怎样把附件的133456读取出来，我用了多模板来识别，有问题，两个“3'都识别出来了，但是只有一个出现
-
import time, sensor, image,pyb from image import SEARCH_EX, SEARCH_DS from pyb import RTC #从imgae模块引入SEARCH_EX和SEARCH_DS。使用from import仅仅引入SEARCH_EX, #SEARCH_DS两个需要的部分，而不把image模块全部引入。 # Reset sensor sensor.reset() # Set sensor settings sensor.set_contrast(3) sensor.set_gainceiling(8) # Max resolution for template matching with SEARCH_EX is QVGA sensor.set_framesize(sensor.QVGA) # You can set windowing to reduce the search image. #sensor.set_windowing(((640-80)//2, (480-60)//2, 80, 60)) sensor.set_pixformat(sensor.GRAYSCALE) # Load template. # Template should be a small (eg. 32x32 pixels) grayscale image. templates = ["/0.pgm", "/1.pgm", "/2.pgm", "/3.pgm","/4.pgm", "/5.pgm", "/6.pgm", "/7.pgm","/8.pgm", "/9.pgm"] #保存多个模板 #加载模板图片 clock = time.clock() # Run template matching while (True): clock.tick() #每1s触发一次相机 time.sleep_ms(1000) img = sensor.snapshot() #相机拍照显示红色 led = pyb.LED(1) #亮灯 led.on() #亮灯3ms time.sleep_ms(3) led.off() for t in templates: template = image.Image(t) #对每个模板遍历进行模板匹配 r = img.find_template(template, 0.60,roi=(110,90,160,100), step=4, search=SEARCH_EX) #, roi1=(10, 0, 60, 60)) if r: img.draw_rectangle(r) print(t) #打印模板名字 #准备保存以时间命名的图片 rtc = pyb.RTC() dateTime = rtc.datetime() year = str(dateTime[0]) month = '%02d' % dateTime[1] day = '%02d' % dateTime[2] hour = '%02d' % dateTime[4] minute = '%02d' % dateTime[5] second = '%02d' % dateTime[6] subSecond = str(dateTime[7]) sensor.snapshot().save(year+month+hour+minute+second+".jpg") #保存照片显示绿色 # Red LED = 1, Green LED = 2, Blue LED = 3, IR LEDs = 4. led1 = pyb.LED(2) #亮灯 led1.on() #亮灯3ms time.sleep_ms(3) led1.off() #print(year+month+hour+minute+second) # print(clock.fps())
-
你同一秒检测出多个图片，文件名一样，不就覆盖了？
-
是的，那有没有一种方法可以快速达到OCR功能的，在每个字符位置建立独立的roi进行for循环搜素吗，那有没有带位置矫正功能的