Wenjing Jia

Learning-Based License Plate Detection Using Global and Local Features

This paper proposes a license plate detection algorithm using both global statistical features and local Haar-like features. Classifiers using global statistical features are constructed firstly through simple learning procedures. Using these classifiers, more than 70% of background area can be excluded from further training or detecting. Then the AdaBoost learning algorithm is used to build up the other classifiers based on selected local Haar-like features. Combining the classifiers using the global features and the local features, we obtain a cascade classifier. The classifiers based on global features decrease the complexity of the system. They are followed by the classifiers based on local Haar-like features, which makes the final classifier invariant to the brightness, color, size and position of license plates. The encouraging detection rate is achieved in the experiments

Region-based license plate detection

Automatic license plate recognition (ALPR) is one of the most important aspects of applying computer techniques towards intelligent transportation systems. In order to recognize a license plate efficiently, however, the location of the license plate, in most cases, must be detected in the first place. Due to this reason, detecting the accurate location of a license plate from a vehicle image is considered to be the most crucial step of an ALPR system, which greatly affects the recognition rate and speed of the whole system. In this paper, a region-based license plate detection method is proposed. In this method, firstly, mean shift is used to filter and segment a color vehicle image in order to get candidate regions. These candidate regions are then analyzed and classified in order to decide whether a candidate region contains a license plate. Unlike other existing license plate detection methods, the proposed method focuses on regions, which demonstrates to be more robust to interference characters and more accurate when compared with other methods.

Mean shift for accurate license plate localization

This paper presents a region-based algorithm for accurate license plate localization, where mean shift is utilized to filter and segment color vehicle images into candidate regions. Three features are extracted in order to decide whether a candidate region represents a real license plate, namely, rectangularity, aspect ratio, and edge density. Then, the Mahalanobis classifier is used with respect to above three features to classify license plate regions and non-license plate regions. Experimental results show that the proposed algorithm produces high robustness and accuracy.

Characterness: An Indicator of Text in the Wild

Text in an image provides vital information for interpreting its contents, and text in a scene can aid a variety of tasks from navigation to obstacle avoidance and odometry. Despite its value, however, detecting general text in images remains a challenging research problem. Motivated by the need to consider the widely varying forms of natural text, we propose a bottom-up approach to the problem, which reflects the characterness of an image region. In this sense, our approach mirrors the move from saliency detection methods to measures of objectness. In order to measure the characterness, we develop three novel cues that are tailored for character detection and a Bayesian method for their integration. Because text is made up of sets of characters, we then design a Markov random field model so as to exploit the inherent dependencies between characters. We experimentally demonstrate the effectiveness of our characterness cues as well as the advantage of Bayesian multicue integration. The proposed text detector outperforms state-of-the-art methods on a few benchmark scene text detection data sets. We also show that our measurement of characterness is superior than state-of-the-art saliency detection models when applied to the same task.Text in an image provides vital information for interpreting its contents, and text in a scene can aid a variety of tasks from navigation to obstacle avoidance and odometry. Despite its value, however, detecting general text in images remains a challenging research problem. Motivated by the need to consider the widely varying forms of natural text, we propose a bottom-up approach to the problem, which reflects the characterness of an image region. In this sense, our approach mirrors the move from saliency detection methods to measures of objectness. In order to measure the characterness, we develop three novel cues that are tailored for character detection and a Bayesian method for their integration. Because text is made up of sets of characters, we then design a Markov random field model so as to exploit the inherent dependencies between characters. We experimentally demonstrate the effectiveness of our characterness cues as well as the advantage of Bayesian multicue integration. The proposed text detector outperforms state-of-the-art methods on a few benchmark scene text detection data sets. We also show that our measurement of characterness is superior than state-of-the-art saliency detection models when applied to the same task.

