4fi5 发布的帖子

支持在openmv运用svm或者决策树这两种方法进行机器学习吗

模板匹配能搭配滤波处理和边缘检测吗，为什么我在多模板匹配里面加了中值滤波处理后运行没问题，但不进行模板匹配了

import time, sensor, image
from image import SEARCH_EX, SEARCH_DS

# 初始化传感器和设置
sensor.reset()
sensor.set_contrast(1)
sensor.set_gainceiling(16)
sensor.set_framesize(sensor.QQVGA)
sensor.set_pixformat(sensor.GRAYSCALE)

# 模板列表
templates = [
    "/0.pgm", "/1.pgm", "/2.pgm", "/3.pgm", "/4.pgm",
]

# ROI列表
roi_list = [(10, 0, 40, 40)] * len(templates)
sensor.skip_frames(time = 2000) # 让新的设置生效
clock = time.clock() # 跟踪FPS帧率

while(True):
    clock.tick() # 追踪两个snapshots()之间经过的毫秒数.
    img = sensor.snapshot() # 拍一张照片，返回图像

    # 第一个参数是内核大小。N对应于((N * 2)+1)^ 2内核大小。
    # 例如。 1 == 3x3内核，2 == 5x5内核等。

    # 第二个参数“percentile”是从NxN邻域中选择的百分位数。
    # 0.5是中位数，0.25是下四分位数，0.75是上四分位数。
    img.median(1, percentile=0.5, threshold=True, offset=5, invert=True)
# 添加中值滤波预处理
def apply_median_blur(image, kernel_size=3):
    return image.median_blur(kernel_size)

clock = time.clock()

while True:
    clock.tick()

    # 捕获图像
    img = sensor.snapshot()

    # 对图像进行中值滤波预处理
    img = apply_median_blur(img)

    char_positions = []  # 存储字符及其位置

    for t, roi in zip(templates, roi_list):
        template = image.Image(t)
        r = img.find_template(template, 0.70, step=3, search=SEARCH_DS, roi=roi)
        if r:
            img.draw_rectangle(r)
            char_positions.append((t[1], r[0]))  # 使用模板文件名的第一个字符作为字符标识

    # 检查是否有至少三个字符被识别
    if len(char_positions) > 2:  
        # 按水平位置排序
        char_positions.sort(key=lambda x: x[1])

        # 将排序后的字符打印出来
        result = ''.join([char for char, _ in char_positions])
        print("识别结果:", result)

你好，同样的数据集我之前也在星瞳上面训练了，准确率部署到上面同样不太行，请问是要怎样上传数据你可以看见

# Edge Impulse - OpenMV Image Classification Example

import sensor, image, time, os, tf, uos, gc

sensor.reset()                         # Reset and initialize the sensor.
sensor.set_pixformat(sensor.RGB565)    # Set pixel format to RGB565 (or GRAYSCALE)
sensor.set_framesize(sensor.QVGA)      # Set frame size to QVGA (320x240)
sensor.set_windowing((240, 240))       # Set 240x240 window.
sensor.skip_frames(time=2000)          # Let the camera adjust.

net = None
labels = None

try:
    # load the model, alloc the model file on the heap if we have at least 64K free after loading
    net = tf.load("trained.tflite", load_to_fb=uos.stat('trained.tflite')[6] > (gc.mem_free() - (64*1024)))
except Exception as e:
    print(e)
    raise Exception('Failed to load "trained.tflite", did you copy the .tflite and labels.txt file onto the mass-storage device? (' + str(e) + ')')

try:
    labels = [line.rstrip('\n') for line in open("labels.txt")]
except Exception as e:
    raise Exception('Failed to load "labels.txt", did you copy the .tflite and labels.txt file onto the mass-storage device? (' + str(e) + ')')

clock = time.clock()
while(True):
    clock.tick()

    img = sensor.snapshot()

    # default settings just do one detection... change them to search the image...
    for obj in net.classify(img, min_scale=1.0, scale_mul=0.8, x_overlap=0.5, y_overlap=0.5):
        print("**********\nPredictions at [x=%d,y=%d,w=%d,h=%d]" % obj.rect())
        img.draw_rectangle(obj.rect())
        # This combines the labels and confidence values into a list of tuples
        predictions_list = list(zip(labels, obj.output()))

        for i in range(len(predictions_list)):
            print("%s = %f" % (predictions_list[i][0], predictions_list[i][1]))

    print(clock.fps(), "fps")