Image Processing Algorithms For Detection Research Articles

Research on Manufacturing Technology of New Energy Vehicle Based on NDT

For the detection of laser welding defects of new energy vehicles, the traditional detection methods are inefficient and have limited accuracy. The existing visual detection methods mainly use area array cameras and image processing algorithms for detection. The image acquisition efficiency of the area array camera is low. The traditional image processing methods are vulnerable to the strong reflection on the surface of new energy vehicles, and the recognition speed and accuracy are limited. Therefore, in this paper, the linear array high-resolution camera is used for two-dimensional image acquisition, and the deep learning method is used for the recognition of weld defects. Based on the single-stage target detection network, the YOLO network is optimized according to the particularity of weld defects. The weld data set and defect data set are prepared, and the data set is used to train the optimized YOLO model. The feasibility of the method is verified by experiments, which can meet the mainstream weld length detection standards in the automotive industry.

A Four Stage Image Processing Algorithm for Detecting and Counting of Bagworm, Metisa plana Walker (Lepidoptera: Psychidae)

The bagworm is a vicious leaf eating insect pest that threatens the oil palm plantations in Malaysia. The economic impact from defoliation of approximately 10% to 13% due to bagworm attack might cause about 33% to 40% yield loss over 2 years. Due to this, monitoring and detecting of bagworm populations in oil palm plantations is required as the preliminary steps to ensure proper planning of control actions in these areas. Hence, the development of an image processing algorithm for detection and counting of Metisa plana Walker, a species of Malaysia’s local bagworm, using image segmentation has been researched and completed. The color and shape features from the segmented images for real time object detection showed an average detection accuracy of 40% and 34%, at 30 cm and 50 cm camera distance, respectively. After some improvements on training dataset and marking detected bagworm with bounding box, a deep learning algorithm with Faster Regional Convolutional Neural Network (Faster R-CNN) algorithm was applied leading to the percentage of the detection accuracy increased up to 100% at a camera distance of 30 cm in close conditions. The proposed solution is also designed to distinguish between the living and dead larvae of the bagworms using motion detection which resulted in approximately 73–100% accuracy at a camera distance of 30 cm in the close conditions. Through false color analysis, distinct differences in the pixel count based on the slope was observed for dead and live pupae at 630 nm and 940 nm, with the slopes recorded at 0.38 and 0.28, respectively. The higher pixel count and slope correlated with the dead pupae while the lower pixel count and slope, represented the living pupae.

Image processing algorithm for detection, quantification and classification of microdefects in wire electric discharge machined precision finish cut surfaces

This study aims to create an image processing algorithm that categorises the wire electric discharge machine (WEDM) processed finish cut surfaces, based on surface microdefects. The algorithm also detects the defect locations and suggests alternate parameter settings for improving the surface integrity. The proposed automated analysis is more precise, efficient and repeatable compared to manual inspection. Also, the method can be used for automatic data generation to suggest parameter changes in closed loop systems. During the training phase, mean, standard deviation and defect area fraction of enhanced binary images are extracted and stored. The training dataset consists of 27 WEDM finish cut surface images with labels, ‘coarse’, ‘average’ and ‘smooth’. The trained model is capable of categorising any machined surface by detecting the microdefects. If the machined surface image is not classified as a smooth image, then alternate input parameter settings will be suggested by the model to minimise the microdefects. This is done based on the Euclidean distance between the current image datapoint and the nearest ‘smooth’ class datapoint.

An image processing algorithm for detection and analysis of slicing checks

In this paper, a new method of measuring slicing checks for flat-sliced veneers was evaluated. The method is based on image analysis of veneer cross-sections, having highlighted the slicing checks using surface staining. The segmentation of the checks consists of global thresholding followed by some morphological operations. The outputs of the algorithm are check depth ratio and check frequency. The method was tested on flat-sliced oak (Quercus robur L. and Quercus petraea (Matt). Liebl.) veneers of different thicknesses (1.5, 2.5, 3.5 and 4.5 mm). Two distinct wood qualities and two different cutting directions (lengthwise-sliced and plain-sliced veneers) were evaluated. The algorithm performance resulted in an overall accuracy of 85% enabling an accessible method for relatively fast and accurate measurements of slicing check characteristics in lamella cross-sections. Regression analysis indicated a lack of fixed bias but the presence of proportional bias with the presented method. Check measurements indicate that by varying cutting parameters, it is possible to achieve desired check characteristics independent of slicing thickness. The semi-automated slicing check detection method could benefit further research and optimisation of the slicing process parameters and pave the way towards industrial quality control of slicing checks. The intended area of application is veneer-laminated products for interior use with the focus on veneered wood flooring.

