License plate recognition algorithm for passenger cars in Chinese residential areas

Scale-Invariant Multidirectional License Plate Detection with the Network Combining Indirect and Direct Branches

As the license plate is multiscale and multidirectional in the natural scene image, its detection is challenging in many applications. In this work, a novel network that combines indirect and direct branches is proposed for license plate detection in the wild. The indirect detection branch performs small-sized vehicle plate detection with high precision in a coarse-to-fine scheme using vehicle–plate relationships. The direct detection branch detects the license plate directly in the input image, reducing false negatives in the indirect detection branch due to the miss of vehicles’ detection. We propose a universal multidirectional license plate refinement method by localizing the four corners of the license plate. Finally, we construct an end-to-end trainable network for license plate detection by combining these two branches via post-processing operations. The network can effectively detect the small-sized license plate and localize the multidirectional license plate in real applications. To our knowledge, the proposed method is the first one that combines indirect and direct methods into an end-to-end network for license plate detection. Extensive experiments verify that our method outperforms the indirect methods and direct methods significantly.

A Vision-Based Machine Learning Method for Barrier Access Control Using Vehicle License Plate Authentication

Automatic vehicle license plate recognition is an essential part of intelligent vehicle access control and monitoring systems. With the increasing number of vehicles, it is important that an effective real-time system for automated license plate recognition is developed. Computer vision techniques are typically used for this task. However, it remains a challenging problem, as both high accuracy and low processing time are required in such a system. Here, we propose a method for license plate recognition that seeks to find a balance between these two requirements. The proposed method consists of two stages: detection and recognition. In the detection stage, the image is processed so that a region of interest is identified. In the recognition stage, features are extracted from the region of interest using the histogram of oriented gradients method. These features are then used to train an artificial neural network to identify characters in the license plate. Experimental results show that the proposed method achieves a high level of accuracy as well as low processing time when compared to existing methods, indicating that it is suitable for real-time applications.

Identification of carbon nanotube particles in liver tissue and its effects on apoptosis of birds exposed to air pollution

Aim

This study aimed to distinguish carbon nanotube (CNT) particles and their pathological effects on the liver of birds in areas with carbon emissions.

Materials and Methods

Twenty-one domestic ducks were collected from pure farmers and exposed to different sources of air pollution. Histological stains were used to detect the accumulation of carbon particles. In addition, acridine orange/ethidium bromide staining was used to detect apoptosis, and scanning electron microscope (SEM) technique was used to determine the morphological design of carbon particles.

Results

Light microscope results showed that the liver sections contain multiwalled CNTs (MWCNTs) which appear as black spots in the hepatic parenchyma. The histopathological changes of parenchyma include sinusoidal dilatation, infiltration, and congestion with frequently high number of macrophages. In general, early destruction of hepatic parenchyma was observed. Moreover, SEM results showed two morphological types of CNTs: The ball-shaped nanoparticles scattered as ultrafine carbon black and fiber form of carbon particles were recognized as MWCNTs in the hepatic tissue. Fluorescence microscopy results showed the early and progressive stages of apoptosis in the hepatic cells of birds in polluted areas, which can be related to the degree and exposure period to pollutants.

Conclusion

The study indicates that liver morbidity of birds living in the farms affected by the pollution of brick factories is higher than the birds living in farms affected by the pollution of oil fields.

Barrier Access Control Using Sensors Platform and Vehicle License Plate Characters Recognition

The paper proposes a sensors platform to control a barrier that is installed for vehicles entrance. This platform is automatized by image-based license plate recognition of the vehicle. However, in situations where standardized license plates are not used, such image-based recognition becomes non-trivial and challenging due to the variations in license plate background, fonts and deformations. The proposed method first detects the approaching vehicle via ultrasonic sensors and, at the same time, captures its image via a camera installed along with the barrier. From this image, the license plate is automatically extracted and further processed to segment the license plate characters. Finally, these characters are recognized with the help of a standard optical character recognition (OCR) pipeline. The evaluation of the proposed system shows an accuracy of 98% for license plates extraction, 96% for character segmentation and 93% for character recognition.

Multi-Oriented and Scale-Invariant License Plate Detection Based on Convolutional Neural Networks

License plate detection (LPD) is the first and key step in license plate recognition. State-of-the-art object-detection algorithms based on deep learning provide a promising form of LPD. However, there still exist two main challenges. First, existing methods often enclose objects with horizontal rectangles. However, horizontal rectangles are not always suitable since license plates in images are multi-oriented, reflected by rotation and perspective distortion. Second, the scale of license plates often varies, leading to the difficulty of multi-scale detection. To address the aforementioned problems, we propose a novel method of multi-oriented and scale-invariant license plate detection (MOSI-LPD) based on convolutional neural networks. Our MOSI-LPD tightly encloses the multi-oriented license plates with bounding parallelograms, regardless of the license plate scales. To obtain bounding parallelograms, we first parameterize the edge points of license plates by relative positions. Next, we design mapping functions between oriented regions and horizontal proposals. Then, we enforce the symmetry constraints in the loss function and train the model with a multi-task loss. Finally, we map region proposals to three edge points of a nearby license plate, and infer the fourth point to form bounding parallelograms. To achieve scale invariance, we first design anchor boxes based on inherent shapes of license plates. Next, we search different layers to generate region proposals with multiple scales. Finally, we up-sample the last layer and combine proposal features extracted from different layers to recognize true license plates. Experimental results have demonstrated that the proposed method outperforms existing approaches in terms of detecting license plates with different orientations and multiple scales.

A Character Segmentation Proposal for High-Speed Visual Monitoring of Expiration Codes on Beverage Cans

Expiration date labels are ubiquitous in the food industry. With the passage of time, almost any food becomes unhealthy, even when well preserved. The expiration date is estimated based on the type and manufacture/packaging time of that particular food unit. This date is then printed on the container so it is available to the end user at the time of consumption. MONICOD (MONItoring of CODes); an industrial validator of expiration codes; allows the expiration code printed on a drink can to be read. This verification occurs immediately after printing. MONICOD faces difficulties due to the high printing rate (35 cans per second) and problematic lighting caused by the metallic surface on which the code is printed. This article describes a solution that allows MONICOD to extract shapes and presents quantitative results for the speed and quality.

Application of morphological segmentation to leaking defect detection in sewer pipelines

As one of major underground pipelines, sewerage is an important infrastructure in any modern city. The most common problem occurring in sewerage is leaking, whose position and failure level is typically identified through closed circuit television (CCTV) inspection in order to facilitate rehabilitation process. This paper proposes a novel method of computer vision, morphological segmentation based on edge detection (MSED), to assist inspectors in detecting pipeline defects in CCTV inspection images. In addition to MSED, other mathematical morphology-based image segmentation methods, including opening top-hat operation (OTHO) and closing bottom-hat operation (CBHO), were also applied to the defect detection in vitrified clay sewer pipelines. The CCTV inspection images of the sewer system in the 9th district, Taichung City, Taiwan were selected as the experimental materials. The segmentation results demonstrate that MSED and OTHO are useful for the detection of cracks and open joints, respectively, which are the typical leakage defects found in sewer pipelines.