Morphological Dilation Operation Research Articles

A Multi-Target Identification and Positioning System Method for Tomato Plants Based on VGG16-UNet Model

The axillary buds that grow between the main and lateral branches of tomato plants waste nutrients and lead to a decrease in yield, necessitating regular removal. Currently, these buds are removed manually, which requires substantial manpower and incurs high production costs, particularly on a large scale. Replacing manual labor with robots can lead to cost reduction. However, a critical challenge is the accurate multi-target identification of tomato plants and precise positioning for axillary bud removal. Therefore, this paper proposes a multi-target identification and localization method for tomato plants based on the VGG16-UNet model. The average intersection and pixel accuracies of the VGG16-UNet model after introducing the pretrained weights were 85.33% and 92.47%, respectively, which were 5.02% and 4.08% higher than those of the VGG16-UNet without pretrained weights, achieving the identification of main branches, side branches, and axillary bud regions. Then, based on the multi-objective segmentation of the tomato plants in the VGG16-UNet model, the regions of the axillary buds in the tomato plants were identified by HSV color space conversion and color threshold range selection. Morphological dilation and erosion operations were used to remove noise and connect adjacent regions of the same target. The endpoints and centroids of the axillary buds were identified using the feature point extraction algorithm. The left and right positions of the axillary buds were judged by the relationship between the position of the axillary bud centroid and the position of the main branch. Finally, the coordinate parameters of the axillary bud removal points were calculated using the feature points to determine the relationship between the position of the axillary bud and the position of the branch. Experimental results showed that the average accuracy of the axillary bud pruning point recognition was 85.5%.

An efficient algorithm for areal morphological filter

This article discusses morphological filtering for assessing a areal parameters of a texture of engineering products. A data organization structure has been proposed that makes it possible to increase the efficiency of an iterative algorithm for enumerating a surface coordinates. Morphological filters complement the standard Gaussian filter to evaluate the functional properties of a surface. The widespread use of the areal morphological filtering in metrological practice is currently hampered by the lack of an effective algorithm. An algorithm based on a matrix representation of morphological operations on the surface coordinates is presented. For this purpose, different indexing of points on a primary surface and a structuring element has been introduced. A sphere or flat segment is used as the structuring element. The high performance of the developed algorithm is ensured due to the fact that all calculations are carried out by enumerating the surface coordinates in one pass, without nested loops, as in some other algorithms. Algorithms for morphological operations of dilation and erosion are presented, on the basis of which a closing and opening filters are constructed. Simulations carried out for various data sets and comparison with known morphological filtering algorithms confirmed the high efficiency of the designed algorithm. The results obtained can be used to analyze the functional properties of product surfaces.

Assessment of satellite-derived shorelines automatically extracted from Sentinel-2 imagery using SAET

The definition of the shoreline position from satellite imagery is of great interest among coastal monitoring techniques. Understanding the reality mapped by the resulting shorelines and defining their accuracy is of paramount importance. The assessment described in this paper constitutes a validation of the shorelines obtained by using the novel tool SAET (Shoreline Analysis and Extraction Tool) for automatic shoreline extraction. The resulting shorelines applying the different parameters available in SAET are assessed in 9 test sites with diverse morphology and oceanographic conditions along the Atlantic European and Western Mediterranean coasts. The reference data is obtained along large coastal segments (covering up to about 240 km) from nearly coincident very high-resolution satellite images.Different image processing levels and extraction methods have been tested, showing their key role in the accuracy of shoreline position. When defining the approximate shoreline position the Automated Water Extraction Index for images without shadows (AWEInsh) with a 0 threshold generally constitutes the best segmentation method. In turn, the employment of the mathematical morphological operations of dilation or erosion considerably improves the results in certain coastal typologies. On the contrary, the employment of atmospherically-corrected images has a smaller influence on the accuracy of the SDSs.Results support the idea that the magnitude of the errors is strongly related to the specific coastal conditions- In general, the lowest errors appear in low-energetic microtidal sites, contrary to the energetic and mesotidal coasts with gentle slopes.The shoreline errors range between 3.7 m and 13.5 m RMSE (root-mean-square error) among the different coastal types when selecting the most appropriate extraction parameters. The shoreline position identified with SAET shows a similar or better accuracy to that obtained by other tools.