Identification of Common Skin Defects and Classification of Early Decayed Citrus Using Hyperspectral Imaging Technique

Automatic detection of fruit skin defects is always one of the main tasks of post-harvest processing of citrus fruit. However, it is a challenge to identify different types of defects simultaneously due to a high rate of unpredictability in texture and color of defects. In addition, as a typical spherical fruit, the uneven lighting distribution on the citrus is also one of the main problems causing low accuracy of defect detection. This study observed that the feasibility of using visible-near-infrared (Vis-NIR) hyperspectral reflectance imaging technology to identify the common seven types of skin defects on oranges and also classify the early decayed oranges from other samples simultaneously. Segmented principal component analysis (PCA), such as Vis-NIR-PCA, Vis-PCA and NIR-PCA, was first performed to reduce data dimensions and obtain the optimal principal component (PC) that was used to extract several characteristic wavelength images. Five characteristic wavelength images centered at around 540, 623, 675, 805, and 975 nm were selected based on the optimal Vis-NIR-PC2 image and weight coefficient analysis. The mean normalization method was used to correct the uneven lighting distribution on spherical orange fruit based on characteristic wavelength images. The multispectral image processing algorithms for detection of all defective oranges and classification of early decayed oranges are developed, respectively. For the investigated 397 independent test samples, an overall classification accuracy of 97.73% was obtained for differentiating normal and defective oranges based on mean-PC images combined with the improved watershed segmentation algorithm, and identification rate of 100% was obtained for classifying decayed and non-decayed oranges based on mean-PC5 and a simple global threshold. The results of this study can be used as a reference to develop the fast and low-cost multispectral image detection system for the rapid detection of defective citrus fruit and classification of specific oranges with early decay synchronously.

Fully adaptive segmentation of cracks on concrete surfaces

In this study, we present fully automated image processing algorithms for detection of cracks on concrete surfaces. The acquired images of these concrete surfaces are the inputs to the proposed system. Solutions are developed for factors, which hinder accurate automated crack region analysis. These factors include noise, rough textures, uneven illumination and poor contrast. Both subjective and objective evaluation using standard datasets indicate better performance than several algorithms from the literature. Furthermore, the proposed scheme is implemented and deployed as a Java software application.

Development of Real-time HABs Detection Technique Using Unmanned Aerial Vehicle (UAV)

Kim, T.W.; Yun, H.S.; Kim, K.B., and Hong, S.B., 2019. Development of real-time HABs detection technique using Unmanned Aerial Vehicle (UAV). In: Lee, J.L.; Yoon, J.-S.; Cho, W.C.; Muin, M., and Lee, J. (eds.), The 3rd International Water Safety Symposium. Journal of Coastal Research, Special Issue No. 91, pp. 391-395. Coconut Creek (Florida), ISSN 0749-0208.If HABs flow into the seawater desalination plant by surprise, it can inflict some serious damages on the plant such as plant contamination. A monitoring system capable of detecting and tracking HABs based on UAV has been developed in order to solve this problem. The monitoring system is based on the HSV Color Detection Image Processing Algorithm, which demonstrates an excellent price/performance ratio for monitoring the HABs behavior, as well as excellent monitoring range and maneuverability. The HSV color detection algorithm, which has a superior detection range under sunlight, was able to continuously track the HABs, extracting the velocity and direction data. Finally, these results were compared with those obtained by conventional technologies to verify its effectiveness.

