import time, sensor, image,math,pyb
thresholds = (65, 9)
thresholdss = (0, 80)
from image import SEARCH_EX, SEARCH_DS
sensor.reset()
sensor.set_contrast(1)
sensor.set_gainceiling(16)
sensor.set_framesize(sensor.QQVGA)
sensor.set_pixformat(sensor.GRAYSCALE)
sensor.set_auto_gain(False)
sensor.set_auto_whitebal(False)
sensor.skip_frames(time = 2000)
template = image.Image("/fhy1.pgm")
clock = time.clock()

while (True):
    #for i in range(100):
    clock.tick()
    img = sensor.snapshot().lens_corr(1.8)  #畸变矫正
    #img.binary([thresholdss], invert = 1) #二值化
    
    零件 = img.find_template(template, 0.70, step=4, search=SEARCH_EX) #, roi=(10, 0, 60, 60))
    for r in img.find_blobs([thresholds], roi=[40,20,70,70],pixels_threshold=15, area_threshold=15, merge=False):
        #if r.pixels() >100 and r.pixels() <300:
        
            img.draw_rectangle(r.rect())
    
    if 零件:
        img.draw_rectangle(零件)
        print("检测到零件")
    
    
        if r:
            print("不合格")
        else:
            print("合格")![0_1683039656447_零件.png](https://fcdn.singtown.com/0f1cf444-87a0-4b03-a642-a490a84e7983.png) 

请问怎么检测零件上的缺口？

想用openmv筛选表面有瑕疵的次品，用什么功能实现？模板匹配或者特征点检测还是其他的？