Section 4 presents utilizing MLSR algorithm to achieve solder panel position determination.
Based on moving least square regression (MLSR) [25,26], we improve the least square fitting used in previous work  for more accurate and robust solder panel edge estimation.
According to the matrix E, use MLSR algorithm to update the initial edge line and acquire this turn edge line denoted as y(x).
After using MLSR algorithm, the final edge lines estimation result is shown in Figure 9.
Suppose that there are eight vertexes, ([wx.sub.1], [wy.sub.1]), ([wx.sub.2], [wy.sub.2]), ([wx.sub.3], [wy.sub.3]), ([wx.sub.4], [wy.sub.4]), ([wx.sub.5], [wy.sub.5]), ([wx.sub.6], [wy.sub.6]), ([wx.sub.7], [wy.sub.7]), and ([wx.sub.8], [wy.sub.8]); after using MLSR algorithm, the final refined edges are shown in Figure 10.
All experiments and comparisons under different background show that the proposed MLSR algorithm is efficient in solar panel position determination and edge lines estimation.
Moreover, MLSR algorithm is proposed to estimate the edge lines of solar panel and then to determine the panels' position.