Text detection in natural scene images is an important prerequisite for many content-based multimedia understanding applications. The authors present a simple and effective text detection method in natural scene image. Firstly, MSERs are extracted by the V-MSER algorithm from channels of G, H, S, O 1 , and O 2 , as component candidates. Since text is composed of character candidates, the authors design an MRF model to exploit the relationship between characters. Secondly, in order to filter out non-text components, they design a set of two-layers filtering scheme: most of the non-text components can be filtered by the first layer of the filtering scheme; the second layer filtering scheme is an AdaBoost classifier, which is trained by the features of compactness, horizontal variance and vertical variance, and aspect ratio. Then, only four simple features are adopted to generate component pairs. Finally, according to the orientation similarity of the component pairs, component pairs which have roughly the same orientation are merged into text lines. The proposed method is evaluated on two public datasets: ICDAR 2011 and MSRA-TD500. It achieves 82.94 and 75% F-measure, respectively. Especially, the experimental results, on their URMQ_LHASA-TD220 dataset which contains 220 images for multi-orientation and multi-language text lines evaluation, show that the proposed method is general for detecting scene text lines in different languages.

No abstract

The skeleton plays an important role in sex determination in forensic anthropology. The skull bone is considered as the second best after the pelvic bone in sex determination due to its better retention of morphological features. Different populations have varying skeletal characteristics, making population specific analysis for sex determination essential. However, most previous studies have used the traditional discriminant function method, which is highly dependent on the population, and does not consider the uncertainty in the process of sex identification. In view of the above problems, this paper proposes a method of sex identification based on fuzzy decision tree. The proposed method is to improve the uncertainty, by constructing the fuzzy function of statistical information based on the cranial measurement item, as the basis of the fuzzy decision process, the classification factor is determined at the end of the training process, and a fuzzy decision binary tree is established. The experimental results show that the proposed method is effective and can provide reference for the practical application of gender discrimination.

We investigate facial expression recognition (FER) based on image appearance. FER is performed using state-of-the-art classification approaches. Different approaches to preprocess face images are investigated. First, region-of-interest (ROI) images are obtained by extracting the facial ROI from raw images. FER of ROI images is used as the benchmark and compared with the FER of difference images. Difference images are obtained by computing the difference between the ROI images of neutral and peak facial expressions. FER is also evaluated for images which are obtained by applying the Local binary pattern (LBP) operator to ROI images. Further, we investigate different contrast enhancement operators to preprocess images, namely, histogram equalization (HE) approach and a brightness preserving approach for histogram equalization. The classification experiments are performed for a convolutional neural network (CNN) and a pre-trained deep learning model. All experiments are performed on three public face databases, namely, Cohn–Kanade (CK[Formula: see text]), JAFFE and FACES.

No abstract