检测照片方向的算法 [英] Algorithm to detect photo orientation

问题描述

我想自动旋转照片，即使有关图像方向的EXIF元数据不可用。

I would like to rotate photos automatically, even when EXIF metadata about the image orientation is not available.

是否有任何好的算法来检测照片的方向？图像是来自数码相机的照片。该算法不必完美地工作，但正确旋转照片所需的人工交互量的减少将是一个好处。

Are there any good algorithms for detecting the orientation of a photo? The images are photographs from a digital camera. The algorithm doesn't have to work perfectly, but any reduction in the amount of human interaction required to properly rotate photos would be a benefit.

我发现这两篇论文关于这个话题：

I have found these two papers on the topic:

• 自动图像定位的预分类（2006）


• 通过基于置信度的低级和语义提示集成进行图像方向检测的概率方法（2004）

• Pre-Classification for Automatic Image Orientation (2006)
• A Probabilistic Approach to Image Orientation Detection via Confidence-Based Integration of Low-Level and Semantic Cues (2004)

对其他研究，特别是实施的指针表示赞赏。

Pointers to other research and especially implementations are appreciated.

推荐答案

消费者数码相机的许多照片都是人物，可用于定位。人脸检测是一个研究得很好的研究领域。基本面部检测会为您提供一个矩形，其长边应为垂直尺寸。此外，如果您可以检测到眼睛/嘴巴，您应该能够选择正确的矩形方向。

Many photographs from consumer digital cameras are of people, which could be used for orientation. Face detection is a well-studied research area. Basic face detection would give you a rectangle whose longer side should be the vertical dimension. Further, if you can detect the eyes/mouth, you should be able to pick the correct orientation of the rectangle.

许多其他照片是旅游快照，天空是向上和蓝色，地面向下和绿色。

Many other photographs are tourist snaps, where the sky is up and blue, and the ground is down and green.

这篇关于检测照片方向的算法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！