Benchmarking Image Processing Algorithms for Unmanned Aerial System-Assisted Crack Detection in Concrete Structures

This paper summarizes the results of traditional image processing algorithms for detection of defects in concrete using images taken by Unmanned Aerial Systems (UASs). Such algorithms are useful for improving the accuracy of crack detection during autonomous inspection of bridges and other structures, and they have yet to be compared and evaluated on a dataset of concrete images taken by UAS. The authors created a generic image processing algorithm for crack detection, which included the major steps of filter design, edge detection, image enhancement, and segmentation, designed to uniformly compare different edge detectors. Edge detection was carried out by six filters in the spatial (Roberts, Prewitt, Sobel, and Laplacian of Gaussian) and frequency (Butterworth and Gaussian) domains. These algorithms were applied to fifty images each of defected and sound concrete. Performances of the six filters were compared in terms of accuracy, precision, minimum detectable crack width, computational time, and noise-to-signal ratio. In general, frequency domain techniques were slower than spatial domain methods because of the computational intensity of the Fourier and inverse Fourier transformations used to move between spatial and frequency domains. Frequency domain methods also produced noisier images than spatial domain methods. Crack detection in the spatial domain using the Laplacian of Gaussian filter proved to be the fastest, most accurate, and most precise method, and it resulted in the finest detectable crack width. The Laplacian of Gaussian filter in spatial domain is recommended for future applications of real-time crack detection using UAS.

Development of a robust algorithm for detection of nuclei of white blood cells in peripheral blood smear images

Microscopic evaluation of peripheral blood smear analysis is a commonly used laboratory procedure to diagnose various diseases such as anemia, malaria, leukemia, etc. Manual microscopic evaluation is laborious and hence many research groups have attempted to automate smear analysis. Variations in staining procedure and smear preparation introduces color shade variations into peripheral blood smear images. Illumination provided by point source bulb introduces brightness variations across the smear which affects the performance of an automated method. In this paper we present an image processing algorithm for detection of nuclei of white blood cells which is robust to color and brightness variations. In the proposed method we used two different datasets and also five datasets which were derived from original images by introducing brightness variations. We also compared the results of the proposed method with four state-of-the-art methods. The results demonstrate that the proposed method detects nuclei accurately with an average accuracy of 0.99 and Dice coefficient of 0.965.

A Pump Based Microfluidic Image Processing System for Droplet Detection and Counting

Droplet Microfluidics has attracted great attention in recent years because of its interdisciplinary nature and had a wide application in various field especially biomedical applications. Till now researcher focus on controlling the size of droplet through flow rates but none of them focus on droplet detection and counting. This is the first research in which we have presented an automatic system based on Image processing algorithm for detection and counting of the droplets. The image processing algorithm is based on temporal differencing-based motion detection algorithm for continuous flowing droplet detection and counting. Moreover, the overall system was tested to generate droplet of phosphate-buffered Saline and 8% polyethylene glycol diacrylate pre-polymer droplet. The results depicted that our algorithm is capable of detecting the droplets as well as counting them with lowest statistical errors.

Development of a Robust Algorithm for Detection of Nuclei and Classification of White Blood Cells in Peripheral Blood Smear Images.

Peripheral Blood Smear analysis plays a vital role in diagnosis of many diseases such as leukemia, anemia, malaria, lymphoma and infections. Unusual variations in color, shape and size of blood cells indicate abnormal condition. We used a total of 117 images from Leishman stained peripheral blood smears acquired at a magnification of 100X. In this paper we present a robust image processing algorithm for detection of nuclei and classification of white blood cells based on features of the nuclei. We used novel image enhancement method to manage illumination variations and TissueQuant method to manage color variations for the detection of nuclei. Dice similarity coefficient of 0.95 was obtained for nucleus detection. We also compared the proposed method with a state-of-the-art method and the proposed method was found to be better. Shape and texture features of the detected nuclei were used for classifying white blood cells. We considered classification of WBCs using two approaches such as 5-class and cell-by-cell approaches using neural network and hybrid-classifier respectively. We compared the results of both the approaches for classification of white blood cells. Cell-by-cell approach offered 1.4% higher sensitivity in comparison with the 5-class approach. We obtained an accuracy of 100% for lymphocyte and basophil detection. Hence, we conclude that lymphocytes and basophils can be accurately detected even when the analysis is limited to the features of nuclei whereas, accurate detection of other types of WBCs will require analysis of the cytoplasm too.

Characterization of dental pathologies using digital panoramic X-ray images based on texture analysis.

