Good news! just got “Accept for Oral Presentation” for the Mirage 2007. Mirage 2007 is an international conference with focus on Computer Vision/Computer Graphics collaboration techniques involving image analysis/synthesis approaches.The conference will be hosted at INRIA Rocquencourt in France

The Abstract of the paper is below:

Human motion analysis has received a great attention from researchers in the last decade due to its potential use in different applications. We propose a new approach to extract human joints (vertex positions) using a model-based method. Motion templates describing the motion of the joints as derived by gait analysis, are parametrized using the elliptic Fourier descriptors. The heel strike data is exploited to reduce the dimensionality of the parametric models. People walk normal to the viewing plane, as major gait information is available in a sagittal view. The ankle, knee and hip joints are successfully extracted with high accuracy for indoor and outdoor data. In this way, we have established a baseline analysis which can be deployed in recognition, marker-less analysis and other areas. The experimental results confirmed the robustness of the proposed method to recognize walking subjects with a correct classification rate of %92.

Planning to write a chat Software for providing Live Support through the Web. Machine learning algorithm will be used to design a bot which can be used to answer customer questions.

HaVing FuN with ProGramminG!

We just finished designing and building the supportUP.com website with Samir of AlgerianHosting.com. This joint venture is to offer outsource IT support to different companies including ISPs, and hosting providers. Backup solutions and system administration are also offered.

After being annoyed by spammer exploiting customers’ websites to send millions of spam emails. Sapmmers usually find holes ont he mal-coded software used by customers most of them are content management systems, guest books and contact us forms. The developed system wraps the sendmail linux tool with a script which would log all emails being send by the user ‘nobody’. The software then checks periodically any unusual activities in the log files, and if there is a spam detected, the abused or “abusing” account will be suspended.

The bad thing if we let spammers do their job is that IPs will be blacklisted by most ISP and email providers and therefore no legitmate email out, in addition to the legal notices and more headaches!

Human motion analysis has received a great attention from researchers in the last decade due to its potential use in different applications. This field of research focuses on the perception and recognition of human activities, including people identification. We have proposed a new method to extract human joints using a model-based method. the gait pattern is used to aid the extraction process, where model templates are established through the analysis of gait motion. Gait periodicity and other parameters are estimated through the finding of the heel strikes. The joints for the ankle, knee and hip are successfully extracted with high accuracy for an indoor data. In this way, we have established a baseline analysis which can be deployed in recognition, marker-less analysis and other areas.

The central aim of this seminal research work is to find the main features that mostly contribute to a gait signature. Principal Components Analysis is used to reduce the dimensionality of the data, which was obtained mainly via labelling. Canonical Analysis was then used to separate the projected data into predefined classes. K-nearest method is then applied to classify testing data in the canonical space. A Divide and Merge algorithm is derived to search for the best features that offer higher level of discriminability for gait signature, it is revealed that it is possible to achieve 100% CCR using only a set of 50 features which is a trade-off between noise and poor discriminability. The application of Fourier Frequencies Analysis revealed that the combination of the product of the magnitude and phase for the thigh and lower leg offer a discriminability capability to a gait identification system. Moreover, the Algorithm is extended to use of both selection criteria i.e. Correct Classification Rate and the Distribution J values, a better results is obtained using a set of only 20 features.

Never used C# as it is a new language which just came out or recame out when Microsoft put J++ under the table. So why not to try it for a project.
I have written a labeller software to be used for my research project. The system enables me extract the joint positions of walking subjects manually and export this data as a matlab file. This data is needed as the ground truth data to compare it with data automatically extracted by a model-based method.