25 research outputs found
What is the average human face?
No full textThis paper examines the generation of a generic face model from a moderate sized database. Generic models of a human face have been used in a number of computer vision fields, including reconstruction, active appearance model fitting and face recognition. The model that is constructed in this paper is based upon the mean of the squared errors that are generated by comparing average faces that are calculated from two independent and random samplings of a database of 3D range images. This information is used to determine the average amount of error that is present at given height locations along the generic face based on the number of samples that are considered. These results are then used to sub-region the generic face into areas where the greatest variations occur in the generic face models
Human Face Reconstruction Using Bayesian Deformable Models
No full textThis paper presents a Bayesian framework for 3D facial reconstruction. The framework iteratively deforms a generic face mesh to fit a set of range points representing a face. The generic mesh is generated from the extensive FRGC database of face images. The deformation process is conducted within a Bayesian framework and is driven by a Markov Chain Monte Carlo (MCMC) sampler which uses information from the likelihood and prior distributions of the generic face mesh. The paper presents results on the construction of a generic face model, the deformation framework and fitting results to both synthetic and real data. The results verify the effectiveness of the proposed technique, accurately deforming a generic face mesh to captured 3D data points of human faces
Gaze based personal identification
No full textThis chapter describes the use of visual attention characteristics as a biometric for authentication or identification of individual viewers. The visual attention characteristics of a person can be easily monitored by tracking the gaze of a viewer during the presentation of a known or unknown visual scene. The positions and sequences of gaze locations during viewing may be determined by overt (conscious) or covert (sub-conscious) viewing behaviour. Methods to quantify the spatial and temporal patterns established by the viewer for both overt and covert behaviours are proposed. The former behaviour entails a simple PIN-like approach to develop an independent signature while the latter behaviour is captured through three proposed techniques: a principal component analysis technique (‘eigenGaze’); a linear discriminant analysis technique; and a fusion of distance measures. Experimental results suggest that both types of gaze behaviours can provide simple and effective biometrics for this application
Improved GrabCut segmentation via GMM optimisation
No full textSemi-automatic segmentation of still images has vast and varied practical applications. Recently, an approach "GrabCut" has managed to successfully build upon earlier approaches based on colour and gradient information in order to address the problem of efficient extraction of a foreground object in a complex environment. In this paper, we extend the GrabCut algorithm further by applying an unsupervised algorithm for modelling the Gaussian Mixtures that are used to define the foreground and background in the segmentation algorithm. We show examples where the optimisation of the GrabCut framework leads to further improvements in performance
Do Croatian Quoted Companies Satisfy IFRS Disclosure Requirements of Accounting Estimates for Investment Property?
No full textAbstractAccounting estimates occur because a large number of items in financial statements cannot be measured precisely but can only be estimated. Significant accounting estimates are disclosed in the notes to the financial statements. The aim of the paper was to identify whether Croatian quoted companies disclose all information about accounting estimates related to the Investment property, as required by IAS 40. The research included 132 quoted companies in Croatia that apply IFRSs. The research results showed that investment property has a relatively small share in the structure of total assets of quoted companies in Croatia, which is probably one of the reasons why related accounting estimates published in the notes are brief and incomplete. The general conclusion is that the notes regarding accounting estimates on investment property are composed of definitions set in the standard, instead of providing more transparent information for investors and other interested users of financial statements. As expected, the companies with the higher share of investment property have shown greater level of transparency, providing additional information which is not required by the standards
The Impact of Accounting Estimates on Financial Position and Business Performance – Case of Non-Current Intangible and Tangible Assets
No full textAbstractFinancial statements represent a great source of information for company's financial position and business performance evaluation. Management judgment depends on the information base which is given at the time of judgement. Each judgement is by its nature subjective, so the results of the estimation can differ. Non-current tangible and intangible assets represent a significant proportion of assets of many companies. There is a plenty of space for applying accounting estimates in order to recognise and measure such assets. The research model confirmed the volatility of financial condition and performance of a company as a result of different accounting estimates