Sub-Pixel Surface Water Mapping for Heterogeneous Areas from Sentinel-2 Images: A Case Study in the Jinshui Basin, China

Mapping high-spatial-resolution surface water bodies in urban and suburban areas is crucial in understanding the spatial distribution of surface water. Although Sentinel-2 images are popular in mapping water bodies, they are impacted by the mixed-pixel problem. Sub-pixel mapping can predict finer-spatial-resolution maps from the input remote sensing image and reduce the mixed-pixel problem to a great extent. This study proposes a sub-pixel surface water mapping method based on morphological dilation and erosion operations and the Markov random field (DE_MRF) to predict a 2 m resolution surface water map for heterogeneous regions from Sentinel-2 imagery. DE_MRF first segments the normalized difference water index image to extract water pixels and then detects the mixed pixels by using combined morphological dilation and erosion operations. For the mixed pixels, DE_MRF considers the intra-pixel spectral variability by extracting multiple water endmembers and multiple land endmembers within a local window to generate the water fraction images through spectral unmixing. DE_MRF was evaluated in the Jinshui Basin, China. The results suggested that DE_MRF generated a lower commission error rate for water pixels compared to the comparison methods. Because DE_MRF considers the intra-class spectral variabilities in the unmixing, it is better in mapping sub-pixel water distribution in heterogeneous regions where different water bodies with distinct spectral reflectance are present.

Brain tumour detection in magnetic resonance imaging using Levenberg–Marquardt backpropagation neural network

Magnetic resonance imaging (MRI) is a high-quality medical image that is used to detect brain tumours in a complex and time-consuming manner. In this study, a back propagation neural network (BPNN) along with the Levenberg–Marquardt algorithm (LMA) is proposed to classify MRIs and diagnose brain tumours in a simple and fast process. The BPNN has 10 neurons in the hidden layer, and the default function of the feedforward feeds is mean squared error (MSE). The LMA is optimized as a multivariable adaptive approach and considerably decreases the MSE of the BPNN, so the errors of the tumour classification are diminished. The proposed method follows four steps including preprocessing, skull removal, feature extraction, and classification. The input MRIs are converted to greyscale, resized, and thresholding is performed in the preprocessing step and followed by skull removal. Morphological operations of closing, opening, and dilation are used to segment abnormal areas in the MRIs, and the opening operator recognizes the tumour more accurately. Using statistical analysis and a grey-level co-occurrence matrix (GLCM) 12 features are extracted from the MRIs and used as the inputs of the BPNN. To evaluate the proposed method, 670 normal and 670 abnormal brain MRIs are used as input data, and the classification is performed in 0.494 s. The accuracy, sensitivity, specificity, precision, dice, recall, and MSE are 98.7%, 97.61%, 99.7%, 97.61%, 98.6%, 97.61%, and 0.005, respectively. The approach is accurate and fast for medical images classification.

Real-Time Computer Vision-Based Bangla Vehicle License Plate Recognition using Contour Analysis and Prediction Algorithm

Computer vision-based recognition of Bangle vehicle license plates (LPs) is an arduous task in dirty and muddy situations. This paper proposes an efficient method for real-time computer vision-based recognition of Bangla vehicle LPs using contour analysis and prediction algorithms. The method initially applies gray scaling the input RGB images, histogram equalization to improve the grayscale image quality, edge detection using Sobel edge detector, and adaptive thresholding to convert it to a binary image. The system localizes the vehicle LP based on the maximum rectangular contour area and converts it into a predefined size. Noise removal technique using morphological dilation and erosion operation is used, followed by Gaussian filtering on binary image to improve the image quality further. The system clusters the two-lined LP into seven clusters. The sub-clustering is applied on specific clusters and makes 68 individual sub-clusters. The system extracts vector contour (VC) from each 68 individual classes. After VC extraction, the system normalizes it into a q predefined length. The system applies inter co-relation function (ICF) to categorize each sub-cluster to its previously defined individual class. For that, it calculates the maximum similarity between test and previously trained VCs. The system applies the dependency prediction algorithm in parallel to predict the whole string (district name) in the cluster-1 based on previously categorized class or classes (starting character or characters of the district part). (Metro) or (null) from cluster-2, “-” (hyphen) from cluster-3 and 6 are predicted automatically as their positions are fixed. The system is trained using 68 classes in which each class contains 100 samples generated by the augmentation technique. The system is tested using another set of 68 classes with a total of [Formula: see text] images acquiring the recognition accuracy of 96.62% with the mean computational cost of 8.363[Formula: see text]ms/f. The system is also tested using 500 vehicle whole Bangla LPs achieving the mean whole LP recognition accuracy of 95.41% with a mean computational cost of 35.803[Formula: see text]ms/f.

