Biblio

In this paper, we present an improved approach to transfer style for videos based on semantic segmentation. We segment foreground objects and background, and then apply different styles respectively. A fully convolutional neural network is used to perform semantic segmentation. We increase the reliability of the segmentation, and use the information of segmentation and the relationship between foreground objects and background to improve segmentation iteratively. We also use segmentation to improve optical flow, and apply different motion estimation methods between foreground objects and background. This improves the motion boundaries of optical flow, and solves the problems of incorrect and discontinuous segmentation caused by occlusion and shape deformation.

Neural architectures are the foundation for improving performance of deep neural networks (DNNs). This paper presents deep compositional grammatical architectures which harness the best of two worlds: grammar models and DNNs. The proposed architectures integrate compositionality and reconfigurability of the former and the capability of learning rich features of the latter in a principled way. We utilize AND-OR Grammar (AOG) as network generator in this paper and call the resulting networks AOGNets. An AOGNet consists of a number of stages each of which is composed of a number of AOG building blocks. An AOG building block splits its input feature map into N groups along feature channels and then treat it as a sentence of N words. It then jointly realizes a phrase structure grammar and a dependency grammar in bottom-up parsing the “sentence” for better feature exploration and reuse. It provides a unified framework for the best practices developed in state-of-the-art DNNs. In experiments, AOGNet is tested in the ImageNet-1K classification benchmark and the MS-COCO object detection and segmentation benchmark. In ImageNet-1K, AOGNet obtains better performance than ResNet and most of its variants, ResNeXt and its attention based variants such as SENet, DenseNet and DualPathNet. AOGNet also obtains the best model interpretability score using network dissection. AOGNet further shows better potential in adversarial defense. In MS-COCO, AOGNet obtains better performance than the ResNet and ResNeXt backbones in Mask R-CNN.

The Internet plays an increasingly important role in people's lives, but it also brings security problems. CAPTCHA, which stands for Completely Automated Public Turing Test to Tell Computers and Humans Apart, has been widely used as a security mechanism. This paper outlines the scientific and technological progress in both the design and attack of CAPTCHAs related to these three CAPTCHA categories. It first presents a comprehensive survey of recent developments for each CAPTCHA type in terms of usability, robustness and their weaknesses and strengths. Second, it summarizes the attack methods for each category. In addition, the differences between the three CAPTCHA categories and the attack methods will also be discussed. Lastly, this paper provides suggestions for future research and proposes some problems worthy of further study.

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.

Remote authentication via biometric features has received much attention recently, hence the security of biometric data is of great importance. Here a crypto-steganography method applied for the protection of biometric data is implemented. It include semantic segmentation, chaotic encryption, data hiding and fingerprint recognition to avoid the risk of spoofing attacks. Semantically segmented image of the person to be authenticated is used as the cover image and chaotic encrypted fingerprint image is used as secret image here. Chaotic encrypted fingerprint image is embedded into the cover image using Integer Wavelet Transform (IWT). Extracted fingerprint image is then compared with the fingerprints in database to authenticate the person. Qualified Significant Wavelet Trees (QSWT`s) of the cover image act as the target coefficients to insert the secret image. IWT provide both invisibility and resistance against the lossy transmissions. Experimental result shows that the semantic segmentation reduces the bandwidth efficiently. In addition, chaotic encryption and IWT based data hiding increases the security of the transmitted biometric data.

In order to solve the interference of burrs, aliasing and other noises in the background area of millimeter wave human security inspection on the objects identification, an adaptive template matching filtering method is proposed. First, the preprocessed original image is segmented by level set algorithm, then the result is used as a template to filter the background of the original image. Finally, the image after background filtered is used as the input of bilateral filtering. The contrast experiments based on the actual millimeter wave image verifies the improvement of this algorithm compared with the traditional filtering method, and proves that this algorithm can filter the background noise of the human security image, retain the image details of the human body area, and is conducive to the object recognition and location in the millimeter wave security image.

In the past few years, visual information collection and transmission is increased significantly for various applications. Smart vehicles, service robotic platforms and surveillance cameras for the smart city applications are collecting a large amount of visual data. The preservation of the privacy of people presented in this data is an important factor in storage, processing, sharing and transmission of visual data across the Internet of Robotic Things (IoRT). In this paper, a novel anonymisation method for information security and privacy preservation in visual data in sharing layer of the Web of Robotic Things (WoRT) is proposed. The proposed framework uses deep neural network based semantic segmentation to preserve the privacy in video data base of the access level of the applications and users. The data is anonymised to the applications with lower level access but the applications with higher legal access level can analyze and annotated the complete data. The experimental results show that the proposed method while giving the required access to the authorities for legal applications of smart city surveillance, is capable of preserving the privacy of the people presented in the data.

