1. Pig weight estimation according to RGB image analysisAndras Kárpinszky, Gergely Dobsinszki, 2023, original scientific article Abstract: In pig farming, knowing the exact weight of each animal is critical for the owner. Such information can help determine the amount and type of feed that needs to be fed to a specific fattening pig. Weighing pigs has always been problematic, because it is highly time consuming, and herding the pigs on the scale is extremely cumbersome. Moreover, it causes stress to the animals. The aim of our study was to build an RGB-based system that could estimate the daily weight of pigs and individual animal weight. The study was set up in a 100-day rotation in a commercial pig farm where we monitored 32 pigs. We developed a system to identify the features of the pigs, more particularly the head, shoulder, belly, and rump part. Three different models
were tested, and their main differences were linked to image processing and training data. Using these models, we received higher than 97% accuracy between the predicted and the manually recorded weight of the animals. This system allows owners to manage and monitor their pigs using our web interface, allowing them to make crucial decisions during the farming process.
Keywords: image processing, pig size, decision support system, precision livestock farming
Published in DKUM: 25.04.2025; Views: 0; Downloads: 1
 Link to file |
2. DigiPig : First developments of an automated monitoring system for body, head and tail detection in intensive pig farmingMarko Ocepek, Anja Žnidar, Miha Lavrič, Dejan Škorjanc, Inger Lise Andersen, 2022, original scientific article Abstract: The goal of this study was to develop an automated monitoring system for the detection of pigs’ bodies, heads and tails. The aim in the first part of the study was to recognize individual pigs (in lying and standing positions) in groups and their body parts (head/ears, and tail) by using machine learning algorithms (feature pyramid network). In the second part of the study, the goal was to improve the detection of tail posture (tail straight and curled) during activity (standing/moving around) by the use of neural network analysis (YOLOv4). Our dataset (n = 583 images, 7579 pig posture) was annotated in Labelbox from 2D video recordings of groups (n = 12–15) of weaned pigs. The model recognized each individual pig’s body with a precision of 96% related to threshold intersection over union (IoU), whilst the precision for tails was 77% and for heads this was 66%, thereby already achieving human-level precision. The precision of pig detection in groups was the highest, while head and tail detection precision were lower. As the first study was relatively time-consuming, in the second part of the study, we performed a YOLOv4 neural network analysis using 30 annotated images of our dataset for detecting straight and curled tails. With this model, we were able to recognize tail postures with a high level of precision (90%).
Keywords: pig, welfare, image processing, object detection, deep learning, smart farming
Published in DKUM: 11.07.2024; Views: 87; Downloads: 9
 Full text (48,11 MB)
This document has many files! More... |
3. A VAN-Based Multi-Scale Cross-Attention Mechanism for Skin Lesion Segmentation NetworkShuang Liu, Zeng Zhuang, Yanfeng Zheng, Simon Kolmanič, 2023, original scientific article Abstract: With the rise of deep learning technology, the field of medical image segmentation has undergone rapid development. In recent years, convolutional neural networks (CNNs) have brought many achievements and become the consensus in medical image segmentation tasks. Although many neural networks based on U-shaped structures and methods, such as skip connections have achieved excellent results in medical image segmentation tasks, the properties of convolutional operations limit their ability to effectively learn local and global features. To address this problem, the Transformer from the field of natural language processing (NLP) was introduced to the image segmentation field. Various Transformer-based networks have shown significant performance advantages over mainstream neural networks in different visual tasks, demonstrating the huge potential of Transformers in the field of image segmentation. However, Transformers were originally designed for NLP and ignore the multidimensional nature of images. In the process of operation, they may destroy the 2D structure of the image and cannot effectively capture low-level features. Therefore, we propose a new multi-scale cross-attention method called M-VAN Unet, which is designed based on the Visual Attention Network (VAN) and can effectively learn local and global features. We propose two attention mechanisms, namely MSC-Attention and LKA-Cross-Attention, for capturing low-level features and promoting global information interaction. MSC-Attention is designed for multi-scale channel attention, while LKA-Cross-Attention is a cross-attention mechanism based on the large kernel attention (LKA). Extensive experiments show that our method outperforms current mainstream methods in evaluation metrics such as Dice coefficient and Hausdorff 95 coefficient.
Keywords: CNNs, deep learning, medical image processing, NLP, semantic segmentation
Published in DKUM: 14.03.2024; Views: 496; Downloads: 311
Full text (1,46 MB)
This document has many files! More... |
4. Estimating the size of plants by using two parallel viewsBarbara Videc, Jurij Rakun, 2017, original scientific article Abstract: This paper presents a method of estimating the size of plants by using two parallel views of the scene, taken by a common digital camera. The approach relays on the principle of similar triangles with the following constraints: the resolution of the camera is known; the object is always in parallel to the camera sensor and the intermediate distance between the two concessive images is available. The approach was first calibrated and tested using one artificial object in a controlled environment. After that real examples were taken from agriculture, where we measured the distance and the size of a vine plant, apple and pear tree. By comparing the calculated values to measured values, we concluded that the average absolute error in distance was 0.11 m or around 3.7 %, and the absolute error in high was 0.09 m or 4.6 %.
