DOI QR코드

DOI QR Code

Deep Learning based Photo Horizon Correction

딥러닝을 이용한 영상 수평 보정

  • Received : 2017.06.24
  • Accepted : 2017.07.06
  • Published : 2017.07.14

Abstract

Horizon correction is a crucial stage for image composition enhancement. In this paper, we propose a deep learning based method for estimating the slanted angle of a photograph and correcting it. To estimate and correct the horizon direction, existing methods use hand-crafted low-level features such as lines, planes, and gradient distributions. However, these methods may not work well on the images that contain no lines or planes. To tackle this limitation and robustly estimate the slanted angle, we propose a convolutional neural network (CNN) based method to estimate the slanted angle by learning more generic features using a huge dataset. In addition, we utilize multiple adaptive spatial pooling layers to extract multi-scale image features for better performance. In the experimental results, we show our CNN-based approach robustly and accurately estimates the slanted angle of an image regardless of the image content, even if the image contains no lines or planes at all.

본 논문은 딥 러닝(deep learning)을 이용하여 입력 영상의 기울어진 정도를 측정하고 수평에 맞게 바로 세우는 방법을 제시한다. 기존 방법들은 일반적으로 영상 내에서 선분, 평면 등 하위 레벨의 특징들을 추출한 후 이를 이용해 영상의 기울어진 정도를 측정한다. 이러한 방법들은 영상 내에 선이나 평면이 존재하지 않는 경우에는 제대로 동작하지 않는다. 본 논문에서는 대규모 데이터 셋을 통해 영상의 다양한 특징들에 대해 학습 가능한 Convolutional Neural Network (CNN)를 이용하여 인물이나 복잡한 배경으로 구성된 기울어진 영상에 대해서도 강인하게 동작하는 프레임워크를 제시한다. 또한, 네트워크에 가변 공간적 (adaptive spatial) pooling 레이어를 추가하여 영상의 다중 스케일 특징을 동시에 고려할 수 있게 하여 영상의 기울어진 정도를 측정하는 성능을 높인다. 실험 결과를 통해 다양한 콘텐츠를 포함한 영상의 기울어짐을 높은 정확도로 바로 세울 수 있음을 확인할 수 있다.

Keywords

References

  1. B.T. Avila and R.D. Lins, "A fast orientation and skew detection algorithm for monochromatic document images," in proc. ACM Symposium on Document Engineering, pp. 118-126, 2005.
  2. N. Gourier, D. Hall and J.L. Crowley, "Estimating face orientation from robust detection of salient facial structures," in proc. FG Net Workshop on Visual Observation of Deictic Gestures, vol. 6, 2004.
  3. M. Osadchy, Y.L. Cun and M.L. Miller, "Synergistic face detection and pose estimation with energy-based models," Journal of Machine Learning Research, pp. 1197-1215, 2007.
  4. Y.M. Wang and H. Zhang, "Detecting image orientation based on low-level visual content," Computer Vision and Image Understanding, 93(3), pp. 328-346, 2004. https://doi.org/10.1016/j.cviu.2003.10.006
  5. M. Datar and X. Qi, "Automatic image orientation detection using the supervised self-organizing map," in proc. 8th IASTED International Conference, 2006.
  6. L. Wang, X. Liu, L. Xia, G. Xu and A. Bruckstein, "Image orientation detection with integrated human perception cues (or which way is up)," in proc. International Conference on Image Processing (ICIP), vol.3, 2003.
  7. H. Lee, E. Shechtman, J. Wang and S. Lee, "Automatic upright adjustment of photographs," in proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 877-884, 2012.
  8. K. He, X. Zhang, S. Ren and J. Sun, "Deep residual learning for image recognition," in proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770-778, 2016.
  9. L. Mai, H. Jin and F. Liu, "Composition-preserving deep photo aesthetics assessment," in proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 497-506, 2016.
  10. U. Joshi and M. Guerzhoy, "Automatic photo orientation detection with convolution neural networks," in proc. Conference on Computer and Robot Vision (CRV), 2017.
  11. G. Tolias and Y. Avrithis "Speeded-up, relaxed spatial matching," in proc. International Conference on Computer Vision(ICCV), 2011.