Category: Uncategorized

PGRs Research Presentations – May 2013

Amr Ahmed / / Uncategorized

The May’s PGRs Research Presentations was held on Wed. 8th May, 2pm, Meeting Room, MC3108 (3rd floor).

This session we had the following presentations:

Title: “Automatic Phonetization of Holy Quran Text to build Arabic phonetic corpus“. Title:   “Understanding the correlation between the personalities of video game players and the decisions they make in a game environment; using action analysis and personal temperament profiling techniques to expand game design theory.”

By: Belal Al-Daradkah

By: Samuel Battye
Abstract:The large vocabulary phonetic corpus is an essential component of speech processing application. This research is to build an Arabic phonetic corpus from the Holy Quran text. This will be the base of developing Text-to-Speech (TTS) and Large Vocabulary Speech Recognition (LVSR) . The corpus will be built on a phonetic dictionary generated automatically by using Arabic pronunciation rules of Arabic language and Tajweed rules. Abstract: As more people become video game players, due to the vast expanse of the gaming industry, there are more player personalities than ever in the gaming environment. Different kinds of players often conflict with one another in multiplayer environments as diverse and varied play-styles emerge. Using temperament profiling techniques, game design theory and a player decision oriented game, this project looks at understanding how these vast ranges of personalities interact, and how innovative game design can be used to create games that accommodate as many different kinds of video game players as possible, while increasing a user’s enjoyment by reducing player to player conflict.

The Q/A was followed by a brief cath-up meeting with update on the latest procedures.

 

PGRs Research Presentations – April 2013

Amr Ahmed / / Uncategorized

The April’s PGRs Research Presentations was held on Wed. 10th April, 2pm, Meeting Room, MC3108 (3rd floor).

In this session we had the following presentations:

Title: “Analysis of Wing Beat Frequency using Computer Vision Techniques“.

By: John Atanbori

Abstract:Computer vision techniques have been used extensively to automatically monitor human activities; however applications for analysing animal behaviour are sparse. The analysis of bat behaviour in particular has attracted only one or two studies. Most existing work uses either expensive thermal imaging equipment, or bespoke sensors which are not accessible to field researchers, ecologists, and scientists studying behaviour. The work we present here uses spectral analysis techniques to quantify wing beat frequency, using a single imaging device in low-light. We then propose two improved techniques based on bounded box metrics and similarity matrices for measuring periodic and cyclical motion as a 1D time domain signal and transforming them to the frequency domain using Short Time Fourier Transform (STFT). Finally we evaluate these techniques against a baseline algorithm proposed by Cutler and Davis, using expert-annotated ground-truth data.  

The Q/A was followed by a meeting discussing various aspects, including the available PG courses (from the Graduate School and others), PG week, PG Conference, potential PG Showcase Event,……etc.

 

 

PGRs Research Presentations – March 2013

Amr Ahmed / / Uncategorized

The March’s PGRs Research Presentations was held on Wed. 13th March, 2pm, Meeting Room, MC3108 (3rd floor).

This session we had the following presentations:

Title: “A primal-dual fixed point algorithm with nonnegative constraint for CT image
reconstruction“.		 Title:   “Video Similarity in Compressed Domain”

