A novel approach to automatic detection of interest points in multiple facial images
Journal Title: International Journal of Environment and Geoinformatics - Year 2017, Vol 4, Issue 2
Abstract
The human face includes different colors and forms due to its complexity. Therefore, facial image processing comprises even more problems than image processing of other objects. Interest point detection is one of the important problems in computer vision, which is the key aspect of solving problems such as facial expression analysis, age analysis, sex defining, facial recognition, and three-dimensional face modelling in augmented reality. To accomplish these tasks, facial interest points need automatic definition. A hybrid algorithm was developed to detect automatically interest regions and points in multiple images in the resented study. The study used processed facial images from an authorized image database with a resolution of 1600 x 1200, taken in standardized illumination conditions by using an InSpeck Mega Capturor II optical 3D structured light digitizer and 1000-W halogen lamp. The presented study integrated skin color analysis with the Haar classification method, processing 11 male and 25 female facial images with the developed algorithm. The average accuracy of facial interest point detection was 0.68 mm after testing all images.
Authors and Affiliations
Bülent Bayram, G. Çiğdem Çavdaroğlu, Dursun Zafer SEKER, Sıtkı Külür
Keywords
Related Articles
- EP ID EP198313
- DOI -
- Views 99
- Downloads 0
An Evaluation of Vanadium Enrichment in the Eastern Shelf Sediments of the Turkish Black Sea
This paper presents an evaluation of the spatial distribution of vanadium level, its enrichment and possible sources in the bottom sediment along the shelf of the Turkish Black Sea. In April 2006, vanadium concentrations...
Influence of Riverbed Change on a Possibility of Flooding During Water Level Rise of the River Kura
The study of floods by remote sensing data and GIS technology is necessary for the rapid detection of floods in the populated areas, provision of an early evacuation of the population and implementing correct response me...
3D Documentation of Archaeological Excavations Using Image-Based Point Cloud
Rapid progress in digital technology enables us to create three-dimensional models using digital images. Low cost, time efficiency and accurate results of this method put to question if this technique can be an alternati...
Statistical Analyses of Wave Height and Wind Velocity Distributions for the Sea of Marmara
The Sea of Marmara, a relatively small basin located between the Black Sea and the Aegean Sea with narrow seaways of the Bosphorus and the Dardanelles, has vital importance in coastal and ocean engineering activities due...
Importance and Vulnerability Analyses for Functional Zoning in a Coastal District of Turkey
Functional zoning of Akcakoca District located along the Western Black Sea Coast of Turkey is achieved by implementing the ‘Methodology for Spatial Planning for the Coastal Zone’ developed by European Union for coastal a...