Deep learning-based human head detection and extraction for robotic portrait drawing

This paper presents a head detection and extraction method that can be used in robotic portrait drawing. First, using the state-of-the-art, real-time object detection system-YOLO(You Only Look Once), we train the model to automatically detect human heads directly from the image. Then we utilize the holistically-nested edge detection (HED) algorithm to extract head edges by performing image-to-image prediction. Finally, the content image of the head can be synthesized into a head edge map with a style synthesis algorithm. The synthesized image can be sent to the robot for drawing. Our method was verified and evaluated on the drawing robot we developed.

[1]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  G. Jean-Pierre,et al.  The artist robot: A robot drawing like a human artist , 2012, 2012 IEEE International Conference on Industrial Technology.

[4]  Luc Van Gool,et al.  The Pascal Visual Object Classes Challenge: A Retrospective , 2014, International Journal of Computer Vision.

[5]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[6]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Yan Wang,et al.  DeepContour: A deep convolutional feature learned by positive-sharing loss for contour detection , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[9]  Chuan Li,et al.  Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Jianbo Shi,et al.  DeepEdge: A multi-scale bifurcated deep network for top-down contour detection , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Aude Billard,et al.  A humanoid robot drawing human portraits , 2005, 5th IEEE-RAS International Conference on Humanoid Robots, 2005..

[12]  P. Selinger.  Potrace : a polygon-based tracing algorithm , 2003 .

[13]  Charless C. Fowlkes,et al.  Contour Detection and Hierarchical Image Segmentation , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[15]  Sheng Bi,et al.  Automatic feature extraction and optimal path planning for robotic drawing , 2016, 2016 IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER).

[16]  Leon A. Gatys,et al.  A Neural Algorithm of Artistic Style , 2015, ArXiv.

[17]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Zhuowen Tu,et al.  Holistically-Nested Edge Detection , 2015, ICCV.