Defect detection enhancement using Gaussian Sparse Models.

Detecting defects is critical in industrial fabrication, such as pipe welding, where radiography testing (RT) is the gold standard as a non-destructive method for monitoring weld quality and weld corrosion. The extraction of seamless information from radiographic images is critical for this approach. Image processing techniques can improve the quality of radiographic images by enhancing image contrast, especially in flawed regions. In this study, a method based on Gaussian mixture models was implemented and applied to radiographs of welded objects to improve visualization and detectability. In the Sparse Coding and Gaussian Scale Mixture method (SSC-GSM), the local image patches are described as a mixture of Gaussian distributions. Given the different levels of noise in the individual images, the background was determined and subtracted from each original image. The results show that the proposed techniques can maintain and improve the edge information in radiographs and defective regions. The density of pixels along the analyzed profile lines has yielded enhancement by a factor of approximately two for the reconstructed images as compared to the original images. We tested the SSC-GSM method on GD-Xray database with 68 radiographs of the weld. In total, the SSC-GSM technique can improve the contrast of radiography image by back ground removal method and show the defects better that exist in weld radiographs, compared to traditional method for the detection of weld defects.

The effects of fatigue on synergy of selected lower limb muscles during running.

The purpose of this study was to investigate the effect of fatigue on selected lower extremity muscles synergy during running using non-negative matrix factorization algorithm method. Sixteen male recreational runners participated in this study. The surface electromyographic activity of rectus femoris (RF), vastus lateralis (VL), vastus medialis (VM), biceps femoris (BF), semitendinosus, gastrocnemius medialis (GM), soleus (SO) and tibialis anterior (TA) were recorded on treadmill at 3.3 m s-1 before and after the fatigue protocol. Synergy pattern and relative muscle weight were calculated by non-negative matrix factorization (NNMF) algorithm method. The results showed that using the VAF method, five muscle synergies were extracted from the emg data during running. After the fatigue, the number of muscular synergies did not show a change, but relative weight of the muscles changed. Fatigue did not have any effect on the structure of muscular synergy, but changed the relative weight of muscles. These changes could be the strategy of the central nervous system to maintain optimal function of the motor system.