使用dlib进行狗脸检测-需要改善建议的建议 [英] Dog face detection with dlib - need advice on improving recal

问题描述

我正在尝试使用dlib的生猪金字塔探测器训练狗脸探测器。
我使用了哥伦比亚狗的数据集： ftp：//ftp.umiacs.umd .edu / pub / kanazawa / CU_Dogs.zip

I'm trying to train a dog face detector with dlib's hog pyramid detector. I used Columbia dogs dataset: ftp://ftp.umiacs.umd.edu/pub/kanazawa/CU_Dogs.zip

起初，我的召回率为0％，但是通过提高C值，我设法提高了它达到训练集的62％和测试集的53％。在某个点之后，增加C值会停止提供帮助（1000+），只会减慢训练速度。

At first I would get a recall of 0%, but by increasing C value I managed to increase it to 62% on training set and 53% on testing set. After certain point increasing C value stopped helping (1000+) and would only slow down training.

尽管它确实能够找到狗的脸，但精确度确实很高，它总是是的，没有看到任何误报。

Precision is really high though, if it actually manages to find dog's face it's always correct, haven't seen any false positives.

您能对我如何提高召回率以降低血统召回质量提供任何建议吗？

Could you give any advice on how I could improve recall to a descent recall quality?

预先感谢

更新：
根据戴维斯·金的建议，将训练集的准确性提高到100％，将测试的准确性提高到80％通过训练每个品种不同的检测器进行设置。我想如果按照他们希望的方向将它们聚类，它甚至会更高。

UPDATE: Following Davis King's advice, got the accuracy to 100% on training set and 80% on testing set just by training different detector per breed. I imagine it could be even higher if I cluster them by direction they're looking to.

推荐答案

您可能需要训练其他方法用于不同头部姿势和狗的探测器看起来很不一样。我会尝试使用--cluster选项运行dlib的imglab命令行工具。这样会将图像聚类为相干的姿势，您可以训练每个姿势的检测器。

You probably need to train different detectors for different head poses and dogs that look very different. I would try running dlib's imglab command line tool with the --cluster option. That will cluster the images into coherent poses and you can train detectors for each pose.

这篇关于使用dlib进行狗脸检测-需要改善建议的建议的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！