Quantitative Analysis of Digital Image Stabilization

Image stabilization has become a subject of significant interest and an active research field over the past years due to the wide use of digital imaging devices. The image stabilization process aims at removing irregular motion phenomena from image sequences in order to accomplish a compensated sequence that displays smooth camera movements. A variety of image processing applications requires motion-compensated image sequences as inputs. The unwanted positional vacillations of the video sequence will affect the visual quality and impede the subsequent processes for several applications. An innovative technique for digital image stabilization (DIS) based on the HilbertHuang transform (HHT) is studied. It exploits the basic features of the HHT in order to separate the local motion signal obtained from an image sequence into two different motion vectors. A variety of embedded systems equipped with a digital image sensor, such as handheld cameras, mobile phones, and robots, can produce image sequences with an observed motion caused by two different types of movements: the smooth camera motion (intentional) and the unwanted shaking motion (jitter). To verify the effectiveness of the proposed DIS method, several simulations were performed, and the results were compared with existing stabilization methods. An attempt has been made for estimate Mean square error (MSE), peak signal to noise ratio (PSNR) and structural similarity index (SSIM) to study the performance of HHT-DIS and compared with other existing techniques and showed that HHT-DIS outperforms the existing methods.