Search

Gait-based person identification suffers from the problem of different covariate factors such as clothing and carrying objects, which drastically reduce the recognition rate. Most existing methods capture dynamic and static information and remove the covariate factors without any systematic study. However, it has been reported in the literature that the head is one of the important features and the removal of the head from static information decreases the recognition rate. In our preliminary study, we developed a novel random walk (RW)-based gait extraction method that retains the head portion and removes certain static body parts to reduce the effect of covariate factors. The RW-based method is a novel gait feature extraction method and should be exploited more for its discriminative power to separate different body parts efficiently. However, the dynamic part is also significant in gait information, which is not very effectively represented in the RW-based gait extraction method. Therefore, a discrete Fourier transform (DFT)-based frequency component of the gait is considered to represent the dynamic part of gait information. Furthermore, we propose a novel gait recognition algorithm that fuses dynamic and static information from DFT- and RW-based representations. The proposed method systematically retains the discriminative static gait information along with the frequency attribute embedded as the dynamic gait information. Extensive experiments on the Chinese Academy of Sciences, Institute of Automation and the HumanID datasets have been carried out to demonstrate that the proposed fused gait features-based approach outperforms the existing methods, particularly when there are substantial appearance changes.

The use of biometrics has become a popular method to counter the threat of terrorism. Biometric features can be used to confirm identity (biometric authentication) or to identify an individual (biometric identification). Such features include physical (e.g. fingerprints and DNA) and behavioural characteristics (e.g. handwriting and gait). This paper is concerned with one type of behavioural characteristics, namely gait. Gait refers to an individual's style or manner of walk and thus represents one of the body language information signifiers that can identify individuals distinctively in surveillance videos. Recently, gait recognition for individual identification has received increased attention from biometrics researchers as gait can be captured at a distance by using a low-resolution camera. Human gait properties can be affected by clothing and the carrying of objects both of which have been identified within the existing literature as causing difficulties in gait recognition. In this paper, we propose ...

The term ‘steganography’ encapsulates the practice of secretly embedding data into digital mediums including video, image and audio files. Although steganography is often associated with nefarious activities, conceptually it asserts several characteristics that render it useful in contemporary security applications. Not just a mechanism for criminals to communicate secret information over a digital channel, steganography is also used as a legitimate method of ensuring integrity of digital media artefacts and for identification of same. This application of steganography allows for identification images storing additional information to verify both the identity of the subject as well as the authenticity of the image. Developed methods of steganography invoke various spatial domain techniques that are successful in covertly concealing data within ‘innocent’ carrier images. The techniques include linear methods such as those which replace the least significant bit (LSB) of the bytes in an image and frequency domain methods including discrete cosine transform (DCT), discrete wavelet transform (DWT) and discrete Fourier transform (DFT). The success of a steganographic algorithm is hinged on the method's ability to successfully embed data, so that the data remains concealed within a carrier image; and also to successfully extract the same data uncorrupted. Often modern image coding formats include lossy compression in the frequency domain; this can result in data loss, corruption and noise within the image when carrier images are re-encoded. To ensure data extraction is successful, error correction functions must be invoked to counteract noise and ensure embedded data is extracted without any loss or corruption. In exploring steganographic software, the functionality and reliability of a novel steganographic application ‘Intelligent Identity Authenticator’ (IIA) was assessed. IIA invokes the use of steganography to conceal real-time identity information within images on identity cards. The functionality of IIA is based on a unique algorithm that utilizes DWT to embed a string of characters within an identity image. When data is extracted, it provides a link to further documentation relating to the data subject, allowing for verification of the claimant's identity and authenticity of the identity card. The embedding and extraction functions executed by IIA were found to be mostly reliable, except where data had been embedded within a carrier image that was characterized by a large proportion of black pixels. In these cases, the extracted data string experienced significant loss and corruption, thus preventing access to the identity verification documentation. This paper explores the potential cause of this specific corruption and discusses extensive testing conducted on control images. The results are analysed to identify an improved solution that could rectify the issue, with an aim to improving both the functionality and reliability of the IIA system.