Application of morphological processing methods in computer stereo vision

Computer vision algorithms are important for many areas of human activity. In particular, the number of applications related to the need to process images of real-world objects with computerized tools and the subsequent use of descriptive information in a variety of interactive and automated decision-making systems is increased. An important tool for analyzing real-world scenes are approaches to the application of stereo vision algorithms. The important step of many stereo matching algorithms is a disparity map. Depending on the content of the observed scene, part of the values on the disparity map can be immediately attributed to background values on a certain basis, or form a "natural" background, which is characterized by loss of informative data due to unacceptable error of subsequent resultant distance values. The calculated disparity map of any algorithm may contain some shortcomings in the form of discontinuities of continuous information areas caused by the complexity of shooting conditions, the impact of noise of various natures, hardware imperfections, and so on. An approach to mitigating the undesirable influence of negative factors on the resulting disparity is the use of mathematical morphology operations to process disparity maps at the post-processing stage. This paper presents information technology for increasing the content of disparity maps based on the mathematical morphology methods. The technology is based on a combination of morphological operations of erosion and dilation, which eliminates the typical problems of discontinuities of monotone regions and erroneous values on disparity maps. The proposed approach allows reducing the impact of common problems that arise during the operation of stereo matching algorithms, as well as increase the overall informativeness of disparity maps for images of real objects in the absence of partial or complete initial data on the characteristics of the observed scene. The results of testing morphological operations with disparity maps for real objects allow us to conclude about the possibility of partial restoration of areas of disparity maps with gaps in continuous information areas, as well as to reduce the impact of random anomalous values on the overall content of the disparity maps.

Mathematical morphology directly applied to point cloud data

Many of the point cloud processing techniques have their origin in image processing. But mathematical morphology, despite being one of the most used image processing techniques, has not yet been clearly adapted to point clouds. The aim of this work is to design the basic operations of mathematical morphology applicable to 3D point cloud data, without the need to transform point clouds to 2D or 3D images and avoiding the associated problems of resolution loss and orientation restrictions. The object shapes in images, based on pixel values, are assumed to be the existence or absence of points, therefore, morphological dilation and erosion operations are focused on the addition and removal of points according to the structuring element. The structuring element, in turn, is defined as a point cloud with characteristics of shape, size, orientation, point density, and one reference point. The designed method has been tested on point clouds artificially generated, acquired from real case studies, and the Stanford bunny model. The results show a robust behaviour against point density variations and consistent with image processing equivalent. The proposed method is easy and fast to implement, although the selection of a correct structuring element requires previous knowledge about the problem and the input point cloud. Besides, the proposed method solves well-known point cloud processing problems such as object detection, segmentation, and gap filling.

Content-aware specular reflection suppression based on adaptive image inpainting and neural network for endoscopic images

In this article, a content-aware specular reflection suppression scheme was developed based on adaptive image inpainting and neural network for endoscopic images. To decrease the impact of specular reflection on visual quality, the proposed scheme consists of three parts: reflection detection, reflection region classification, and reflection concealment. To automatically locate specular reflection regions, a thresholding algorithm with a morphological dilation operation is employed. To reduce the effect of specular reflection, an adaptive image inpainting algorithm is devised to deal with different reflection regions. To achieve content-aware image inpainting, a reflection region classification algorithm is designed by analyzing the local image content to adjust the parameters in the proposed image inpainting algorithm. The experimental results demonstrate that the proposed scheme can automatically and correctly not only locate but also conceal specular reflection regions in endoscopic images. Furthermore, since the average SSIM (structural similarity index) value of the proposed scheme is higher than those of the existing methods, our specular reflection suppression scheme is superior to the existing methods.

Impact of boosting saturation on automatic human detection in imagery acquired by unmanned aerial vehicles

