirements for additional computational resources. It is important from our perspective since the proposed method is dedicated to smartphones and other handhelds in mobile verification scenarios.

As steganography is the main practice of hidden writing, many deep neural networks are proposed to conceal secret information into images, whose invisibility and security are unsatisfactory. In this paper, we present an encoder-decoder framework with an adversarial discriminator to conceal messages or images into natural images. The message is embedded into QR code first which significantly improves the fault-tolerance. Considering the mean squared error (MSE) is not conducive to perfectly learn the invisible perturbations of cover images, we introduce a texture-based loss that is helpful to hide information into the complex texture regions of an image, improving the invisibility of hidden information. In addition, we design a truncated layer to cope with stego image distortions caused by data type conversion and a moment layer to train our model with varisized images. Finally, our experiments demonstrate that the proposed model improves the security and visual quality of stego images.

This work proposes an approach to find and learn informative representations from 2 dimensional gray-level images for facial expression recognition application. The learned features are obtained from a designed convolutional neural network (CNN). The developed CNN enables us to learn features from the images in a highly efficient manner by cascading different layers together. The developed model is computationally efficient since it does not consist of a huge number of layers and at the same time it takes into consideration the overfitting problem. The outcomes from the developed CNN are compared to handcrafted features that span texture and shape features. The experiments conducted on the Bosphours database show that the developed CNN model outperforms the handcrafted features when coupled with a Support Vector Machines (SVM) classifier.

Transferring artistic styles onto everyday photographs has become an extremely popular task in both academia and industry. Recently, offline training has replaced online iterative optimization, enabling nearly real-time stylization. When those stylization networks are applied directly to high-resolution images, however, the style of localized regions often appears less similar to the desired artistic style. This is because the transfer process fails to capture small, intricate textures and maintain correct texture scales of the artworks. Here we propose a multimodal convolutional neural network that takes into consideration faithful representations of both color and luminance channels, and performs stylization hierarchically with multiple losses of increasing scales. Compared to state-of-the-art networks, our network can also perform style transfer in nearly real-time by performing much more sophisticated training offline. By properly handling style and texture cues at multiple scales using several modalities, we can transfer not just large-scale, obvious style cues but also subtle, exquisite ones. That is, our scheme can generate results that are visually pleasing and more similar to multiple desired artistic styles with color and texture cues at multiple scales.

``Style transfer'' among images has recently emerged as a very active research topic, fuelled by the power of convolution neural networks (CNNs), and has become fast a very popular technology in social media. This paper investigates the analogous problem in the audio domain: How to transfer the style of a reference audio signal to a target audio content? We propose a flexible framework for the task, which uses a sound texture model to extract statistics characterizing the reference audio style, followed by an optimization-based audio texture synthesis to modify the target content. In contrast to mainstream optimization-based visual transfer method, the proposed process is initialized by the target content instead of random noise and the optimized loss is only about texture, not structure. These differences proved key for audio style transfer in our experiments. In order to extract features of interest, we investigate different architectures, whether pre-trained on other tasks, as done in image style transfer, or engineered based on the human auditory system. Experimental results on different types of audio signal confirm the potential of the proposed approach.

Recent research endeavors have shown the potential of using feed-forward convolutional neural networks to accomplish fast style transfer for images. In this work, we take one step further to explore the possibility of exploiting a feed-forward network to perform style transfer for videos and simultaneously maintain temporal consistency among stylized video frames. Our feed-forward network is trained by enforcing the outputs of consecutive frames to be both well stylized and temporally consistent. More specifically, a hybrid loss is proposed to capitalize on the content information of input frames, the style information of a given style image, and the temporal information of consecutive frames. To calculate the temporal loss during the training stage, a novel two-frame synergic training mechanism is proposed. Compared with directly applying an existing image style transfer method to videos, our proposed method employs the trained network to yield temporally consistent stylized videos which are much more visually pleasant. In contrast to the prior video style transfer method which relies on time-consuming optimization on the fly, our method runs in real time while generating competitive visual results.

