scanchars.py 文件源码

def splitimage(image):
    dpmm = min(image.shape[0:2]) / DOCSIZE[0]
    sizethresh = SIZE_THRESH_MM * dpmm

    uprightimg = makeupright(image)
    grayimg = getgrayimage(uprightimg)

    # top line
    top = grayimg[0,:]
    sepx = [0,]
    ret, binimg = cv2.threshold(top,0,255,cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)
    nlabels, labels, stats, centroids = cv2.connectedComponentsWithStats(binimg)
    for i in range(1,nlabels):
        if stats[i,cv2.CC_STAT_AREA] >= sizethresh:
            sepx.append(centroids[i][1])

    # left line 
    left = grayimg[:,0]
    sepy = [0,]
    ret, binimg = cv2.threshold(left,0,255,cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)
    nlabels, labels, stats, centroids = cv2.connectedComponentsWithStats(binimg)
    for i in range(1,nlabels):
        if stats[i,cv2.CC_STAT_AREA] >= sizethresh:
            sepy.append(centroids[i][1])

    # divide into images
    imgs = []
    for iy in range(len(sepy)):
        for ix in range(len(sepx)):
            if iy == len(sepy) - 1:
                if ix == len(sepx) - 1:
                    #right-bottom corner
                    imgs.append(uprightimg[int(sepy[iy]):,int(sepx[ix]):])
                else:
                    #bottom end
                    imgs.append(uprightimg[int(sepy[iy]):,int(sepx[ix]):int(sepx[ix+1])])
            else:
                if ix == len(sepx) - 1:
                    #right end
                    imgs.append(uprightimg[int(sepy[iy]):int(sepy[iy+1]),int(sepx[ix]):])
                else:
                    #others
                    imgs.append(uprightimg[int(sepy[iy]):int(sepy[iy+1]),int(sepx[ix]):int(sepx[ix+1])])

    return imgs