隨著人們所能接觸到的影像資料大量增加，影像檢索的發展是非常重要的課題，但目前影像檢索辨識率仍不夠高，因為有著低階和高階意涵上的鴻溝問題，因此，自動影像註解開始發展並不斷改良影像萃取方式和分類方法等等來增加影像註解的準確率，近幾年更發展出了BOW(Bag of Words)的袋字模型方法，此方法原本是用於文字探勘上，但目前很常被使用在影像註解的領域上，目前不少研究針對BOW做改良，像是SPM(Spatial Pyramid Matching Bag Of Words)就是針對BOW加上空間資訊所形成，這些方法中會用到所謂的keypoint，keypoint為BOW方法中所偵測出的影像特徵，目前少有研究針對於keypoint作處理，通常萃取的keypoint數量非常龐大，因此不但可能消耗CPU的運算且可能影響訓練的model結果，進而使影像註解效果不佳，因此本研究將使用一種新的非監督演算法叫做IKS( Iterative Keypoint Selection)來做keypoint的篩選。 IKS主要概念是利用距離來做keypoint的篩選，在IKS中認為在一定的範圍距離內只需要有一個keypoint來代表這個區域或物件，因此從原始keypoints中挑出這些具代表性的keypoints來實行keypoints的篩選動作，另外可根據挑選方法分成兩種，IKS1使用隨機的方法，IKS2則採用分群的方法來進行。 本研究採用Caltech101以及Caltech256兩種資料集來進行實驗，透過IKS來做為keypoints的篩選方法，並比較經過IKS篩選和未經過篩選的BOW和SPM所產生的影像註解效果，評估的分類方法採用SVM(Support Vector Machines)。 實驗結果顯示，透過IKS的篩選，能夠將具有代表性的keypoints留下，不管是針對較少類別的Caltech101或是較多類別的Caltech256，IKS皆能對BOW和改良過的SPM產生作用，使得SVM所產生的分類率有提高的效果。 To search images from large image databases, image retrieval is the major technique to retrieve similar images based on users’ queries. In order to allow users to provide keyword-based queries, automatically annotating images with keywords has been extensively studied. In particular, BOW(Bag Of Words)and SPM(Spatial Pyramid Matching Bag Of Words) are two well-known methods to represent image content as the image feature descriptors. To extract the BOW or SPM features, some keypoints must be detected from each image. However, the number of the detected keypoints is usually very large and some of them are unhelpful to describe the image content, such as background and similar keypoints in different classes. In addition, the computational cost of the vector quantization step heavily depends on the amount of detected keypoints. Therefore, in this thesis I introduce a new algorithm called IKS(Iterative Keypoint Selection), whose aim is to select representative keypoints for generating the BOW and SPM features. The main concept of IKS is based on identifying some representative keypoints and the distance to select useful keypoints. Specifically, IKS can be divided into IKS1 and IKS2 according to the strategy of identifying representative keypoints. While IKS1 focuses on randomly selecting a keypoint from an image as the representative keypoint, IKS2 uses the k-means to generate the cluster centroids to find the representative keypoints that is closest to them. Our experimental results based on the Caltech101 and Caltech256 datasets demonstrate that performing keypoint selection by IKS1 and IKS2 can allow the SVM classifier to provide better classification accuracy than the baseline BOW and SPM without keypoint selection. More specifically, IKS2 is more appropriate than IKS1 for image annotation since it performs better than IKS1 when the larger dataset, i.e. Caltech 256, is used.