In this paper, inspired by Gatys's recent work, we propose a novel approach that transforms photos to comics using deep convolutional neural networks (CNNs). While Gatys's method that uses a pre-trained VGG network generally works well for transferring artistic styles such as painting from a style image to a content image, for more minimalist styles such as comics, the method often fails to produce satisfactory results. To address this, we further introduce a dedicated comic style CNN, which is trained for classifying comic images and photos. This new network is effective in capturing various comic styles and thus helps to produce better comic stylization results. Even with a grayscale style image, Gatys's method can still produce colored output, which is not desirable for comics. We develop a modified optimization framework such that a grayscale image is guaranteed to be synthesized. To avoid converging to poor local minima, we further initialize the output image using grayscale version of the content image. Various examples show that our method synthesizes better comic images than the state-of-the-art method.

Malware classification is a critical part in the cyber-security. Traditional methodologies for the malware classification typically use static analysis and dynamic analysis to identify malware. In this paper, a malware classification methodology based on its binary image and extracting local binary pattern (LBP) features is proposed. First, malware images are reorganized into 3 by 3 grids which is mainly used to extract LBP feature. Second, the LBP is implemented on the malware images to extract features in that it is useful in pattern or texture classification. Finally, Tensorflow, a library for machine learning, is applied to classify malware images with the LBP feature. Performance comparison results among different classifiers with different image descriptors such as GIST, a spatial envelop, and the LBP demonstrate that our proposed approach outperforms others.

The image contains a lot of visual as well as hidden information. Both, information must be secured at the time of transmission. With this motivation, a scheme is proposed based on encryption in tetrolet domain. For encryption, an iterative based Arnold transform is used in proposed methodology. The images are highly textured, which contains the authenticity of the image. For that, decryption process is performed in this way so that maximum, the edges and textures should be recovered, effectively. The suggested method has been tested on standard images and results obtained after applying suggested method are significant. A comparison is also performed with some standard existing methods to measure the effectiveness of the suggested method.

A number of blind Image Quality Evaluation Metrics (IQEMs) for Unmanned Aerial Vehicle (UAV) photograph application are presented. Nowadays, the visible light camera is widely used for UAV photograph application because of its vivid imaging effect; however, the outdoor environment light will produce great negative influences on its imaging output unfortunately. In this paper, to conquer this problem above, we design and reuse a series of blind IQEMs to analyze the imaging quality of UAV application. The Human Visual System (HVS) based IQEMs, including the image brightness level, the image contrast level, the image noise level, the image edge blur level, the image texture intensity level, the image jitter level, and the image flicker level, are all considered in our application. Once these IQEMs are calculated, they can be utilized to provide a computational reference for the following image processing application, such as image understanding and recognition. Some preliminary experiments for image enhancement have proved the correctness and validity of our proposed technique.

The technology of vehicle video detecting and tracking has been playing an important role in the ITS (Intelligent Transportation Systems) field during recent years. The occlusion phenomenon among vehicles is one of the most difficult problems related to vehicle tracking. In order to handle occlusion, this paper proposes an effective solution that applied Markov Random Field (MRF) to the traffic images. The contour of the vehicle is firstly detected by using background subtraction, then numbers of blocks with vehicle's texture and motion information are filled inside each vehicle. We extract several kinds of information of each block to process the following tracking. As for each occlusive block two groups of clique functions in MRF model are defined, which represents spatial correlation and motion coherence respectively. By calculating each occlusive block's total energy function, we finally solve the attribution problem of occlusive blocks. The experimental results show that our method can handle occlusion problems effectively and track each vehicle continuously.
 

Abnormal crowd behavior detection is an important research issue in video processing and computer vision. In this paper we introduce a novel method to detect abnormal crowd behaviors in video surveillance based on interest points. A complex network-based algorithm is used to detect interest points and extract the global texture features in scenarios. The performance of the proposed method is evaluated on publicly available datasets. We present a detailed analysis of the characteristics of the crowd behavior in different density crowd scenes. The analysis of crowd behavior features and simulation results are also demonstrated to illustrate the effectiveness of our proposed method.