会议论文集名称：
International Conference on Image Processing Theory Tools and Applications
关键词：
Deep learning;Barcode Detection;Distortion Correction;Barcode recognition
摘要：
The widespread use of barcode technology has led to the complexity of the application scenario. In the traditional barcode recognition method, there is no universal solution to the problems of uneven illumination, distortion, and sheltered. In this paper, the deep learning theory is used to solve the problem of barcode detection under the above situation. And on this basis, the problem of correcting linear distortion Data Matrix code is solved, and the key technology of barcode recognition under complex situation is broken through. After testing, the recognition speed reached 125ms, and the recognition accuracy reached about 93 %. The system uses CCD camera to collect pictures, adopts the HALCON to build the processing algorithm, and uses Visual Studio platform to build the software, which realizes the Date Matrix code, Drug Electronic Supervision Code and Product bar code fast and accurate identification on pharmaceutical packaging. The developed system can also detect the rotation angle of Barcode and Data Matrix code, which is favorable for reading the barcode information. The whole process is real-time.
摘要：
In order to ensure the rapid, safe and stable operation of trains, it is very important to detect the flaws on the rail surface. At present, although there are many detection methods for rail surface defects, the comprehensiveness, rapidity and accuracy of defect detection are still not satisfactory. Therefore, this paper presents a deep learning method using the YOLOv3 algorithm to realize rail surface defect detection. It first resets the input rail image size to 416*416, and then divides the rail image into S*S cells. According to the position of the defect in the cell, the width and height of the defect and the coordinates of the center point are calculated by the method of dimensional clustering, the coordinates are normalized. At the same time, it uses logistic regression to predict the bounding box object score, the binary cross-entropy loss is used to predict the categories that the bounding box may contain, the confidence is calculated and then prediction. The test results show that the recognition rate of this algorithm can reach more than 97%, and the identification time is about 0.15s. This method has great advantages for the detection of rail surface defects.
摘要：
The particle matter inspection for pharmaceutical injection is inevitable in the field of pharmaceutical manufacturing, as it has the direct impact on the quality of the drugs. It is a challenge to inspect the contaminated injection online using an imaging system. This paper introduces a novel and effective inspection machine consisting of three modules, a mechanical system with 120 carousel grips, an image acquisition system with multihigh resolution cameras and a multilight sources station, and a distributed industrial electrical computer control system. Particle visual inspection machine first acquires image sequence using the high-speed image acquisition system. The image capture process at each camera module is alternately synchronized with different LED illumination techniques (light transmission method and light reflection method), enabling independent capture of particle images from the same container. Then, a set of novel algorithms for image registration and fast segmentation are proposed to minimize false rejections even in sensitive conditions, which enable the identification of all the tiny potential defects. Finally, a particle tracking and classification algorithm based on an adaptive local weighted-collaborative sparse model is also presented. The experiments demonstrate that the proposed inspection system can effectively detect the particles in the pharmaceutical infusion solution online, and achieve a performance rate of above 97% average accuracy.
摘要：
Automatic image classification has become a necessary task to handle the rapidly growing digital image usage. It has branched out many algorithms and adopted new techniques. Among them, feature fusion-based image classification methods rely on hand-crafted features traditionally. However, it has been proven that the bottleneck features extracted through pre-trained convolutional neural networks (CNNs) can improve the classification accuracy. Thence, this study analyses the effect of fusing such cues from multiple architectures without being tied to any hand-crafted features. First, the CNN features are extracted from three different pre-trained models, namely AlexNet, VGG-16, and Inception-V3. Then, a generalised feature space is formed by employing principal component reconstruction and energy-level normalisation, where the features from individual CNN are mapped into a common subspace and embedded using arithmetic rules to construct fused feature vectors (FFVs). This transformation play a vital role in creating a representation that is appearance invariant by capturing complementary information of different high-level features. Finally, a multi-class linear support vector machine is trained. The experimental results demonstrate that such multi-modal CNN feature fusion is well suited for image/object classification tasks, but surprisingly it has not been explored so far by the computer vision research community extensively.
摘要：
At present, the detection of pharmaceutical injection products is a quite important step in the pharmaceutical manufacturing, as it has the direct related to the quality of medical product quality. Aiming at the difficulty that liquid particle has a smaller pixel point in the high resolution image of detection of pharmaceutical liquid particle, hence consider combined with deep neural network and clustering algorithm for detection and localization of little particle, and a processing method combining single-frame images with multi-frame images was proposed to identifying liquid particle. Firstly, the single-frame image is detected by using Faster-RCNN deep neural network, and it can obtain the detection result of the 8-frame sequence image. Then hierarchical clustering and K-means clustering algorithm are used for clustering to obtain the same target motion area. In this way, liquid particle can be more accurately identified and the accuracy of detection can be greatly improved. The experimental results show that the accuracy of detection and recognition of foreign substances in liquid medicine is improved by more than 10% on average.
摘要：
In bridge buildings, concrete is widely used because its materials are considerably low-cost and it has high plasticity. However, some drawbacks exist in this kind of bridges, and crack is the most common ones. In order to avoid the cracks in bridge buildings becoming worse, it is necessary to periodically perform the inspection for it. Thus, a bridge inspection robot system with machine vision is designed for precise and robust bridge crack detection. In order to facilitate the analysis for cracks, a number of images are collected and are stitched into a high quality panorama, then the crack-like defects in the panorama are segmented. Firstly, in this paper, a quick and high-quality method for image stitching is applied, which is based on ORB algorithm. Then, the local directional evidence(LDE) method is used to enhance the crack structures from low contrast images, which serves as a preprocessing. Finally, the crack-like defects can be easily segmented by several morphological operations and a technique called Tubularity flow field. The experimental results have not only verified the rapidity and high-quality of applied image stitching method, but also the excellent effect of the segmentation method.
作者机构：
[金侠挺; 张辉] College of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha, 410012, China;[张辉] College of Electrical and Information Engineering, Hunan University, Changsha, 410082, China
通讯机构：
College of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha, China
关键词：
new energy electric vehicle charging;detection and location to charging hole;machine vision;HSI color model;morphology
摘要：
A new method based on machine vision is designed for electric vehicle charging hole detection and location in order to solve the low efficiency, space limitations or leakage risk in artificial charging operation for electric vehicle and to realize the automatic charging based on robot. The method enable to efficiently and accurately extract valuable characteristics of the charging hole from a charging socket image. Aim at the problem that strong electromagnetic automobile charging system will bring salt and pepper noise to image signal, the paper firstly adopts the classical median filtering for image noise cancellation. The charging socket image shows complicated background, uneven brightness, strong reflective and few goal characteristic, making the goal segmentation extremely difficult when employing the common method with fixed or adaptive threshold. Therefore, a two-stage image segmentation method based on HSI color model is proposed in paper to extract the characteristics of the charging hole target with sub-pixel precision. The image segmentation method involves threshold segmentation in the Hue component of original image, morphological operation and edge detection based on Canny operator. Meanwhile, It also reduces the influence of problem above due to the operation in Hue component. In this paper, it is based on vision platform HALCON and experiment result shows that the method enable to meet the requirements where location accuracy with sub-pixel precision and detection.