Dental caries and the cysts of jaws are frequently occurring pathologies encountered in a dental practice. Imaging of these dental anomalies is done with radiographic examination. Panoramic radiography/ Orthopantomography (OPG) is a common modality to screen patients with an advantage of ease of imaging and reduced exposure to patients. The panoramic images obtained with this equipment are exploited by noise embedded during its acquisition making the detection of this dental caries difficult. Detection and characterization of dental caries and various other maxilla-facial pathologies can be achieved by the application of computer aided image processing algorithms applied on dental panoramic images. This paper presents two distinct image processing algorithms for detection of dental anomalies. The first part of this paper presents a novel approach for detection of dental caries using hybridized negative transformation. The second part of paper presents, statistical texture analysis for the dental images containing cysts along with dental caries. The texture analysis is used when the objects to be segmented based on texture content rather than intensities. The texture of panoramic image is characterized by Gray Level Co-occurrence Matrix (GLCM). The texture features obtained from the GLCM are energy, entropy, homogeneity, contrast and correlation. These texture features can be used to find texture boundaries to obtain segmentation about the region of cysts. Results obtained by both the methods were satisfactory correlating with the diagnosis made by the maxillofacial radiologists.

Wireless Multimedia Sensor Network Based Subway Tunnel Crack Detection Method

Subway tunnel cracks directly reflect the structural integrity of a tunnel, and as such the detection of subway tunnel cracks is always an important task in tunnel structure monitoring. This paper presents a convenient, fast, and automated crack detection method based on a wireless multimedia sensor subway tunnel network. This method primarily provides a solution for image acquisition, image detection and identification of cracks. In order to quickly obtain a surface image of the tunnel, we used special train image sensor nodes to provide the high speed and high performance processing capability with a large-capacity battery. The proposed process can significantly reduce the amount of data transmission by compressing the binary image obtained by initial processing of the original image. We transferred the data compressed by the sensor to an appropriate station and uploaded them to a database when the train passes through the station. We also designed a fast, easy to implement fracture identification and detection image processing algorithm that can solve the image identification and detection problem. In real subway field tests, this method provided excellent performance for subway tunnel crack detection, and recognition.

Embedded Image Processing Systems for Automatic Recognition of Cracks using UAVs

Aiming at the use of Unmanned Aerial Vehicle (UAV) in civil construction for autonomous inspection of building pathologies, this paper discusses some implementation alternatives of image processing algorithms for the detection of cracks in building facades. These algorithms should run in an embedded computing platform installed on UAVs. Two image processing algorithms for crack detection and classification were selected and different embedded system implementations were evaluated. A version of the algorithms running in a Matlab environment on a desktop computer, which can be used in an approach on which the image processing is done in the ground and the UAV is only applied for image acquisition, was used as a baseline for the comparison. This baseline is compared with implementations running on an embedded processor (a Raspberry PI, running a distribution of Debian ARM operating system) and with implementations on a Xilinx FPGA-board installed in the UAV. Different scenarios for the execution of a inspection task of building facades were defined and the obtained results are presented in the paper.

무인항공기의 근거리 비행체 탐지 및 추적을 위한 영상처리 알고리듬

본 논문에서는 무인항공기의 근거리 비행체 탐지 및 추적을 위한 영상처리 알고리듬을 제안한다. 제안된 알고리듬은 연속되는 영상에서 계산되는 호모그래피를 사용하여 움직이는 객체를 검출하고 확률적 다수-가설 추적기법으로 검출된 객체가 접근하는 비행체인지의 여부를 판단한다. 이는 항공기의 저고도 비행 시 영상에 보여지는 지표면과 같이 복잡한 배경 위에서 이동하는 비행체를 검출할 수 있고, 비행체의 동역학적 특성을 고려할 수 있기 때문에 색상기반의 비행체 탐지기법보다 향상된 성능을 보여준다. 또한 외부영향에 대한 임계치의 민감도를 현저히 감소시키므로 소형 무인항공기의 저고도 비행실험수행 시 효과적이다. 제안된 영상처리 알고리듬을 실제 비행실험 영상에 적용하여 성능을 검증하였다. This paper proposes an image processing algorithms for detection and tracking of aerial vehicles in short-range. Proposed algorithm detects moving objects by using image homography calculated from consecutive video frames and determines whether the detected objects are approaching aerial vehicles by the Probabilistic Multi-Hypothesis Tracking method(PMHT). This algorithm can perform better than simple color-based detection methods since it can detect moving objects under complex background such as the ground seen during low altitude flight and consider the characteristics of vehicle dynamics. Furthermore, it is effective for the flight test due to the reduction of thresholding sensitivity against external factors. The performance of proposed algorithm is verified by applying to the onboard video obtained by flight test.