A reliable human skin detection method that is adaptable to different human skin colours and illu- mination conditions is essential for better human skin segmentation. Even though different human skin colour detection solutions have been successfully applied, they are prone to false skin detection and are not able to cope with the variety of human skin colours across different ethnic. Moreover, existing methods require high computational cost. In this paper, we propose a novel human skin de- tection approach that combines a smoothed 2D histogram and Gaussian model, for automatic human skin detection in colour image(s). In our approach an eye detector is used to refine the skin model for a specific person. The proposed approach reduces computational costs as no training is required; and it improves the accuracy of skin detection despite wide variation in ethnicity and illumination. To the best of our knowledge, this is the first method to employ fusion strategy for this purpose. Qualitative and quantitative results on three standard public datasets and a comparison with state-of-the-art methods have shown the effectiveness and robustness of the proposed approach., Accepted in IEEE Transactions on Industrial Informatics, vol. 8(1), pp. 138-147, new skin detection + ground truth (Pratheepan) dataset

Two approaches are described that improve the efficiency of optical flow computation without incurring loss of accuracy. The first approach segments images into regions of moving objects. The method is based on a previously defined Galerkin finite element method on a triangular mesh combined with a multiresolution segmentation approach for object flow computation. Images are automatically segmented into subdomains of moving objects by an algorithm that employs a hierarchy of mesh coarseness for the flow computation, and these subdomains are reconstructed over a finer mesh on which to recompute flow more accurately. The second approach uses an adaptive mesh in which the resolution increases where motion is found to occur. Optical flow is computed over a reasonably coarse mesh, and this is used to construct an optimal adaptive mesh in a way that is different from the gradient methods reported in the literature. The finite element mesh facilitates a reduction in computational effort by enabling processing to focus on particular objects of interest in a scene (i.e. those areas where motion is detected). The proposed methods were tested on real and synthetic image sequences, and promising results are reported.

The Internet is a widely open source to everyone to access Web pages. Using a web browser anyone can access websites. Because of this facility people can easily download images from websites without the owner's knowledge and use them in their own documents. Also image content may be modified for illegal purposes. Therefore a system is needed to authenticate images over the Web. Web image authentication is a challenging task that requires web crawlers to track and download images for authentication. Most of the known web image tracking engines such as Tin Eye and PicScout retrieve images according to the image infringement of the original image. However, these systems do not have the facility to authenticate the retrieved image, i.e. whether the retrieved image is similar to the original image or any image content alteration has occurred in the retrieved image and who is the copyrighted owner of the retrieved image. In order to solve the above mentioned drawbacks this paper presents a framework to protect image content, track it over the internet and authenticate the content. The proposed framework is based on self-embedding (i.e. where secret data and a binary version of the image are encrypted and embedded into the image), tracking (i.e. where a web crawler traverses over the internet to download images) and self-authentication (i.e. where the binary version of the hidden data is extracted to authenticate the image). Also another advantage of the proposed system is that it does not need the original image for the authentication process.

In this paper, the concept of object-oriented embedding (OOE) is introduced into information hiding in general and particularly to steganography which is the science that involves undetectable communication of secret data in an appropriate multimedia carrier. The proposal takes advantage of computer vision to orient the embedding process. Although, any existing algorithm can benefit from this technique to enhance its performance against steganalysis attacks, however this work also considers a new embedding algorithm in the wavelet domain using the Binary Reflected Gray Code (BRGC). In the realm of information hiding, one wing focuses on robustness, i.e., watermarking, and another wing focuses on imperceptibility, i.e., steganography. This work advocates for a new steganographic model that meets both robustness as well as imperceptibility. Resilience against common steganalysis attacks including the 274-D merged Markov and DCT features while surviving various image processing manipulations are reported. A neural network classifier was trained with features derived from 400 images. Comparisons with existing systems will also be highlighted.

The human visual system demonstrates powerful image processing functionalities. Inspired by the principles from neuroscience, a spiking neural network is proposed to perform the discrete cosine transform for visual images. The structure and the properties of the network are detailed in this paper. Simulation results show that the network is able to perform the discrete cosine transform for visual images. Based on this mechanism, the key features can be extracted in ON/OFF neuron arrays. These key features can be used to reconstruct the visual images. The network can be used to explain how the spiking neuron-based system can perform key feature extraction. The differences between the discrete cosine transform and the spiking neural network transform are discussed.