In order to study the application of improved image hashing algorithm in image tampering detection, based on compressed sensing and ring segmentation, a new image hashing technique is studied. The image hash algorithm based on compressed sensing and ring segmentation is proposed. First, the algorithm preprocesses the input image. Then, the ring segment is used to extract the set of pixels in each ring region. These aggregate data are separately performed compressed sensing measurements. Finally, the hash value is constructed by calculating the inner product of the measurement vector and the random vector. The results show that the algorithm has good perceived robustness, uniqueness and security. Finally, the ROC curve is used to analyze the classification performance. The comparison of ROC curves shows that the performance of the proposed algorithm is better than FM-CS, GF-LVQ and RT-DCT.

Image registration is the process of aligning images of the same scene taken at different instances, from different viewpoints or by heterogeneous sensors. This can be achieved either by area based or by feature based image matching techniques. Feature based image registration focuses on detecting relevant features from the input images and attaching descriptors to these features. Matching visual descriptions of two images is a major task in image registration. This feature matching is currently done using Exhaustive Search (or Brute-Force) and Nearest Neighbour Search. The traditional method used for nearest neighbour search is by representing the data as k-d trees. This nearest neighbour search can also be performed using combinatorial optimization algorithms such as Simulated Annealing. This work proposes a method to perform image feature matching by nearest neighbour search done based on Threshold Accepting, a faster version of Simulated Annealing.The experiments performed suggest that the proposed algorithm can produce better results within a minimum number of iterations than many existing algorithms.

Convolutional Neural Networks (CNN) have shown astonishing results in the field of computer vision. This paper proposes a foreground segmentation algorithm based on CNN to tackle the practical challenges in the video surveillance system such as illumination changes, dynamic backgrounds, camouflage, and static foreground object, etc. The network is trained using the input of image sequences with respective ground-truth. The algorithm employs a CNN called VGG-16 to extract features from the input. The extracted feature maps are upsampled using a bilinear interpolation. The upsampled feature mask is passed through a sigmoid function and threshold to get the foreground mask. Binary cross entropy is used as the error function to compare the constructed foreground mask with the ground truth. The proposed algorithm was tested on two standard datasets and showed superior performance as compared to the top-ranked foreground segmentation methods.

In the field of video surveillance, the demands of intelligent video analysis services based on Deep Neural Networks (DNNs) have grown rapidly. Although most existing studies focus on the performance of DNNs pre-deployed at remote clouds, the network delay caused by computation offloading from network cameras to remote clouds is usually long and sometimes unbearable. Edge computing can enable rich services and applications in close proximity to the network cameras. However, owing to the limited computing resources of distributed edge clouds, it is challenging to satisfy low latency and high accuracy requirements for all users, especially when the number of users surges. To address this challenge, we first formulate the intelligent video surveillance task scheduling problem that minimizes the average response time while meeting the performance requirements of tasks and prove that it is NP-hard. Second, we present an adaptive DNN model selection method to identify the most effective DNN model for each task by comparing the feature similarity between the input video segment and pre-stored training videos. Third, we propose a two-stage delay-aware graph searching approach that presents a beneficial trade-off between network delay and computing delay. Experimental results demonstrate the efficiency of our approach.

The transmission of medical image data in an open network environment is subject to privacy issues including patient privacy and data leakage. In the past, image encryption and information-hiding technology have been used to solve such security problems. But these methodologies, in general, suffered from difficulties in retrieving original images. We present in this paper an algorithm to protect key regions in medical images. First, coefficient of variation is used to locate the key regions, a.k.a. the lesion areas, of an image; other areas are then processed in blocks and analyzed for texture complexity. Next, our reversible data-hiding algorithm is used to embed the contents from the lesion areas into a high-texture area, and the Arnold transformation is performed to protect the original lesion information. In addition to this, we use the ciphertext of the basic information about the image and the decryption parameter to generate the Quick Response (QR) Code to replace the original key regions. Consequently, only authorized customers can obtain the encryption key to extract information from encrypted images. Experimental results show that our algorithm can not only restore the original image without information loss, but also safely transfer the medical image copyright and patient-sensitive information.

