Haar-like的优势在于能更好的描述明暗变化,因此用于检测正面的人脸
HoG的优势在于能更好的描述形状,在行人识别方面有很好的效果
LBP比haar快很多倍,但是提取的准确率会低(10-20% 取决于训练对象)如果是嵌入式或者移动端的开发,推荐使用LBP。
这也解释了为什么haar应用于人的正面检测要明显好于应用于侧脸检测:正脸由于鼻子等凸起的存在,使得脸上的光影变化十分明显。而侧脸侧脸最重要的特征是形状和轮廓。 所以用HoG描述符检测侧脸更加有效。
It's important to look at the most prominent feature of pedestrians. There can be more than one prominent feature but the defining feature of a typical pedestrian is the outline, the legs and head shape. Hence the detection method that best captures or describes the pedestrian outline will ultimately solve the pedestrian detection problem more accurately. HoG features are capable of capturing the pedestrian or object outline/s
HoG的优势在于能更好的描述形状,在行人识别方面有很好的效果
LBP比haar快很多倍,但是提取的准确率会低(10-20% 取决于训练对象)如果是嵌入式或者移动端的开发,推荐使用LBP。
这也解释了为什么haar应用于人的正面检测要明显好于应用于侧脸检测:正脸由于鼻子等凸起的存在,使得脸上的光影变化十分明显。而侧脸侧脸最重要的特征是形状和轮廓。 所以用HoG描述符检测侧脸更加有效。
参考原文:
It's important to look at the most prominent feature of pedestrians. There can be more than one prominent feature but the defining feature of a typical pedestrian is the outline, the legs and head shape. Hence the detection method that best captures or describes the pedestrian outline will ultimately solve the pedestrian detection problem more accurately. HoG features are capable of capturing the pedestrian or object outline/s