We aim to investigate a potential impact of boosting saturation of aerial imagery on the performance of unsupervised human detection algorithms. The study is empirical since it is based on processing photographs taken during a full year experiment in the Izerskie Mountains (southwestern Poland) by a consumer-grade Canon S110 camera mounted onboard eBee, a fixed-wing micro-unmanned aerial vehicle (UAV). In the preliminary analysis, we used a few basic color adjustments (sharpening, hue–saturation–luminance, contrast, saturation, and vibrance) to process UAV-taken photographs prior to the automated human detection with the nested k -means algorithm. We found that saturation boost is an image preprocessing method that may potentially improve the performance of human detection. In the actual analysis, we investigate only the saturation effect by employing four saturation modification schemes (two versions of enhancements of unusual colors, additive boost of saturation, and multiplicative boost of saturation) and three human detection algorithms [three-dimensional (3-D) nested k -means on RGB, two-dimensional nested k -means on hue–saturation–value, morphological operations of erosion, and dilation with thresholding]. All the studied saturation boost techniques increase detection rates of the 3-D nested k -means on RGB, with particularly meaningful improvement for images acquired in the spring. Morphological operations of erosion and dilation are not found to be skillful in detecting persons. However, their performance is improved after the initial preprocessing by the original or modified enhancement of unusual colors.

Shape Feature Extraction Methods of Rodents in the Field Based on Machine Vision

In order to obtain the shape features of rodents from the field, a feature extraction scheme based on machine vision was proposed. We design an experimental device with a camera. The camera placed on the top of the device to get the rodent image. After thresholding rodent image based on the global value, we get the binary image, and then the morphological erosion and dilation operation are used to denoise, and the contour are detected by the 8 adjacent pixels of a point. Chain code analysis method is used to track the contour. Multi-contour tracking extraction method is used to remove the non-rodent region. Based on the shape of the rodent tail that is slenderer than the body, we split the rodent’s tail from the body on the precise contour image. The length of the tail, the length of the body, the height of the body, the proportions of the tail and the body are extract based on contour analysis. Experiments show that this method can extract shape features of rodents accurately. It can provide basic data for analyzing the life habits and population evolution of field rodents.

Subpixel Surface Water Extraction (SSWE) Using Landsat 8 OLI Data

Surface water extraction from remote sensing imagery has been a very active research topic in recent years, as this problem is essential for monitoring the environment, ecosystems, climate, and so on. In order to extract surface water accurately, we developed a new subpixel surface water extraction (SSWE) method, which includes three steps. Firstly, a new all bands water index (ABWI) was developed for pure water pixel extraction. Secondly, the mixed water–land pixels were extracted by a morphological dilation operation. Thirdly, the water fractions within the mixed water–land pixels were estimated by local multiple endmember spectral mixture analysis (MESMA). The proposed ABWI and SSWE have been evaluated by using three data sets collected by the Landsat 8 Operational Land Imager (OLI). Results show that the accuracy of ABWI is higher than that of the normalized difference water index (NDWI). According to the obtained surface water maps, the proposed SSWE shows better performance than the automated subpixel water mapping method (ASWM). Specifically, the root-mean-square error (RMSE) obtained by our SSWE for the data sets considered in experiments is 0.117, which is better than that obtained by ASWM (0.143). In conclusion, the SSWE can be used to extract surface water with high accuracy, especially in areas with optically complex aquatic environments.

Coupling the Modified Linear Spectral Mixture Analysis and Pixel-Swapping Methods for Improving Subpixel Water Mapping: Application to the Pearl River Delta, China

High-resolution water mapping with remotely sensed data is essential to monitoring of rainstorm waterlogging and flood disasters. In this study, a modified linear spectral mixture analysis (LSMA) method is proposed to extract high-precision water fraction maps. In the modified LSMA, the pure water and mixed water-land pixels, which are extracted by the Otsu method and a morphological dilation operation, are used to improve the accuracy of water fractions. The modified LSMA is applied to the 18 October 2015 Landsat 8 OLI image of the Pearl River Delta for the extraction of water fractions. Based on the water fraction maps, a modified subpixel mapping method (MSWM) based on a pixel-swapping algorithm is proposed for obtaining the spatial distribution information of water at subpixel scale. The MSWM includes two steps in subpixel water mapping. The MSWM considers the inter-subpixel/pixel and intra-subpixel/subpixel spatial attractions. Subpixel water mapping is first implemented with the inter-subpixel/pixel spatial attractions, which are estimated using the distance between a given subpixel and its surrounding pixels and the water fractions of the surrounding pixels. Based on the initialized subpixel water mapping results, the final subpixel water maps are determined by a modified pixel-swapping algorithm, in which the intra-subpixel/subpixel spatial attractions are estimated using the initialized subpixel water maps and an inverse-distance weighted function of the current subpixel at the centre of a moving window with its surrounding subpixels within the window. The subpixel water mapping performance of the MSWM is compared with that of subpixel mapping for linear objects (SPML) and that of the subpixel/pixel spatial attraction model (SPSAM) using the GF-1 reference image from 20 October 2015. The experimental results show that the MSWM shows better subpixel water mapping performance and obtains more details than SPML and SPSAM, as it has the largest overall accuracy values and Kappa coefficients. Furthermore, the MSWM can significantly eliminate the phenomenon of jagged edges and has smooth continuous edges.

