Anuja Dharmaratne

3D Face Reconstruction from 2D Images

This paper surveys the topic of 3D face reconstruction using 2D images from a computer science perspective. Various approaches have been proposed as solutions for this problem but most have their limitations and drawbacks. Shape from shading, shape from silhouettes, shape from motion and analysis by synthesis using morphable models are currently regarded as the main methods of attaining the facial information for reconstruction of its 3D counterpart. Though this topic has gained a lot of importance and popularity, a fully accurate facial reconstruction mechanism has not yet being identified due to the complexity and ambiguity involved. This paper discusses about the general approaches of 3D face reconstruction and their drawbacks. It concludes with an analysis of several implementations and some speculations about the future of 3D face reconstruction.

FaceID: A 3D computer graphic application for forensic medicine: A novel semi-automated muscle based digital sculpting initiative for forensic facial reconstruction in Sri Lanka

The field of medicine has integrated with law and regulation in the form of forensic medicine. While the field of medicine, as a whole, is leaping forward by integrating computer solutions, Forensic Medicine- particularly in developing regions such as Sri Lanka- is lacking innovative computer integrations. The process of forensic facial reconstruction in particular, is still at its infancy in Sri Lanka, and is yet to utilize the advanced technologies of other countries. Hence introducing a more efficient multimedia based technique to the local forensic officials in order to improve the efficiency and the accuracy of the reconstructions is the aim of this study. In contrast to the facial reconstructions conducted in other countries, this study introduces a novel semi-automated method of computer aided digital sculpting to the field of forensic medicine. The adopted process involved, acquiring a 3D model of the skull and digitally sculpting muscles in a 3D environment, followed by adding different facial features to improve identification. The research also encompassed a tissue thickness analysis and a facial component analysis, both of which were conducted for the first time on Sri Lankans since both were needed to improve the accuracy of the final output. This procedure was attempted on cases of the age category 20–30 and of medium weight. The outputs and the process were evaluated with different parties such as general public, forensic officials, lawyers and CID all of which yielded true positive results. The ultimate goal of conducting the study was to understand and overcome the challenges faced in developing this novel application for the Sri Lankan Forensic officials and to establish the first unit for facial reconstruction in Sri Lanka.

A Tool for Ranking and Enhancing Aesthetic Quality of Paintings

Measuring aesthetic value of an artwork is a significant task in the field of visual & performing arts. Artists follow several techniques manually using traditional methods to balance the visual aesthetic value of different aesthetic products such as a film, a drama, a painting etc. Today, artists are enthusiastic on emerging information technology techniques for judgment and enhancement of designed product aesthetically and efficiently while applying traditional concepts to design initial form of the artwork. Computational aesthetics is the research of computational methods that do make applicable aesthetic decisions in a similar fashion as human can. This paper introduces a new tool that can be used to rank a given digital image of paintings based on a common parameter set with their weighting factors which are supposed to be adjusted for changing the aesthetic level of a particular painting in the area of computational aesthetics.

Taxonomy of File Fragments Using Gray-Level Co-Occurrence Matrices

Researches up to data have focused on using non texture based methods in addressing the problem of classifying the data types of file fragments. In this research we considered a file fragment as a 8 bit grayscale image and the Gray Level Co-Occurrence Matrix (GLCM) based method was used to extract textural features. Texture features for fragment dimensions 8 × 8, 16 × 16, 32 × 32 and 64 × 64 and gray level quantizations from 4 to 64 with step increments of 4 were explored. The K nearest neighbor classifier was used as the classifier and the optimal GLCM features for a particular gray level and fragment dimension were determined using Sequential Forward Selection (SFS) algorithm. On the classification of 7 data types, our novel approach reached a maximum overall accuracy of 86.86% in classifying 64 × 64 sized fragments with 12 gray levels.

A New Approach for Object Boundary Detection and Identification

This paper introduces a new boundary detection technique, named rotating line scanning, which can be considered as a boundary growing methodology. Some image enhancement techniques are also introduced which were used to make it possible to work correctly. Image enhancement techniques used in this method do not include any kind of smoothing and as a result the preprocessed image remains as sharp as the original. This technique has a number of parameters that can be tuned to achieve the desired result according to the situation. Using these parameters the algorithm can detect individual objects or a system of objects at once. All the algorithms used in the research consume very less computing power by nature.

Aging Progression of Elderly People Using Image Morphing.

Aging is an inevitable process and its effects cause major variations in the appearance of human faces. Human face identification has a significant amount of information depend on his age, gender, ethnicity and etc. In addition, facial expression and facial gestures often reveal the emotional state of an individual. Consequently human facial analysis has received considerable attention and has led to the development of novel approaches to perform face recognition, facial expression characterization, face modeling, etc. Facial aging is attributed by changes in facial features, shape and texture and other biological factors like weight loss/gain, facial hair, etc. Age seems to be the main cause of the facial change and it has become forefront. Human life cycle can be classified in to four main stages with the age. Those are babies, children, young adults and elderly. Significant amount of facial changes can be identified in each of these stages. This paper introduces a methodology for elderly facial shape changes, hairlines recede and hair colour change using image morphing.