


摘 "要: 傳統的基于稀疏表示的人臉識別方法是基于人臉的整體特征的,這類方法要求每位測試者的人臉圖像要有足夠多幅,而且特征維度高,計算復雜,針對這一問題,提出一種基于離散余弦變換和稀疏表示的人臉識別方法,對人臉圖像進行分塊采樣,對采樣樣本使用離散余弦變換和稀疏分解,然后使用一種類似于詞袋的方法得到整幅圖像的特征向量,最后使用相似度比較的方法進行分類識別。實驗表明,在此提出的方法比傳統的基于稀疏表示的人臉識別方法在訓練樣本較少時效果更好。
關鍵詞: 人臉識別; 離散余弦變換; 稀疏表示; 詞袋; 局部特征
中圖分類號: TN919?34; TP391.41 " " " " " " " 文獻標識碼: A " " " " " " " " " "文章編號: 1004?373X(2015)06?0115?04
Face recognition based on DCT and sparse representation
WANG Guang?liang, GUO He?fei
(School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China)
Abstract: Traditional face recognition methods based on sparse representation are based on holistic feature of face image. The methods requires enough face images for each test person and the high dimensional feature, and has computational complexity. Aiming at these shortcomings, a face recognition method based on discrete cosine transform (DCT) and sparse representation is proposed, which divides an image into regions, samples in each region, decomposes the samples by DCT and sparse representation, gets feature vector of the whole image with a method like bag?of?word, and then classifies and identifies them by similarity comparing method. The experiment results indicate that the method outperform the traditional face recognition methods based on sparse representation when there are few training samples.
Keywords: face recognition; discrete cosine transform; sparse representation; bag?of?word; local feature
0 "引 "言
人臉識別一直是計算機視覺領域非常熱門的研究課題之一,有效的人臉識別技術可以應用于社會生活的方方面面,比如公共安全、考勤門禁、人機交互等。近年來,學者們提出了很多人臉識別的方法,但是要建立起一個能夠在現實環境中進行自動人臉識別的系統還是面臨著諸多頗具挑戰性的問題[1],比如光照變化、表情變化、鏡頭角度變化、物體遮擋[2]等。近年來,人臉識別的方法層出不窮,其中一類是將信號處理領域常用的稀疏表示的方法應用到人臉識別:Wright等人在文獻[3]中提出了一種基于稀疏表示的分類方法(Sparse Representation based Classification, SRC),并將此方法應用于人臉識別。SRC方法的主要思想是將測試圖片用字典原子的稀疏線性組合進行表示,然后對于各個類別,分別只用該類的字典原子對原圖像進行重構,將重構殘差最小的那一類作為測試圖片的類別。……