Đang chuẩn bị liên kết để tải về tài liệu:
O’Reilly Learning OpenCV phần 5

với giá trị đã được chuyển thanh trượt, và số lượng, một số giá trị cho giá trị tối đa của thanh trượt. Đối số cuối cùng là một con trỏ đến một | Figure 7-9. Using cvCalcBackProjectPatchO to locate an object here a coffee cup whose size approximately matches the patch size white box in upper right panel the sought object is modeled by a hue-saturation histogram upper left which can be compared with an HS histogram for the image as a whole lower left the result of cvCalcBackProjectPatchO lower right is that the object is easily picked out from the scene by virtue of its color TêsoplatỄ Matching T emplate matching via cnMatchTemplate is notbased on histograms I c ltl e the functionmatches an ectuat ta iigt natch aatinot oninnut imapo Iby sladSag the pntbh aver ahe cupup impga using nc a of the matchtng methods described in this section. Kmin Figure F-hinWC have an image patch containing a face then we can slide that face over an input image looking for strong matches that would indicate another face is present. The function callis similar to that of cvCalcBackProjectPatch void wB PTanplatet const CrAic itkpr const CvArr tempi CvAn reruOt Ỉd-P meCBok t Instead of thearaay of input image planes that we saw in cvCalcBackProjectPatch here wehavs a single 8-bit or floating-point plane or color image as input. The matching model intend w fW a patch from a similar image containing the object for which IPP I CkmpPerB HistcgramsapeMctahinc Figure 7-10. cvMatchTemplateO sweeps a template image patch across another image looking for matches you are searching. The output object image will be put in the result image which is a single-channel byte or floating-point image of size images- width - patch_size.x 1 rimages- height - patch_size.y 1 as we saw previously in cvCalcBackProjectPatch . Hie match ingmethod is somewhat morecomplex as we now explain. We use I todenote the rnput image T the template and R the result. sqnare difference matching method method CV_TM_SQDIFF These methodsmatch the squared differenee so a perfeot match willbe 0 and bail malcdes will belhbge . tho Cortsletids mmtcN dd mef h hft mee otl Ct .