With the rapid development of the World Wide Web, people benefit more and more from the sharing of information. However, Web pages with obscene, harmful, or illegal content can be easily accessed. It is important to recognize such unsuitable, offensive, or pornographic Web pages. In this paper, a novel framework for recognizing pornographic Web pages is described. A C4.5 decision tree is used to divide Web pages, according to content representations, into continuous text pages, discrete text pages, and image pages. These three categories of Web pages are handled, respectively, by a continuous text classifier, a discrete text classifier, and an algorithm that fuses the results from the image classifier and the discrete text classifier. In the continuous text classifier, statistical and semantic features are used to recognize pornographic texts. In the discrete text classifier, the naive Bayes rule is used to calculate the probability that a discrete text is pornographic. In the image classifier, the object's contour-based features are extracted to recognize pornographic images. In the text and image fusion algorithm, the Bayes theory is used to combine the recognition results from images and texts. Experimental results demonstrate that the continuous text classifier outperforms the traditional keyword-statistics-based classifier, the contour-based image classifier outperforms the traditional skin-region-based image classifier, the results obtained by our fusion algorithm outperform those by either of the individual classifiers, and our framework can be adapted to different categories of Web pages.

Abstract

Fresh‐cut coriander is one of the most frequently consumed leafy vegetables in China due to convenience and flavor, but it has safety issue mainly because of microbial contamination. The optimum conditions for treating fresh‐cut coriander with chlorine dioxide were concentration of 60 mg/L, time of 10 min and solution to fresh‐cut product ratio of 8:1. This process decreased the total number of aerobic bacterial colonies to 2.1 lg cfu/g. Seven bacterial strains were identified through 16S rDNA sequence analysis and morphological observation. The potentially pathogenic bacteria such as Staphylococcus, Brevibacterium, Pseudomonas and Acinetobacter, as well as other bacteria were effectively decreased by chlorine dioxide treatment. Therefore, treating fresh‐cut coriander with chlorine dioxide under appropriate conditions during processing or storage can both effectively reduce the food safety risk. These results provide a valuable theoretical basis for improving the safety of fresh‐cut products. Practical applications This is the first study that identifies the microbial genera on fresh‐cut coriander, providing evidence for the need of commercial sterilization. The results of this study can be applied to industrial production and provide references for postharvest quality handlings of other fresh‐cut vegetables and fruits.