我正在构建用于人脸识别的卷积神经网络 (CNN) 模型。
作为训练数据收集的第一步,哪种图像格式更适合训练,灰色还是 RGB?
我读过几篇文章说灰度图像最适合人脸识别,但没有得到令人满意的信息,为什么会这样?
对于这种方法,使用灰度相对于 RGB 有何优点和缺点?
对于人脸识别模型,是否需要有颜色信息,否则灰度转换后会丢失图像中的有用信息吗?
不同预测准确度有何不同?
最佳答案
我们不应该将人脸识别视为一个具体问题,还可以考虑图像分析的一般领域,特别是使用 CNN 时。
我们通常喜欢简化机器学习中的问题,以减少噪音和需要处理的数据量。
Simplicity - Many image processing operations work on a plane of image data (e.g., a single color channel) at a time. So if you have an RGBA image you might need to apply the operation on each of the four image planes and then combine the results. Gray scale images only contain one image plane (containing the gray scale intensity values).
Data reduction - Suppose you have a RGBA image (red-green-blue-alpha). If you converted this image to gray scale you would only need to process 1/4 of the data compared to the color image. For many image processing applications, especially video processing (e.g., real-time object tracking), this data reduction allows the algorithm to run in a reasonable amount of time.
Is conversion to gray scale a necessary step in Image preprocessing?
关于machine-learning - 使用机器学习进行人脸识别的灰色还是 RGB?,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/44019485/