A fast face detection architecture for auto-focus in smart-phones and digital cameras



Auto-focus is very important for capturing sharp human face centered images in digital and smart phone cameras. With the development of image sensor technology, these cameras support more and more highresolution images to be processed. Currently it is difficult to support fast auto-focus at low power consumption on high-resolution images. This work proposes an efficient architecture for an AdaBoost-based face-priority auto-focus. The architecture supports block-based integral image computation to improve the processing speed on high-resolution images; meanwhile, it is reconfigurable so that it enables the sub-window adaptive cascade classification, which greatly improves the processing speed and reduces power consumption. Experimental results show that 96% detection rate in average and 58 fps (frame per second) detection speed are achieved for the 1080p (1920×1080) images. Compared with the state-of-the-art work, the detection speed is greatly improved and power consumption is largely reduced.


1. 提出了并行的阵列化计算架构, 该架构支持包括高分辨率图上的基于块的积分处理, 从而实现并行计算, 可以加速人脸检测中积分计算过程。

2. 提出了子窗口自适应的计算机制, 该机制可以在计算量和检测精度方面达到一个比较好的权衡。

3. 提出了可重构的架构计算机制, 通过阵列之间互联模式重构, 阵列内部基本计算单元计算模式重构, 以及基本计算单元功能重构, 来支持子窗口自适应的分类计算, 有效减少计算量, 提高计算性能。

This is a preview of subscription content, access via your institution.


  1. 1

    Kehtarnavaz N, Oh H. Development and real-time implementation of a rule-based auto-focus algorithm. Real-Time Imag, 2003, 9: 197–203

    Article  Google Scholar 

  2. 2

    Peddigari V, Gamadia M, Kehtarnavaz N. Real-time implementation issues in passive automatic focusing for digital still camera. J Imag Sci Technol, 2005, 49: 114–123

    Google Scholar 

  3. 3

    Rahman M, Kehtarnavaz N. Real-time face-priority auto focus for digital and cell-phone cameras. IEEE Trans Consum Electron, 2008, 54: 1506–1513

    Article  Google Scholar 

  4. 4

    Xiong Y G, Pulli K. Color matching for high-quality panoramic images on mobile phones. IEEE Trans Consum Electron, 2010, 56: 2592–2600

    Article  Google Scholar 

  5. 5

    Chandrasekaran V, Dantu R, Jonnada S, et al. Cuffless differential blood Pressure estimation using smart phones. IEEE Trans Biomed Eng, 2013, 60: 1080–1089

    Article  Google Scholar 

  6. 6

    Yang M, Kriegman D, Ahuja N. Detecting faces in images: a survey. IEEE Trans Patt Anal Mach Intell, 2002, 24: 34–58

    Article  Google Scholar 

  7. 7

    Huang D Y, Lin C J, Hu W C. Learning-based face detection by adaptive switching of skin color models and AdaBoost under varying illumination. J Inf Hid Multimed Signal Process, 2011, 2: 204–216

    Google Scholar 

  8. 8

    Zhang Z W, Wang M H, Lu Z M, et al. A skin color model based on modified GLHS space for face detection. J Inf Hid Multimed Signal Process, 2014, 5: 144–151

    Google Scholar 

  9. 9

    Viola P, Jones M. Robust real-time face detection. Int J Comput Vis, 2004, 57: 137–154

    Article  Google Scholar 

  10. 10

    Isobe T, Fujiwara M, Kaneta H. Development and features of a TV navigation system. IEEE Trans Consum Electron, 2003, 50: 393–399

    Google Scholar 

  11. 11

    Zuo F, de With P H N. Real-time embedded face recognition for smart home. IEEE Trans Consum Electron, 2005, 51: 183–190

    Article  Google Scholar 

  12. 12

    An K H, Chuang M J. Cognitive face analysis system for future interactive TV. IEEE Trans Consum Electron, 2009, 55: 2271–2279

    Article  Google Scholar 

  13. 13

    Soowoong K, Jae-young S, Seungjoon Y. Vision-based cleaning area control for cleaning robots. IEEE Trans Consum Electron, 2002, 58: 685–690

    Google Scholar 

  14. 14

    Hanai Y, Hori Y, Nishimura J, et al. A versatile recognition processor employing Haar-like feature and cascade classifier. In: Proceedings of IEEE International Conference on Solid-State Circuits, San Francisco, 2009. 148–149

    Google Scholar 

  15. 15

    Kyrkou C, Theocharides T. A flexible parallel hardware architecture for AdaBoost-based real-time object detection. IEEE Trans Very Large Scale Integr Syst, 2011, 19: 1034–1047

    Article  Google Scholar 

  16. 16

    Hiromoto M, Sugano H, Miyamoto R. Partially parallel architecture for AdaBoost-based detection with Haar-like features. IEEE Trans Circ Syst Vid Technol, 2009, 19: 41–52

    Article  Google Scholar 

  17. 17

    Liu L B, Chen Y J, Wang D, et al. Implementation of multi-standard video decoder on a heterogeneous coarse-grained reconfigurable processor. Sci China Inf Sci, 2014, 57: 082406

    Google Scholar 

  18. 18

    Liu L B, Chen Y J, Yin S Y, et al. Implementation of AVS Jizhun decoder with HW/SW partitioning on a coarsegrained reconfigurable multimedia system. Sci China Inf Sci, 2014, 57: 082401

    Google Scholar 

Download references

Author information



Corresponding author

Correspondence to Shouyi Yin.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Ouyang, P., Yin, S., Deng, C. et al. A fast face detection architecture for auto-focus in smart-phones and digital cameras. Sci. China Inf. Sci. 59, 122402 (2016). https://doi.org/10.1007/s11432-015-5312-z

Download citation


  • auto-focus
  • AdaBoost
  • face-priority
  • architecture
  • reconfigurable


  • 自动对焦
  • 自适应增强
  • 脸部优先
  • 架构
  • 可重构