Automatic segmentation of optic disk in retinal images

Abstract In this paper a new algorithm is presented for automatic segmentation of the optic disk (OD) in human retinal images. In proposed method, an equiripple low pass finite impulse response (FIR) filter is designed to suppress the dominance of blood vessels and to enhance the OD region in retinal image. Desired frequency response with optimized order of the filter is achieved by choosing proper values of filter design parameters. This method computes the appropriate value of threshold to locate the OD in retinal image. Segmentation of the OD region is carried out using grayscale morphological dilation and median filtering operation. The proposed algorithm has been tested on four standard databases (DRIVE, DIRATEDB0, DIRATEDB1 and DRIONS database). The proposed algorithm detects the OD successfully with accuracies 100%, 96.92%, 98.98%, 100% on DRIVE, DIRATEDB0, DIRATEDB1 and DRIONS databases respectively. The OD segmentation sensitivity and specificity are in the range of 74.60–87.07%, 99.39–99.61% on these four databases. The proposed algorithm has low computation complexity as it takes low computation time to segment the OD over existing methods. Also it is robust to differences in image illumination and retinal anomalies. Hence the proposed method can be used for automatic screening system of retinal related diseases like glaucoma and diabetic retinopathy.

An Innovative Moving Object Detection and Tracking System by Using Modified Region Growing Algorithm

The ultimate goal of this study is to afford enhanced video object detection and tracking by eliminating the limitations which are existing nowadays. Although high performance ratio for video object detection and tracking is achieved in the earlier work it takes more time for computation. Consequently we are in need to propose a novel video object detection and tracking technique so as to minimize the computational complexity. Our proposed technique covers five stages they are preprocessing, segmentation, feature extraction, background subtraction and hole filling. Originally the video clip in the database is split into frames. Then preprocessing is performed so as to get rid of noise, an adaptive median filter is used in this stage to eliminate the noise. The preprocessed image then undergoes segmentation by means of modified region growing algorithm. The segmented image is subjected to feature extraction phase so as to extract the multi features from the segmented image and the background image, the feature value thus obtained are compared so as to attain optimal value, consequently a foreground image is attained in this stage. The foreground image is then subjected to morphological operations of erosion and dilation so as to fill the holes and to get the object accurately as these foreground image contains holes and discontinuities. Thus the moving object is tracked in this stage. This method will be employed in MATLAB platform and the outcomes will be studied and compared with the existing techniques so as to reveal the performance of the novel video object detection and tracking technique.

A collaborative client participant fusion system for realistic remote conferences

Remote conferencing systems provide a shared environment where people in different locations can communicate and collaborate in real time. Currently, remote video conferencing systems present separate video images of the individual participants. To achieve a more realistic conference experience, we enhance video conferencing by integrating the remote images into a shared virtual environment. This paper proposes a collaborative client participant fusion system using a real-time foreground segmentation method. In each client system, the foreground pixels are extracted from the participant images using a feedback background modeling method. Because the segmentation results often contain noise and holes caused by adverse environmental lighting conditions and substandard camera resolution, a Markov Random Field model is applied in the morphological operations of dilation and erosion. This foreground segmentation refining process is implemented using graphics processing unit programming, to facilitate real-time image processing. Subsequently, segmented foreground pixels are transmitted to a server, which fuses the remote images of the participants into a shared virtual environment. The fused conference scene is represented by a realistic holographic projection.

A New Morphology-based Method for Text Detection in Image and Video

Text supply crucial suggestions for understanding video content, also the information that the text convey is much more concise than corresponding audio or video. The reason is that we need language knowledge to understand the text, and the knowledge itself does not need to be embedded in the text data. Text streams contain very rich semantic information. How to effectively extract information from text is an important component in video content analysis and semantics research. In this paper, a new morphology-based method for text detection in image and video is proposed. It consists of three major stages. In the first stage, the input color image is converted to gray-scale, a morphological binary map is generated by calculating the difference between the closing image and the opening image, and a binarization is performed. In the second stage, candidate regions are connected by using a morphological dilation and erosion operations. In the last stage, the extracted regions are verified based on characteristic of text regions to eliminate non text regions.