A universal approximation of grain size from images of noncohesive sediment

The two‐dimensional spectral decomposition of an image of sediment provides a direct statistical estimate, grid‐by‐number style, of the mean of all intermediate axes of all single particles within the image. We develop and test this new method which, unlike existing techniques, requires neither image processing algorithms for detection and measurement of individual grains, nor calibration. The only information required of the operator is the spatial resolution of the image. The method is tested with images of bed sediment from nine different sedimentary environments (five beaches, three rivers, and one continental shelf), across the range 0.1 mm to 150 mm, taken in air and underwater. Each population was photographed using a different camera and lighting conditions. We term it a “universal approximation” because it has produced accurate estimates for all populations we have tested it with, without calibration. We use three approaches (theory, computational experiments, and physical experiments) to both understand and explore the sensitivities and limits of this new method. Based on 443 samples, the root‐mean‐squared (RMS) error between size estimates from the new method and known mean grain size (obtained from point counts on the image) was found to be ±≈16%, with a 95% probability of estimates within ±31% of the true mean grain size (measured in a linear scale). The RMS error reduces to ≈11%, with a 95% probability of estimates within ±20% of the true mean grain size if point counts from a few images are used to correct bias for a specific population of sediment images. It thus appears it is transferable between sedimentary populations with different grain size, but factors such as particle shape and packing may introduce bias which may need to be calibrated for. For the first time, an attempt has been made to mathematically relate the spatial distribution of pixel intensity within the image of sediment to the grain size.

Computer Vision Onboard UAVs for Civilian Tasks

Computer vision is much more than a technique to sense and recover environmental information from an UAV. It should play a main role regarding UAVs' functionality because of the big amount of information that can be extracted, its possible uses and applications, and its natural connection to human driven tasks, taking into account that vision is our main interface to world understanding. Our current research's focus lays on the development of techniques that allow UAVs to maneuver in spaces using visual information as their main input source. This task involves the creation of techniques that allow an UAV to maneuver towards features of interest whenever a GPS signal is not reliable or sufficient, e.g. when signal dropouts occur (which usually happens in urban areas, when flying through terrestrial urban canyons or when operating on remote planetary bodies), or when tracking or inspecting visual targets--including moving ones--without knowing their exact UMT coordinates. This paper also investigates visual servoing control techniques that use velocity and position of suitable image features to compute the references for flight control. This paper aims to give a global view of the main aspects related to the research field of computer vision for UAVs, clustered in four main active research lines: visual servoing and control, stereo-based visual navigation, image processing algorithms for detection and tracking, and visual SLAM. Finally, the results of applying these techniques in several applications are presented and discussed: this study will encompass power line inspection, mobile target tracking, stereo distance estimation, mapping and positioning.

A novel automatic image processing algorithm for detection of hard exudates based on retinal image analysis

We present an automatic image processing algorithm to detect hard exudates. Automatic detection of hard exudates from retinal images is an important problem since hard exudates are associated with diabetic retinopathy and have been found to be one of the most prevalent earliest signs of retinopathy. The algorithm is based on Fisher's linear discriminant analysis and makes use of colour information to perform the classification of retinal exudates. We prospectively assessed the algorithm performance using a database containing 58 retinal images with variable colour, brightness, and quality. Our proposed algorithm obtained a sensitivity of 88% with a mean number of 4.83 ± 4.64 false positives per image using the lesion-based performance evaluation criterion, and achieved an image-based classification accuracy of 100% (sensitivity of 100% and specificity of 100%).

Utilisation of the image analysis method for the detection of the morphological anisotropy of calcite grains in marble

This paper presents the development and utilisation of an automated image processing algorithm for detection and analysis of grains. Using optical polarising microscopy, a set of colored images are collected from an area on a thin section. A filtering operation, using rotation of a morphological alternating sequence filter (based on a structuring element), is used to remove twinning features within individual grains. Filtering is followed by the watershed segmentation technique to determine grain boundaries. The method is used for the identification of calcite grains in marble and the subsequent analysis of morphological anisotropy.