A Fast Algorithm for License Plate Detection in Various Conditions

This paper proposes a fast algorithm detecting license plates in various conditions. There are three main contributions in this paper. The first contribution is that we define a new vertical edge map, with which the license plate detection algorithm is extremely fast. The second contribution is that we construct a cascade classifier which is composed of two kinds of classifiers. The classifiers based on statistical features decrease the complexity of the system. They are followed by the classifiers based on Haar-features, which make it possible to detect license plate in various conditions. Our algorithm is robust to the variance of the illumination, view angle, the position, size and color of the license plates when working in complex environment. The third contribution is that we experimentally analyze the relations of the scaling factor with detection rate and processing time. On the basis of the analysis, we select the optimal scaling factor in our algorithm. In the experiments, both high detection rate (with low false positive rate) and high speed are achieved when the algorithm is used to detect license plates in various complex conditions.

Segmentation of characters on car license plates

License plate recognition usually contains three steps, namely license plate detection/localization, character segmentation and character recognition. When reading characters on a license plate one by one after license plate detection step, it is crucial to accurately segment the characters. The segmentation step may be affected by many factors such as license plate boundaries (frames). The recognition accuracy will be significantly reduced if the characters are not properly segmented. This paper presents an efficient algorithm for character segmentation on a license plate. The algorithm follows the step that detects the license plates using an AdaBoost algorithm. It is based on an efficient and accurate skew and slant correction of license plates, and works together with boundary (frame) removal of license plates. The algorithm is efficient and can be applied in real-time applications. The experiments are performed to show the accuracy of segmentation.

Real-Time license plate detection under various conditions

This paper proposes an algorithm for real-time license plate detection. In this algorithm, the relatively easy car plate features are adopted including the simple statistical feature and Harr-like feature. The simplicity of the object features used is very helpful to real-time processing. The classifiers based on statistical features decrease the complexity of the system. They are followed by the classifiers based on Haar-like features, which makes the final classifier invariant to the brightness, color, size and position of license plates. The experimental results obtained by the proposed algorithm exhibit the encouraging performance.

Car Plate Detection Using Cascaded Tree-Style Learner Based on Hybrid Object Features

Car plate detection is a key component in automatic license plate recognition system. This paper adopts an enhanced cascaded tree style learner framework for car plate detection using the hybrid object features including the simple statistical features and Harr-like features. The statistical features are useful for simplifying the process on cascade classifier. The cascaded tree-style detector design will further reduce the false alarm and the false dismissal while retaining a high detection ratio. The experimental results obtained by the proposed algorithm exhibit the encouraging performance.

Bilateral edge detection on a virtual hexagonal structure

Edge detection plays an important role in image processing area. This paper presents an edge detection method based on bilateral filtering which achieves better performance than single Gaussian filtering. In this form of filtering, both spatial closeness and intensity similarity of pixels are considered in order to preserve important visual cues provided by edges and reduce the sharpness of transitions in intensity values as well. In addition, the edge detec-tion method proposed in this paper is achieved on sampled images represented on a newly developed virtual hexagonal structure. Due to the compact and circular nature of the hexagonal lattice, a better quality edge map is obtained on the hexagonal structure than common edge detection on square structure. Experimental results using proposed methods exhibit encouraging performance.

A new method for violence detection in surveillance scenes

Violence detection is a hot topic for surveillance systems. However, it has not been studied as much as for action recognition. Existing vision-based methods mainly concentrate on violence detection and make little effort to determine the location of violence. In this paper, we propose a fast and robust framework for detecting and localizing violence in surveillance scenes. For this purpose, a Gaussian Model of Optical Flow (GMOF) is proposed to extract candidate violence regions, which are adaptively modeled as a deviation from the normal behavior of crowd observed in the scene. Violence detection is then performed on each video volume constructed by densely sampling the candidate violence regions. To distinguish violent events from nonviolent events, we also propose a novel descriptor, named as Orientation Histogram of Optical Flow (OHOF), which are fed into a linear SVM for classification. Experimental results on several benchmark datasets have demonstrated the superiority of our proposed method over the state-of-the-arts in terms of both detection accuracy and processing speed, even in crowded scenes.