Eye Detection Morphological And Magnetic Field Mapping With Digital Image Processing

Abstract

Eye detection is required in many applications like eye-gaze tracking,iris detection, videoconferencing, auto-stereoscopic displays, face detection and face recognition. This paperproposes a novel technique for eye detection using color and morphological image processing. Itis observed that eye regions in an image are characterized by low illumination, high densityedges and high contrast as compared to other parts of the face. The method proposed is based on assumption that a frontal face image (full frontal) is available. Firstly, the skin region is detected using a color based training algorithm and six-sigma technique operated on RGB, HSV and NTSC scales. Further analysis involves morphological processing using boundary region detection and detection of light source reflection by an eye, commonly known as an eye dot. This gives a finite number of eye candidates from which noise is subsequently removed. Thistechnique is found to be highly efficient and accurate for detecting eyes in frontal face images.Optical position measurement system for an automated magnetic field mapping apparatus based on fluxgate sensors is presented. For the exact position estimation of the sensor head, a simple smart camera wasdeveloped with respect to minimal hardware configuration and real-time execution of position measurement algorithm. The camera is observing the mapped scene and evaluates position of the sensor head using an activemarker. The sensor head is designed as movable, what allows keeping the scene fixed and exactly referenced tothe mapped magnetic field using coordinates obtained from image. With image sensor fixed 2.5 m above the planeand range ±130 mm around the lens optical axis (image center), the total position measurement error is less than 0.5 mm.