基于最大类间方差的Otsu改进图像二值化

int myOtsu(Mat & src, double &maxVal)
{
	int th;
	int GrayScale = round(maxVal) + 1;	//单通道图像总灰度maxVal+1级
	int *pixCount = (int*)malloc(sizeof(int)*GrayScale);//每个灰度值所占像素个数
	memset(pixCount, 0, sizeof(int)*GrayScale);
	int pixSum = src.cols * src.rows;//图像总像素点
	float *pixPro = (float*)malloc(sizeof(float)*GrayScale);//每个灰度值所占总像素比例
	memset(pixPro, 0, sizeof(float)*GrayScale);
	float w0, w1, u0tmp, u1tmp, u0, u1, deltaTmp, deltaMax = 0;

	for (int i = 0; i < src.cols; i++)
	{
		for (int j = 0; j < src.rows; j++)
		{
			int integel = round(src.at(j, i));
			pixCount[integel]++;//统计每个灰度级中像素的个数  
		}
	}

	for (int i = 0; i < GrayScale; i++)
	{
		pixPro[i] = pixCount[i] * 1.0 / pixSum;//计算每个灰度级的像素数目占整幅图像的比例  
	}

	for (int i = 0; i < GrayScale; i++)//遍历所有从0到GrayScale灰度级的阈值分割条件，测试哪一个的类间方差最大
	{
		w0 = w1 = u0tmp = u1tmp = u0 = u1 = deltaTmp = 0;
		for (int j = 0; j < GrayScale; j++)
		{
			if (j <= i)//背景
			{
				w0 += pixPro[j];
				u0tmp += j * pixPro[j];
			}
			else//前景
			{
				w1 += pixPro[j];
				u1tmp += j * pixPro[j];
			}
		}
		u0 = u0tmp / w0;
		u1 = u1tmp / w1;
		deltaTmp = (float)(w0 *w1* pow((u0 - u1), 2)); //类间方差公式 g = w1 * w2 * (u1 - u2) ^ 2
		if (deltaTmp > deltaMax)
		{
			deltaMax = deltaTmp;
			th = i;
		}
	}
	free(pixCount);
	free(pixPro);
	return th;
}