Hierarchic Clustering-Based Face Enhancement for Images Captured in Dark Fields

A hierarchic clustering-based enhancement is proposed to solve the luminance compensation of face recognition in the dark field. First, the face image is divided into five levels by a clustering method. Second, the results above are mapped into three hierarchies according to the histogram thresholds. A low, a middle, and a high-intensity block are found. Third, two kinds of linear transforms are performed to the high and the low-intensity blocks. Finally, a center wrap function-based enhancement is carried out. Experiment results show our method can improve both the face recognition accuracy and image quality.

Quality Controlled EMG Signal Compression using Linear and Non Linear Transforms

In today’s era of telemedicine, data and graphical records are required to be transmitted over noisy, power limited and band limited channels. The effective compression is the best alternate to save time and bandwidth. For Electromyogram (EMG) signal, that are huge in data size, must be compressed in such a way so that can be recovered with minimum alterations. This work focused on the tuneable method to compress EMG signals, with linear and non linear transforms. The analysis is based upon compression factor (CF) and percentage root mean square difference (PRD). The results helps to conclude that non linear transform method have precedence over the linear transforms for almost entire range of user defined PRD (UPRD)