caffe RandomHue和RandomSaturation

https://www.cnblogs.com/wangyblzu/p/5710715.html

HSV和RGB一样是一种图像的颜色模型,h表示色调,s表示饱和度

 1.RandomHue

void RandomHue(const cv::Mat& in_img, cv::Mat* out_img,
               const float hue_prob, const float hue_delta) {
  float prob;
  caffe_rng_uniform(1, 0.f, 1.f, &prob);
  if (prob < hue_prob) {
　　 以一定概率进行色调调整
    CHECK_GE(hue_delta, 0) << "hue_delta must be non-negative.";
    float delta;
    caffe_rng_uniform(1, -hue_delta, hue_delta, &delta);
    AdjustHue(in_img, delta, out_img);
  } else {
    *out_img = in_img;
  }
}

需要先把rgb图转成hsv图,然后对第一个通道也就是h的通道的每个值加上delta,最后再换转成rgb图

void AdjustHue(const cv::Mat& in_img, const float delta, cv::Mat* out_img) {
  if (fabs(delta) > 0) {
    // Convert to HSV colorspae.
    cv::cvtColor(in_img, *out_img, CV_BGR2HSV);

    // Split the image to 3 channels.
    vector<cv::Mat> channels;
    cv::split(*out_img, channels);

    // Adjust the hue.
    channels[0].convertTo(channels[0], -1, 1, delta);
    cv::merge(channels, *out_img);

    // Back to BGR colorspace.
    cvtColor(*out_img, *out_img, CV_HSV2BGR);
  } else {
    *out_img = in_img;
  }
}

2.RandomSaturation

void RandomContrast(const cv::Mat& in_img, cv::Mat* out_img,
    const float contrast_prob, const float lower, const float upper) {
  float prob;
  caffe_rng_uniform(1, 0.f, 1.f, &prob);
  if (prob < contrast_prob) {
    CHECK_GE(upper, lower) << "contrast upper must be >= lower.";
    CHECK_GE(lower, 0) << "contrast lower must be non-negative.";
    float delta;
    caffe_rng_uniform(1, lower, upper, &delta);
    AdjustContrast(in_img, delta, out_img);
  } else {
    *out_img = in_img;
  }
}

RandomSaturation做的是让通道里每个像素值乘以一个数,RandomHue是加一个数,这和 RandomBrightness和RandomContrast的区别是一样的

void AdjustContrast(const cv::Mat& in_img, const float delta,
                    cv::Mat* out_img) {
  if (fabs(delta - 1.f) > 1e-3) {
    in_img.convertTo(*out_img, -1, delta, 0);
  } else {
    *out_img = in_img;
  }
}