By: Yuchao Tang

By: Saddam Bekhet
Abstract:Computed tomography (CT) image reconstruction problems often can be solved by finding the minimizer of a suitable objective function which usually consists of a data fidelity term  and a regularization term  subject to a convex constraint set $C$. In the unconstrained case, an efficient algorithm called the  primal-dual fixed point algorithm (PDFP$^{2}$O) has recently been developed to this problem, when the data fidelity term is differentiable with Lipschitz
continuous gradient and the regularization term composed by a simple convex function (possibly non-smooth) with a linear transformation. In this paper, we propose a modification of the PDFP$^{2}$O, which allows us to deal with the constrained minimization problem. We further propose accelerated algorithms which based on the Nesterov’s accelerated method. Numerical experiments on image reconstruction benchmark problem show that the proposed algorithms can produce better reconstructed image in signal-to-noise ratio than the original PDFP$^{2}$O and state-of-the-art methods with less iteration numbers. The
accelerated algorithms exhibit the fastest performance compared with all the other algorithms		 AbstractThe volume of video data is rapidly increasing, more than 4 billion hours of video are being watched each month on YouTube and more than 72 hours of video are uploaded to YouTube every minute, and counters are still running fast. A key aspect of benefiting from all that volume of data is the ability to annotate and index videos, to be able to search and retrieve them. The annotation process is time consuming and automating it, with semantically acceptable level, is a challenging task.The majority of available video data exists in compressed format MPEG-1, MPEG-2 and MPEG-4. Extraction of low level features, directly from compressed domain without decompression, is the first step towards efficient video content retrieval. Such approach avoids expensive computations and memory requirement involved in decoding compressed videos, which is the tradition in most approaches. Working on compressed videos is beneficial because they are rich of additional, pre-computed, features such as DCT coefficients, motion vectors and Macro blocks types.

The DC image is a thumbnail version that retains most of the visual features of its original full image. Taking advantage of the tiny size, timeless reconstruction and richness of visual content, the DC image could be employed effectively alone or in conjunction with other compressed domain features (e.g. AC coefficients, macro-block types and motion vectors) to represent video clips (with signature) and to detect similarity between videos for various purposes such as automated annotation, copy detection or any other higher layer built upon similarity between videos.

The Q/A was followed by a demonstration of the PGRs blog and discussion with PGRs (and attending staff) about the blog, BB community,…etc.

 

Amjad Altadmri – PhD

Amr Ahmed / / Uncategorized

Amjad Altadmri has passed his PhD viva, subject to minor amendments, earlier today.

Thesis Title:  “Semantic Video Annotation in Domain-Independent Videos Utilising Similarity and Commonsense Knowledgebases”

Thanks to the external, Dr John Wood from the University of Essex, the internal Dr Bashir Al-Diri and the viva chair, Dr Kun Guo.

Congratulations and Well done.

All colleagues are invited to join Amjad on celebrating his achievement, tomorrow (Thursday 28th Feb) at 12:00noon, in our meeting room MC3108, with some drinks and light refreshments available.

Best wishes.

 

February PGR Research Presentations

Amr Ahmed / / Uncategorized

The PGRs Research Presentations series has started on Wed. 13th Feb, 1pm, Meeting Room, MC3108 (3rd floor).

In each session we expect two PGR presentations. This session we had the following presentations:

 

Title: “A probabilistic approach   to Correctly and Automatically form of Retinal Vasculature“.

 Title:   “Semantic Video Analysis: from Camera Language to Human Language”

By: Touseef Qureshi

By: Amjad Altadmri
Abstract: 

Correct configuration and formation of   retinal vasculature is a vital step towards the diagnoses of these   cardiovascular diseases. A single minor mistake during the process of   connecting broken segments of vessels can lead to a completely incorrect   vasculature. Image processing techniques can’t alone solve this problem. On   the other hand, we are working on multidimensional scientific approach that   integrates Artificial intelligence, image process techniques, statistics and   probability. We are working and expecting an optimal approach towards the   correct configuration of broken vessels segments at junctions, bridges, and   terminals.

 Abstract 

The   rapidly increasing volume of visual data, available online or via   broadcasting, emphasizes the need towards building intelligent tools for   indexing, searching, rating, and retrieval. Textual semantic representations,   such as tagging, labeling and annotation, are often important parts of   videos’ indexing process, due to the advances in text analysis and their   intuitive user-friendly nature for representing semantics suitable for search   and retrieval.

 

Ideally,   this annotation should simulate the human cognitive way of perceiving and   describing videos. While these digital video mediums contain low-level visual   data, human beings have the ability to infer more meaningful information from   videos. The difference between these low-level contents and its corresponding   human perception is referred to as the “semantic gap”. This gap is even   harder to be handled in domain-independent uncontrolled videos, mainly due to   the lack of any previous information about the analyzed video on one side,   and the huge generic knowledge needed to be available on the other.