Machine learning 如何使用ImageJ进行二值图像分类？

我想做二值图像分类，我认为ImageJ将是一个很好的平台来做它，但唉，我不知所措。下面是我想做的伪代码。如何在ImageJ中实现这一点？它不必完全遵循伪代码，我只是希望这能给出我想要做什么的想法。（如果有插件或更合适的平台已经做到了这一点，你能告诉我吗？）

培训：

train_directory = get folder from user
train_set = get all image files in train_directory

class_file = get text file from user
// each row of class_file contains image name and a "1" or "-1"
// a "1" indicates that image belongs to the positive class

model = build_model_from_train_set_and_class_file
write_model_to_output_file
// end train

对于测试：

test_directory = get folder from user
test_set = get all images in test_directory
if (user wants to)
    class_file = get text file from user
    // normally for testing one would always know the class of the image
    // the if statement is just in case the user does not

model = read_model_file
output = classify_images_as_positive_or_negative
write_output_to_file

请注意，用户不应进行任何预处理：无额外的遮罩集、无图纸、无额外标签等。算法必须能够仅从训练图像中找出训练图像之间的共同点，并适当地建立模型。当然，该算法可以做任何它想做的预处理，只是不能依赖于已经完成的预处理

我尝试使用CVIPtools进行此操作，但它需要在所有图像上使用一个掩码来进行特征提取