Although image/video based fire recognition has received growing attention, an efficient and robust fire detection strategy is rarely explored. In this paper, we propose a novel approach to automatically identify the flame or smoke regions in an image. It is composed to three stages: (1) a block processing is applied to divide an image into several nonoverlapping image blocks, and these image blocks are identified as suspicious fire regions or not by using two color models and a color histogram-based similarity matching method in the HSV color space, (2) considering that compared to other information, the flame and smoke regions have significant visual characteristics, so that two kinds of image features are extracted for fire recognition, where local features are obtained based on the Scale Invariant Feature Transform (SIFT) descriptor and the Bags of Keypoints (BOK) technique, and texture features are extracted based on the Gray Level Co-occurrence Matrices (GLCM) and the Wavelet-based Analysis (WA) methods, and (3) a manifold learning-based classifier is constructed based on two image manifolds, which is designed via an improve Globular Neighborhood Locally Linear Embedding (GNLLE) algorithm, and the extracted hybrid features are used as input feature vectors to train the classifier, which is used to make decision for fire images or non fire images. Experiments and comparative analyses with four approaches are conducted on the collected image sets. The results show that the proposed approach is superior to the other ones in detecting fire and achieving a high recognition accuracy and a low error rate.
Head pose is useful information for many face-related tasks, such as face recognition, behavior analysis, human–computer interfaces, etc. Existing head pose estimation methods usually assume that the face images have been well aligned or that sufficient and precise training data are available. In practical applications, however, these assumptions are very likely to be invalid. This paper first investigates the impact of the failure of these assumptions, i.e., misalignment of face images, uncertainty and undersampling of training data, on head pose estimation accuracy of state-of-the-art methods. A learning-based approach is then designed to enhance the robustness of head pose estimation to these factors. To cope with misalignment, instead of using hand-crafted features, it seeks suitable features by learning from a set of training data with a deep convolutional neural network (DCNN), such that the training data can be best classified into the correct head pose categories. To handle uncertainty and undersampling, it employs multivariate labeling distributions (MLDs) with dense sampling intervals to represent the head pose attributes of face images. The correlation between the features and the dense MLD representations of face images is approximated by a maximum entropy model, whose parameters are optimized on the given training data. To estimate the head pose of a face image, its MLD representation is first computed according to the model based on the features extracted from the image by the trained DCNN, and its head pose is then assumed to be the one corresponding to the peak in its MLD. Evaluation experiments on the Pointing’04, FacePix, Multi-PIE, and CASIA-PEAL databases prove the effectiveness and efficiency of the proposed method.
Nowadays, with digital cameras and mass storage devices becoming increasingly affordable, each day thousands of
pictures are taken and images on the Internet are emerged at an astonishing rate. Image retrieval is a process of searching
valuable information that user demanded from huge images. However, it is hard to find satisfied results due to the well
known "semantic gap". Image classification plays an essential role in retrieval process. But traditional methods will
encounter problems when dealing with high-dimensional and large-scale image sets in applications. Here, we propose a
novel multi-manifold classification model for image retrieval. Firstly, we simplify the classification of images from high-dimensional
space into the one on low-dimensional manifolds, largely reducing the complexity of classification process.
Secondly, considering that traditional distance measures often fail to find correct visual semantics of manifolds,
especially when dealing with the images having complex data distribution, we also define two new distance measures
based on path-based clustering, and further applied to the construction of a multi-class image manifold. One experiment
was conducted on 2890 Web images. The comparison results between three methods show that the proposed method
achieves the highest classification accuracy.
Automatic license plate segmentation plays an essential role in intelligent transportation systems. But it can be a
challenging task when segmenting the vehicle images with poor quality in real-world applications. For segmenting
license plates out of the vehicle images efficiently, a novel two-stage segmentation strategy that contains a rough
localization stage and a fine segmentation stage is proposed in this paper. Firstly, during the rough localization stage, the
texture characteristic of Chinese license plates is utilized to get candidate rectangle regions. The license plate region is
then identified and extracted from these regions based on projection property and geometric information. In the fine
segmentation stage, two enhancement algorithms are applied to improve image quality and reduce segmentation error.
And then an adaptive threshold-based segmentation approach based on quantum-behaved particle swarm optimization is
presented to deal with the threshold selection of distinguishing the constitution codes from the background in the
obtained license plate region. The experiments of segmenting the vehicle images are illustrated to show that the proposed
method can achieve an ideal segmentation result with less computational cost.