In the last several decades digital images were extend their usage in numerous areas. Due to various digital image processing methods they became part areas such as astronomy, agriculture and more. One of the main task in image processing application is segmentation. Since segmentation represents rather important problem, various methods were proposed in the past. One of the methods is to use clustering algorithms which is explored in this paper. We propose k-means algorithm for digital image segmentation. K-means algorithm's well known drawback is the high possibility of getting trapped into local optima. In this paper we proposed brain storm optimization algorithm for optimizing k-means algorithm used for digital image segmentation. Our proposed algorithm is tested on several benchmark images and the results are compared with other stat-of-the-art algorithms. The proposed method outperformed the existing methods.

With the rapid development of information technology, video surveillance system has become a key part in the security and protection system of modern cities. Especially in prisons, surveillance cameras could be found almost everywhere. However, with the continuous expansion of the surveillance network, surveillance cameras not only bring convenience, but also produce a massive amount of monitoring data, which poses huge challenges to storage, analytics and retrieval. The smart monitoring system equipped with intelligent video analytics technology can monitor as well as pre-alarm abnormal events or behaviours, which is a hot research direction in the field of surveillance. This paper combines deep learning methods, using the state-of-the-art framework for instance segmentation, called Mask R-CNN, to train the fine-tuning network on our datasets, which can efficiently detect objects in a video image while simultaneously generating a high-quality segmentation mask for each instance. The experiment show that our network is simple to train and easy to generalize to other datasets, and the mask average precision is nearly up to 98.5% on our own datasets.

Edge detection is one of the most important topics of image processing. In the scenario of cloud computing, performing edge detection may also consider privacy protection. In this paper, we propose an edge detection and image segmentation scheme on an encrypted image with Sobel edge detector. We implement Gaussian filtering and Sobel operator on the image in the encrypted domain with homomorphic property. By implementing an adaptive threshold decision algorithm in the encrypted domain, we obtain a threshold determined by the image distribution. With the technique of garbled circuit, we perform comparison in the encrypted domain and obtain the edge of the image without decrypting the image in advanced. We then propose an image segmentation scheme on the encrypted image based on the detected edges. Our experiments demonstrate the viability and effectiveness of the proposed encrypted image edge detection and segmentation.

The CAPTCHA is an effective method commonly used in live interactive proofs on the Internet. The widely used CAPTCHAs are text-based schemes. In this paper, we document how we have broken such text-based scheme used by a website CAPTCHA. We use the sliding window to segment 1001 pieces of CAPTCHA to get 5900 images with single-character useful information, a total of 25 categories. In order to make the convolution neural network learn more image features, we augmented the data set to get 129924 pictures. The data set is trained and tested in AlexNet and GoogLeNet to get the accuracy of 87.45% and 98.92%, respectively. The experiment shows that the optimized network parameters can make the accuracy rate up to 92.7% in AlexNet and 98.96% in GoogLeNet.

Online web service providers generally protect themselves through CAPTCHA. A CAPTCHA is a type of challenge-response test used in computing as an attempt to ensure that the response is generated by a person. CAPTCHAS are mainly instigated as distorted text which the handler must correctly transcribe. Numerous schemes have been proposed till date in order to prevent attacks by Bots. This paper also presents a cross correlation based approach in breaking of famous service provider's text CAPTCHA i.e. PayPal.com and the other one is of India's most visited website IRCTC.co.in. The procedure can be fragmented down into 3 firmly tied tasks: pre-processing, segmentation, and classification. The pre-processing of the image is performed to remove all the background noise of the image. The noise in the CAPTCHA are unwanted on pixels in the background. The segmentation is performed by scanning the image for on pixels. The organization is performed by using the association values of the inputs and templates. Two types of templates have been used for classification purpose. One is the standard templates which give 30% success rate and other is the noisy templates made from the captcha images and success rate achieved with these is 100%.

At present, the captcha is widely used in the Internet. The method of captcha recognition using the convolutional neural networks was introduced in this paper. It was easier to apply the convolution neural network model of simple training to segment the captcha, and the network structure was established imitating VGGNet model. and the correct rate can be reached more than 90%. For the more difficult segmentation captcha, it can be used the end-to-end thought to the captcha as a whole to training, In this way, the recognition rate of the more difficult segmentation captcha can be reached about 85%.

We always use CAPTCHA(Completely Automated Public Turing test to Tell Computers and Humans Apart) to prevent automated bot for data entry. Although there are various kinds of CAPTCHAs, text-based scheme is still applied most widely, because it is one of the most convenient and user-friendly way for daily user [1]. The fact is that segmentations of different types of CAPTCHAs are not always the same, which means one of CAPTCHA's bottleneck is the segmentation. Once we could accurately split the character, the problem could be solved much easier. Unfortunately, the best way to divide them is still case by case, which is to say there is no universal way to achieve it. In this paper, we present a novel algorithm to achieve state-of-the-art performance, what was more, we also constructed a new convolutional neural network as an add-on recognition part to stabilize our state-of-the-art performance of the whole CAPTCHA system. The CAPTCHA datasets we are using is from the State Administration for Industry& Commerce of the People's Republic of China. In this datasets, there are totally 33 entrances of CAPTCHAs. In this experiments, we assume that each of the entrance is known. Results are provided showing how our algorithms work well towards these CAPTCHAs.

