Efficient Scale Invariant and Back Propagation Neural Network Method using LIP Region Segmentation

With the advent of technological sensor devices and human interface machine technology, there has been extensive research done in lip segmentation methods by several researchers — some linguistic features required for interaction with the machine equipment. Therefore, research work has been done in the audio speech detection scheme for recognition of lip reading. Visual lip reading technology developed based on the extraction of features of the lip. Lip segmentation is an essential approach to recognize lip reading scheme. Meanwhile, it helps to improve parameters. Several methods studied to segment the lip area based on localized active contour method using twice contour finding and combined color-space method. Apply the illumination histogram equalization to real color images to reduce the distortion of uneven illumination. The proposed method implemented can get better accuracy rate and segmentation results and compare with the existing process using area or circle as the region to segment grayscale images and combined in the color-space image. Using SIFT and BPNN, the inner region of the lip found in the result. The experiment tool is used MATLAB 2016a and designs a PROJECT APPLICATION. Improve the success rate and reduce the segmented error and compared with the current metrics. The experimental analysis determines the accuracy rate with 94%; error rate reduces with Segmented Error % and Overlap Error rate value with 79.73%.

Lip Segmentation Based on Combined Color Space and ACM with Rhombic Initial Contour

Lip segmentation is one of critical steps in a lip-reading system, because it closely relates to the accuracy of system recognition. In this paper, we aim to improve the accuracy of lip segmentation. A novel color space is proposed which consists of the [Formula: see text] component in the CIE-LUV space and the sum of [Formula: see text]2 and [Formula: see text]3 components of the image after discrete Hartley transform (DHT). We select a rhombus as the initial contour as its shape is approximate to a closed lip shape relatively. These notions are achieved based on the method of the Active contour model. The active contour model (ACM) is performed by the Chan–Vese model, and the result of each component is gained separately. Finally, the ultimate results are obtained by merging the result of each component together. Through experiments we can get a conclusion that this method can get more accurate and smoother lip contour. Meanwhile, the proposed method is more efficient compared with the classic ACM because it avoids some problems in the classic active contour model, like the radius of the initial contour needs to be set manually according to the size of images.