基於多核學習之個人化人臉檢索技術

Personalized Face Retrieval based on Multi-Kernel Learning

周佑昇(Yu-Sheng Chou)

指導教授 ： 蘇志文

中原大學/工學院/資訊工程研究所/碩士(2014年)

https://doi.org/10.6840/cycu201400560

摘要

近年來，由於社群網站的快速發展，基於屬性(attribute)的人臉影像檢索技術成為重要的研究課題。使用者透過事先訓練好的人臉視覺屬性來檢索相關的目標，甚至能達到多屬性結合的檢索方式。然而，因為人臉與一般影像同樣無法使用有限的文字結合來表達，因此這種方式無法檢索抽象、或是各人定義不同的人臉屬性。本論文提出了多核學習下之個人化人臉檢索技術，希望透過使用者提供的人臉影像，檢索出符合個人目標的人臉影像，而不受有限文字所箝制。藉由generalized multiple kernel learning(GMKL)的方法，分別依照不同的base-kernel學習臉部部位特徵，並自動調整分類器中各kernel的權重，最後利用此分類器作為個人化的人臉影像檢索工具。實驗的結果中，6種特定人臉屬性正確率都超過八成，並且在小樣本的實驗裡效率與正確率都遠高於LIBSVM，就目前的結果來看，本論文提出的方法不僅具有不錯效果，且更接近實際客制化應用之所需。

關鍵字

機器學習 ； 基於內容之影像檢索 ； 人臉屬性 ； 人臉影像檢索

並列摘要

In recent years, attribute-based face image retrieval has become a hot research topic due to the explosive growth of social media. Semantic visual attributes are pre-trained and combined to retrieve specific face images. However, just like an image cannot be described by keywords completely, it is impossible to describe a face image by limited attributes. Therefore, we propose a personalized face image retrieval scheme based on Generalized Multiple Kernel Learning (GMKL) in this paper. Each face image is first aligned by Constrained Local Model (CLM) and landmarks are extracted for locating facial parts automatically. The local features extracted from different facial parts are then modeled as the base-kernels in GMKL. After learning the kernel weights from the training set that selected by a user, face image retrieval can be achieved without pre-training attributes. Experimental results show that our method is reliable and efficient on LFW dataset using only tens training samples.

並列關鍵字

Face attribute ； Face image retrieval ； Content-based image retrieval ； Machine learning

參考文獻

[2] N. Kumar, P. N. Belhumeur, and S. K. Nayar, "FaceTracer: A Search Engine for Large Collections of Images with Faces," in European Conf. on Computer Vision (ECCV), 2008.

[3] W. J. Scheirer, N. Kumar, P. N. Belhumeur, and T. E. Boult," Multi-Attribute Spaces: Calibration for Attribute Fusion and Similarity Search", Computer Vision and Pattern Recognition (CVPR), 2012.

[4] P. Aarabi, D. Hughes, K. Mohajer, and M. Emaini, “The Automatic Measurement of Facial Beauty,” IEEE International Conference on System, Man and Cybernetics, vol. 4, pp. 2644-2647, 2001.

[5] H. Mao, L. Jin, and M. Du, “Automatic Classification of Chinese Female Facial Beauty using Support Vector Machine”, Proc. of the 2009 IEEE International Conference on Systems, Man, and Cybernetics, pp. 4987-4991, 2009.

[7] Y. Eisenthal, G. Dror, and E. Ruppin, “Facial Attractiveness: Beauty and the Machine”, Neural Computation, pp. 119-142, 2006.