Recently, gait recognition for individual identification has received increased attention from biometrics researchers as gait can be captured at a distance using low-resolution capturing device. Human gait properties can be affected by different clothing and carrying objects (i.e. covariate factors). Most of the literature shows that these covariate factors give difficulties for individual identification based on gait. In this paper, we propose a novel method that generates dynamic and static feature templates of the sequences of silhouette images (Dynamic Static Silhouette Templates (DSSTs)) to overcome this issue. Here the DSST is calculated from Motion History Images (MHIs). The experimental results show that our method overcomes issues arising from differing clothing and the carrying of objects.

This paper presents a method for detection of humans in video sequences. The intended application of the method is outdoor surveillance. In such an uncontrolled environment, the appearance of humans varies hugely due to clothing, identity, occluding accessories (such as briefcases, shopping bags). Also we can have partial human appearances in video sequences. We are developing a system that can detect humans which are partially occluded in video sequences. Here we present some preliminary results.

Previous studies have shown that Steganography tools such as the S-Tools application outperforms counterpart tools in hiding data in the spatial domain. Another tool called F5 is identified as a robust tool in implementing Steganography in the frequency domain. This paper presents a Steganographic system which exploits the YCbCr colour space. YCbCr is intended to take advantage of human colour-response characteristics. Results show that our algorithm outperforms both F5 and S-Tools. Moreover, our system demonstrates improved performance in retrieving the hidden data after applying image processing attacks in the form of additive artificial noise. As a performance measurement for image distortion Peak-Signal-to-Noise Ratio (PSNR), which is classified under the difference distortion metrics, can be applied to the Stego images. This study also shows that by adopting an object oriented Steganography mechanism, in the sense that we track skin tone objects in video frames, we get a higher PSNR value.

The history of steganography can be traced back to ancient civilization - the Persian and Greek conflict around 480 B.C and ancient Egyptian civilization - when steganography was first reported to exist. Steganography is the process of hiding information in a multimedia carrier. Steganalysis, which is the official counter attack science, has defeated Steganographic algorithms whether they are based on the traditional spatial domain or the transform domain. This paper discusses the possibility of embedding data in the frames of video files. We call it adaptive as we select the specific region of interest (ROI) in the cover image where we can safely embed our data. We chose these regions based on human skin tone colour detection. As such the method is obviously constrained to image or video files with face instances present.

The computation of optical flow has been proposed as a pre-processing step for many high-level vision algorithms. One of the main approaches to the optical flow problem is the gradient-based approach which differentiates the image intensity to compute the optical flow. Often motion vectors computed using various approaches are not reliable. Spatial smoothing of the image sequence is advisable in order to improve velocity estimates in the presence of noise. That is, the application of some kind of linear operation to the images in the sequence before solving for the flow. The pre-processing typically takes the form of some type of spatial Gaussian smoothing or scale specific band-pass filtering of the input images. The main objectives of such filtering have been to lessen the effects of noise, to isolate image structure of interest and to attenuate temporal aliasing and quantization effects in the input images. This paper investigates the effect of presmoothing on this computation of optical flow. The well known method of Horn and Schunck as well as our own finite element method are implemented and tested for improvements due to presmoothing. Discussions are provided on the effects of presmoothing for a variety of image sequences. In our experiments, smoothing is carried out on a selection of well known sequences in both time and space. Improvements are shown using presmoothing.

The estimation of velocity has been proposed as a preprocessing step for many high-level vision algorithms for digital images. A new Galerkin inverse finite element approach is described for estimating velocity which uses an adaptive triangular mesh in which the resolution only increases where motion is found to occur. The mesh facilitates a reduction in computational effort by enabling processing to focus on particular objects of interest in a scene, specifically those areas where motion is detected without expending effort on computing flow for regions in which there is no motion. A confidence measure is calculated for the detected motion and if this measure passes a threshold then the motion is used for an adaptive mesh refinement process. The method is applied to real images where a significant part of the image is static. Results show that the adaptive framework estimates motion efficiently without loss of accuracy.

