Abstract: The disclosure provides an automatic geometric method for analyzing and recognizing human facial expressions based on extracted features using a neural network. The extracted features are obtained from extracted right eye, left eye and mouth using radial curves and Cubic Bezier curves. Facial expressions are classified into seven different emotion categories, namely surprise, happiness, disgust, neutral, fear, sadness and anger. The method employs an algorithm which hybridizes genetic algorithms (GA) and iterated local search (ILS) with back-propagation algorithm (BP). The BP is used to train the neural network. The GA and ILS are used to enhance and optimize initial weights of the BP.

Abstract: An apparatus and method for performing image segmentation. The method includes the steps of filtering an X-ray image of a jaw of a patient to reduce noise. Each image pixel is clustered into one of a lesion region and a background region. Further, the method transforms each pixel included in the clustered image into a neutrosophic domain determined by computing a three-tuple including a first probability corresponding to the pixel being correctly clustered in the lesion region, a second probability corresponding to the pixel being incorrectly clustered, and a third probability corresponding to the pixel being indeterminate, and iteratively computes the first probability, the second probability, and the third probability based on a mean value of pixel intensity of a predetermined window and a homogeneity value. The image is segmented by assigning the indeterminate pixels the lesion region or the background region based on a degree of pixel indeterminacy.

Abstract: The disclosure provides an automatic geometric method for analyzing and recognizing human facial expressions based on extracted features using a neural network. The extracted features are obtained from extracted right eye, left eye and mouth using radial curves and Cubic Bezier curves. Facial expressions are classified into seven different emotion categories, namely surprise, happiness, disgust, neutral, fear, sadness and anger. The method employs an algorithm which hybridizes genetic algorithms (GA) and iterated local search (ILS) with back-propagation algorithm (BP). The BP is used to train the neural network. The GA and ILS are used to enhance and optimize initial weights of the BP.