This paper attempts to classify Asian female faces with personal attractive preference utilizing PCA eigenface reconstruction ability. Conventional PCA-based methods combine face images in both attractive and not attractive, group into one huge training set to construct the eigenfaces. On the contrary, the proposed method constructs eigenfaces separately for both attractive and not attractive group. Hence, the eigenfaces will have more specific face features for each group respectively. Then, the similarity between the reconstructed image by eigenfaces of each group with the original image is measured and compared. The method yields average accuracy rate of 84.1% using Euclidean distance as the similarity measurement. It achieves improvement of accuracy by 12.7% and 7.7% if compared to Turkmen method with KNN classifier and Eisenthal pixel image SVM classifier, respectively.
In histopathological microscopic images, the morphological structure of nuclei plays an important role
to diagnose a cancer . In addition, multispectral images may provide more significant information than RGB images for nucleus analysis. In this paper, we present the signific ance of multispectral data in terms of classifying cancer and non cancer cells. We propose a methodology to identify cancer cells of hepatocellular carcinoma (HCC) by
extracting nuclear textures from 100x multispectral images of HE stained tissues. The pro posed system is composed of 2 stages: nuclei segmentation and nuclei classification based on their textural features. Precisely, pixel based classification is performed using a random forests classifier to automate the nuclei segmentation.Subsequently, nu clei textural features are extracted using multifractal descriptors. We utilized a texton based method to extract the texture of the nuclei and classify normal and cancer cells. Experimental results show that our method can automatically classif y the cell nuclei.