This paper develops techniques for the implementation of motion estimation. Gradient-based approaches compute the spatio-temporal derivatives, differentiating the image with respect to time and thus computing the optical flow field. Horn and Schunck's method in particular is considered a benchmarking algorithm of gradient-based differential methods, useful and powerful, yet simple and fast. They formulated an optical flow constraint equation from which to compute optical flow which cannot fully determine the flow but can give the component of the flow in the direction of the intensity gradient. An additional constraint must be imposed, introducing a supplementary assumption to ensure a smooth variation in the flow across the image. The brightness derivatives involved in the equation system were estimated by Horn and Schunck using first differences averaging. Gradient-based methods for optical flow computation can suffer from unreliability of the image flow constraint equation in areas of an image where local brightness function is non-linear or where there are rapid spatial or temporal changes in the intensity function. Little and Verri suggested regularization to help the numerical stability of the solution. Usually this takes the form of smoothing of the function or surface by convolving before the derivative is taken. The method proposed is a finite element method, based on a triangular mesh, in which diffusion is added into the system of equations to perform a type of smoothing while also retrieving the velocity. Quantitative and qualitative results are presented for real and synthetic images.© (2003) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

This chapter presents multiple methods for recognizing individuals from their “style of action/actions,” that is, “biometric behavioural characteristics.” Two forms of human recognition can be useful: the determination that an object is from the class of humans (which is called human detection), and the determination that an object is a particular individual from this class (which is called individual recognition). This chapter focuses on the latter problem. For individual recognition, this chapter considers two different categories. First, individual recognition using “style of single action,” that is, hand waving and partial gait, and second, individual recognition using “style of doing similar actions” in video sequences. The “style of single action” and “style of doing similar actions,” that is, behavioural biometric characteristics, are proposed as a cue to discriminate between two individuals. Nowadays, multibiometric security systems are available to recognise individuals from video sequences. Those multibiometric systems are combined with finger print, face, voice, and iris biometrics. This chapter reports multiple novel behavioural biometric techniques for individual recognition based on “style of single action” and “style of multiple actions” (i.e., analysing the pattern history of behavioural biometric motion), which can be additionally combined with finger print, face, voice, and iris biometrics as a complementary cue to intelligent security systems.

Recently, gait recognition for individual identification has received much increased attention from biometrics researchers as gait can be captured at a distance by using low-resolution capturing device. Human gait properties can be affected by various contexts such as different clothing and carrying objects. Most of the literature shows that these clothing and carrying objects (i.e. covariate factors) give difficulties for gait recognition. In this paper, we propose a novel method that generates dynamic and static feature templates of the sequences of silhouette images called Dynamic Static Silhouette Templates (DSSTs) to overcome this issue. Here the DSST is calculated from Gait Energy Images (GEIs). DSSTs capture the dynamic and static characteristics of gait. The experimental results show that our method overcomes the issues arising from differing clothing and the carrying of objects.

In intelligent surveillance systems, recognition of humans and their activities is generally the most important task. Two forms of human recognition can be useful: the determination that an object is from the class of humans (which is called human detection), and determination that an object is a particular individual from this class (this is called individual recognition). This paper focuses on the latter problem. For individual recognition, this report considers two different categories. First, individual recognition using "style of walk" i.e. gait and second "style of doing similar actions" in video sequences. The "style of walk" and "style of actions" are proposed as a cue to discriminate between two individuals. The "style of walk" and "style of actions" for each individual is called their "body language" information.

Motion estimation of a scene is an interesting problem in computer vision since it is the basis for the dynamic analysis of a scene. However this task is computationally intensive for conventional processors. In this work, an FPGA-based hardware architecture for real-time motion estimation is proposed. The algorithm implemented in hardware is a gradient based inverse finite element method for optical flow computation. It manages the motion estimation of the image by calculating the Gradient, Laplacian, and Velocities of each pixel in a parallel design which improves computational speed. The algorithm used in this paper has been benchmarked against many of the well known algorithms and shows superior performance in terms of average angular error and standard deviation. The FPGA design is presented with preliminary results and discussed.