In the field of image processing, identifying object is based on appropriately chosen descriptors. The proper choice of descriptors in pattern recognition is the most sensitive criteria as small misjudgments may lead to wrong identification. There have been several algorithms proposed and worked in this field. Here, the idea is to identify the objects in an uncomplicated method while being computationally efficient. This paper is based on identifying the patterns of objects / polygons based on the recording area of the objects per line scan. The descriptors here are invariant to translation and become invariant to scaling after normalization. Here the objects considered are regular polygons in various background conditions. In order to reduce the noise, after segmentation by thresholding along with labeling and area filtering is done. Along with polygon identification, descriptors for all the numbers are also shown. In order to identify the objects, the average magnitude difference function (AMDF) is applied to each characteristic curve. This paper also shows that though AMDF is a dissimilarity measure, it works better here than auto correlation function (ACF), which is a similarity measure.

Drowsy driving is one of the major causes of road accidents and death. Hence, detection of driver's fatigue and its indication is an active research area. Most of the conventional methods are either vehicle based, or behavioral based or physiological based. Few methods are intrusive and distract the driver, some require expensive sensors and data handling. Therefore, in this study, a low cost, real time driver's drowsiness detection system is developed with acceptable accuracy. In the developed system, a webcam records the video and driver's face is detected in each frame employing image processing techniques. Facial landmarks on the detected face are pointed and subsequently the eye aspect ratio, mouth opening ratio and nose length ratio are computed and depending on their values, drowsiness is detected based on developed adaptive thresholding. Machine learning algorithms have been implemented as well in an offline manner. A sensitivity of 95.58% and specificity of 100% has been achieved in Support Vector Machine based classification.

No abstract