Feature subset selection is the process of choosing the variables that are important for the classification stage from the original feature space. Feature selection is an important task for almost any pattern recognition problem (Webb, 1999). This procedure is aimed to derive as many discriminative cues as possible whilst removing the redundant and irrelevant information which may degrade the recognition rate. Furthermore, feature selection does not only reduce the cost of recognition by reducing the dimensionality of the feature space, but also offers an improved classification performance through a more stable and compact representation (Jain 1982). It is practically infeasible to run an exhaustive search for all the  possible combinations of features in order to obtain the optimal subset for recognition due to the high dimensionality of the feature space.  For this reason, it is recommended to use a feature selection algorithm as  the Adaptive Sequential Forward Floating Selection (ASFFS)  search algorithm (Pudil 1994).

The feature selection procedure fundamentally relies on an evaluation function that determines the usefulness of each feature in order to derive the ideal subset of features for the classification phase. For every feature or set of features generated by the feature selection algorithm, an evaluation criterion is called to measure the discriminative ability of the set of features to distinguish different subjects (Dash 1997). A number of methods (Mowbray, 2003) rely mainly on statistical metric measures which are based on the scatter or distribution of the training samples in the feature space such as the Bhattacharyya metric. These methods aim to find the features which minimize the overlap between the different classes as well as the inner-class scatter.

Since the adaptive background subtraction lacks capability to remove shadows, it is recommended using the approach described by Cucchiara (2003) to evaluate whether a foreground pixel corresponds to cast shadow based on the Hue Saturation Value (HSV) colour information. The chromaticity and luminosity of the foreground pixels are separated using the HSV colour space which is proved to match the human perception of colour more closely than the RGB model (Herodotou, 1998). The method proposed by Cucchiara et al assumes that shadows reduce surface brightness and saturation while maintaining chromaticity properties in the HSV colour space.

The Harris corner detector is a popular interest point detector due to its invariance to rotation, scale as well as illumination variation and robustness to image noise. The Harris corner detector is based on the local auto-correlation function of a signal; where the local auto-correlation function measures the local changes of the signal with patches shifted by a small amount in different directions.

Surveillance technology is now ubiquitous in modern society.  This is due to  the increasing number of crimes as well as the vital need to provide a safer environment. Because of the rapid growth  of security cameras and incapability of manpower to supervise them, the deployment of biometric technologies becomes important for the development of automated visual surveillance systems. Recently, the use of gait for people identification in surveillance applications has attracted researchers from  computer vision.  The suitability of gait recognition for surveillance systems emerges from the fact that gait can be perceived from a distance as well as its non-invasive nature. Although gait recognition is still a new biometric and is not sufficiently mature to be deployed in real world applications such as visual surveillance, it overcomes most of the limitations that other biometrics suffer from such as face, fingerprints and iris recognition which can be obscured in most situations where serious crimes are involved.

Although people can discern the state of the subject from a single static image, motion pictures provide even more rich and reliable information for the perception of the different biological, social and psychological characteristics of the person such as emotions, actions and personality traits of the subject. This is because the acquired perceptual knowledge is encoded in the human motion. Furthermore, this notion was also observed by Darwin (1872) in his book “The Expression of Emotions in Man and Animals” where it was stated:

Actions speak louder than pictures when it comes to understanding what others are doing.

The human visual system is very sensitive to motion as it tends to focus attention on moving objects. In contrast to static or motionless objects, which are not as straightforward to detect. Motion is a spatio-temporal event defined as the change of spatial location over time. Given some visual input, the perception of motion is regarded as the process by which the visual system acquires perceptual knowledge about the speed and direction of the moving object. Whilst this process is spontaneous for the human visual system, it has proven to be extraordinarily difficult to duplicate this capability into computer vision systems.

  Thinking to start working on a setting up a web application like digg.com but instead for academic research papers and journals only. The site should function the same way as google scholar but with more rich features like voting, digging, posting questions and comments. The web application should be featured with a nice front page portal showing popular articles, latest papers and may be coming conferences or venues.

The idea looks goods to me and encouraging, but thinking money, time and effort wise. it will not be as profitable that much, plus more efforts and time should sacrificed for mining all the research papers from external sites as well as more work must be done for putting references and citations.

But if any one wants to go for it, there is a software called Pligg which you can hack and customize to your needs. For data  which is the most important, if you are that lazy you can write a search mining bot to crawl through google scholar or ieee explorer to get all of their data, but not sure of the legality issues!

Plus, the promotion of the site to academic people is extremely difficult unless you spend money telling them about the site and convince them to use it. But once it is in, it will keep up growing by itself.

Surveillance technology is now ubiquitous in modern society. This is due to the increasing number of crimes as well as the vital need to provide a safer environment. Because of the rapid growth of security cameras and incapability of manpower to supervise them, the deployment of biometric technologies becomes important for the development of an automated visual surveillance system. Recently, the use of gait for people identification in surveillance applications has attracted researchers from the arena of computer vision. The suitability of gait recognition for surveillance systems emerges from the fact that gait can be perceived from a distance as well as its non-invasive nature. Interestingly, in one of the high profile murder cases in the UK where a child was abducted and killed, the identity of the murderer could not be revealed directly from the surveillance video footage. The only solution that could be employed to determine the suspect’s identity in this situation was gait recognition, as proposed by researchers from the University of Southampton [Nixon, 2005]. However, gait as a biometric is still in its infancy and most of the gait recognition methods rely on body-related features.