This paper address the problem of shadow detection and removal in traffic vision analysis. Basically, the presence of the shadow in the traffic sequences is imminent, and therefore leads to errors at segmentation stage and often misclassified as an object region or as a moving object. This paper presents a shadow removal method, based on both color and texture features, aiming to contribute to retrieve efficiently the moving objects whose detection are usually under the influence of cast-shadows. Additionally, in order to get a shadow-free foreground segmentation image, a morphology reconstruction algorithm is used to recover the foreground disturbed by shadow removal. Once shadows are detected, an automatic shadow removal model is proposed based on the information retrieved from the histogram shape. Experimental results on a real traffic sequence is presented to test the proposed approach and to validate the algorithm's performance.

Arabic handwritten documents present specific challenges due to the cursive nature of the writing and the presence of diacritical marks. Moreover, one of the largest labeled database of Arabic handwritten documents, the OpenHart-NIST database includes specific noise, namely guidelines, that has to be addressed. We propose several approaches to process these documents. First a guideline detection approach has been developed, based on K-means, that detects the documents that include guidelines. We then propose a series of preprocessing at text-line level to reduce the noise effects. For text-lines including guidelines, a guideline removal preprocessing is described and existing keystroke restoration approaches are assessed. In addition, we propose a preprocessing that combines noise removal and deskewing by removing line fragments from neighboring text lines, while searching for the principal orientation of the text-line. We provide recognition results, showing the significant improvement brought by the proposed processings.

This paper analyzes score normalization for keystroke dynamics authentication systems. Previous studies have shown that the performance of behavioral biometric recognition systems (e.g. voice and signature) can be largely improved with score normalization and target-dependent techniques. The main objective of this work is twofold: i) to analyze the effects of different thresholding techniques in 4 different keystroke dynamics recognition systems for real operational scenarios; and ii) to improve the performance of keystroke dynamics on the basis of target-dependent score normalization techniques. The experiments included in this work are worked out over the keystroke pattern of 114 users from two different publicly available databases. The experiments show that there is large room for improvements in keystroke dynamic systems. The results suggest that score normalization techniques can be used to improve the performance of keystroke dynamics systems in more than 20%. These results encourage researchers to explore this research line to further improve the performance of these systems in real operational environments.

A process of de-identification used for privacy protection in multimedia content should be applied not only for primary biometric traits (face, voice) but for soft biometric traits as well. This paper deals with a proposal of the automatic hair color de-identification method working with video records. The method involves image hair area segmentation, basic hair color recognition, and modification of hair color for real-looking de-identified images.

This paper describes Smartpig, an algorithm for the iterative mosaicking of images of a planar surface using a unique parameterization which decomposes inter-image projective warps into camera intrinsics, fronto-parallel projections, and inter-image similarities. The constraints resulting from the inter-image alignments within an image set are stored in an undirected graph structure allowing efficient optimization of image projections on the plane. Camera pose is also directly recoverable from the graph, making Smartpig a feasible solution to the problem of simultaneous location and mapping (SLAM). Smartpig is demonstrated on a set of 144 high resolution aerial images and evaluated with a number of metrics against ground control.

The TRECVID report of 2010 [14] evaluated video shot boundary detectors as achieving "excellent performance on [hard] cuts and gradual transitions." Unfortunately, while re-evaluating the state of the art of the shot boundary detection, we found that they need to be improved because the characteristics of consumer-produced videos have changed significantly since the introduction of mobile gadgets, such as smartphones, tablets and outdoor activity purposed cameras, and video editing software has been evolving rapidly. In this paper, we evaluate the best-known approach on a contemporary, publicly accessible corpus, and present a method that achieves better performance, particularly on soft transitions. Our method combines color histograms with key point feature matching to extract comprehensive frame information. Two similarity metrics, one for individual frames and one for sets of frames, are defined based on graph cuts. These metrics are formed into temporal feature vectors on which a SVM is trained to perform the final segmentation. The evaluation on said "modern" corpus of relatively short videos yields a performance of 92% recall (at 89% precision) overall, compared to 69% (91%) of the best-known method.