화소 밝기와 객체 이동을 이용한 비디오 샷 경계 탐지 알고리즘

비디오 데이터를 효율적으로 검색, 정렬, 탐색, 분류하기 위해서는 프레임 간의 샷 전환 탐지가 선행되어야 한다. 프레임 간 화소 밝기와 객체 이동은 높은 탐지율을 보장하는 샷 탐지 알고리즘이 극복해야할 문제이다. 본 논문에서는 프레임의 블록화 및 객체의 이동과 프레임의 밝기를 고려하는 샷 탐지 방법을 제안한다. 먼저 연속하는 두 프레임 사이에서 발생할 수 있는 객체의 이동을 고려하여 계산된 히스토그램과 밝기 차이를 반영하는 모폴러지 팽창 연산을 이용하는 알고리즘을 제안한다. 다음으로 화소 밝기 차를 보상한 프레임 블록의 화소정보와 프레임의 전역적인 밝기 히스토그램의 변화를 함께 이용하는 샷 탐지 방법을 제안한다. 제안된 방법들은 국가기록원 소장 비디오 데이터에 대한 실험에서 화소 또는 히스토그램 기반 알고리즘에 비해 높은 샷 탐지율을 보였다. Shot boundary detection is an essential step for efficient browsing, sorting, and classification of video data. Robust shot detection method should overcome the disturbances caused by pixel brightness and object movement between frames. In this paper, two shot boundary detection methods are presented to address these problem by using segmentation, object movement, and pixel brightness. The first method is based on the histogram that reflects object movements and the morphological dilation operation that considers pixel brightness. The second method uses the pixel brightness information of segmented and whole blocks between frames. Experiments on digitized video data of National Archive of Korea show that the proposed methods outperforms the existing pixel-based and histogram-based methods.

Narrow Band Active Contour Model for Local Segmentation of Medical and Texture Images

A new narrow band active contour model based on binary level set function (LSF) for local segmentation is proposed in this paper. By taking morphological dilation and erosion operations on the binary LSF, a stable and flexible narrow band is built, and the curve evolution precision (CEP) can change from one to infinity flexibly. Considering that the contour will be initialized inside the target object and inflated afterwards in local segmentation, morphological closing operation is utilized to smooth the binary LSF. Comparing with Gaussian filtering and curvature term, morphological closing operation will not only facilitate curve inflation more effectively, but also maintain the binary property of LSF. Moreover, the proposed model is a local segmentation framework, so different speed functions can be designed for different kinds of images. In order to demonstrate the effectiveness and robustness of the framework, we choose medical and texture images as examples. Meanwhile, two speed functions are designed respectively. One is for subcortical brain structures segmentation in MR brain images fused with the non-strict symmetric information, and the other is for texture segmentation combined local entropy and local gradient operators. Experiments on some synthetic, medical and texture images demonstrate the effectiveness and robustness of the proposed method in object segmentation.

Fast Morphological Image Processing Open-Source Extensions for GPU Processing With CUDA

GPU architectures offer a significant opportunity for faster morphological image processing, and the NVIDIA CUDA architecture offers a relatively inexpensive and powerful framework for performing these operations. However, the generic morphological erosion and dilation operation in the CUDA NPP library is relatively naive, and performance scales expensively with increasing structuring element size. The objective of this work is to produce a freely available GPU capability for morphological operations so that fast GPU processing can be readily available to those in the morphological image processing community. Open-source extensions to CUDA (hereafter referred to as LTU-CUDA) have been produced for erosion and dilation using a number of structuring elements for both 8 bit and 32 bit images. Support for 32 bit image data is a specific objective of the work in order to facilitate fast processing of image data from 3D range sensors with high depth precision. Furthermore, the implementation specifically allows scalability of image size and structuring element size for processing of large image sets. Images up to 4096 by 4096 pixels with 32 bit precision were tested. This scalability has been achieved by forgoing the use of shared memory in CUDA multiprocessors. The vHGW algorithm for erosion and dilation independent of structuring element size has been implemented for horizontal, vertical, and 45 degree line structuring elements with significant performance improvements over NPP. However, memory handling limitations hinder performance in the vertical line case providing results not independent of structuring element size and posing an interesting challenge for further optimisation. This performance limitation is mitigated for larger structuring elements using an optimised transpose function, which is not default in NPP, and applying the horizontal structuring element. LTU-CUDA is an ongoing project and the code is freely available at https://github.com/VictorD/LTU-CUDA.