Keywords: digital image processing, size, digital camera, pixels, similar triangles
Published in DKUM: 10.10.2018; Views: 1334; Downloads: 322
Full text (727,92 KB)
This document has many files! More... |
5. Determining the grain size distribution of granular soils using image analysisNihat Dipova, 2017, original scientific article Abstract: Image-processing technology includes storing the images of objects in a computer and processing them with the computer for a specified purpose. Image analysis is the numerical expression of the images of objects by means of mimicking the functioning of the human visual system and the generation of numerical data for calculations that will be made later. Digital image analysis provides the capability for rapid measurement, which can be made in near-real time, for numerous engineering parameters of materials. Recently, image analysis has been used in geotechnical engineering practices. Grain size distribution and grain shape are the most fundamental properties used to interpret the origin and behaviour of soils. Mechanical sieving has some limitations, e.g., it does not measure the axial dimension of a particle, particle shape is not taken into consideration, and especially for elongated and flat particles a sieve analysis will not yield a reliable measure. In this study the grain size distribution of sands has been determined following image-analysis techniques, using simple apparatus, non-professional cameras and open-code software. The sample is put on a transparent plate that is illuminated with a white backlight. The digital images were acquired with a CCD DSLR camera. The segmentation of the particles is achieved by image thresholding, binary coding and particle labeling. The geometrical measurements of each particle are obtained using an automated pixel-counting technique. Local contacts or limited overlaps were overcome using a watershed split. The same sample was tested by traditional sieve analysis. An image-analysis-based grain size distribution has been compared with a sieve-analysis distribution. The results show that the grain size distribution of the image-based analysis and the sieve analysis are in good agreement.
Keywords: image analysis, image processing, grain size, sand
Published in DKUM: 18.06.2018; Views: 1533; Downloads: 165
Full text (1,27 MB)
This document has many files! More... |
6. An overview of image analysis algorithms for license plate recognitionKhalid Aboura, Rami Al-Hmouz, 2017, original scientific article Abstract: Background and purpose: We explore the problem of License Plate Recognition (LPR) to highlight a number of algorithms that can be used in image analysis problems. In management support systems using image object recognition, the intelligence resides in the statistical algorithms that can be used in various LPR steps. We describe a number of solutions, from the initial thresholding step to localization and recognition of image elements. The objective of this paper is to present a number of probabilistic approaches in LPR steps, then combine these approaches together in one system. Most LPR approaches used deterministic models that are sensitive to many uncontrolled issues like illumination, distance of vehicles from camera, processing noise etc. The essence of our approaches resides in the statistical algorithms that can accurately localize and recognize license plate.
Design/Methodology/Approach: We introduce simple and inexpensive methods to solve relatively important problems, using probabilistic approaches. In these approaches, we describe a number of statistical solutions, from the initial thresholding step to localization and recognition of image elements. In the localization step, we use frequency plate signals from the images which we analyze through the Discrete Fourier Transform. Also, a probabilistic model is adopted in the recognition of plate characters. Finally, we show how to combine results from bilingual license plates like Saudi Arabia plates.
Results: The algorithms provide the effectiveness for an ever-prevalent form of vehicles, building and properties management. The result shows the advantage of using the probabilistic approached in all LPR steps. The averaged classification rates when using local dataset reached 79.13%.
Conclusion: An improvement of recognition rate can be achieved when there are two source of information especially of license plates that have two independent texts.
Keywords: image analysis, probabilistic modeling, signal processing, license plate recognition
Published in DKUM: 28.11.2017; Views: 1501; Downloads: 367
Full text (1,01 MB)
This document has many files! More... |
7. The accuracy of the germination rate of seeds based on image processing and artificial neural networksUroš Škrubej, Črtomir Rozman, Denis Stajnko, 2015, original scientific article Abstract: This paper describes a computer vision system based on image processing and machine learning techniques which was implemented for automatic assessment of the tomato seed germination rate. The entire system was built using open source applications Image J, Weka and their public Java classes and linked by our specially developed code. After object detection, we applied artificial neural networks (ANN), which was able to correctly classify 95.44% of germinated seeds of tomato (Solanum lycopersicum L.).
Keywords: image processing, artificial neural networks, seeds, tomato
Published in DKUM: 14.11.2017; Views: 1588; Downloads: 502
Full text (353,43 KB)
This document has many files! More... |
8. Intelligent system for prediction of mechanical properties of material based on metallographic imagesMatej Paulič, David Močnik, Mirko Ficko, Jože Balič, Tomaž Irgolič, Simon Klančnik, 2015, original scientific article Abstract: This article presents developed intelligent system for prediction of mechanical properties of material based on metallographic images. The system is composed of two modules. The first module of the system is an algorithm for features extraction from metallographic images. The first algorithm reads metallographic image, which was obtained by microscope, followed by image features extraction with developed algorithm and in the end algorithm calculates proportions of the material microstructure. In this research we need to determine proportions of graphite, ferrite and ausferrite from metallographic images as accurately as possible. The second module of the developed system is a system for prediction of mechanical properties of material. Prediction of mechanical properties of material was performed by feed-forward artificial neural network. As inputs into artificial neural network calculated proportions of graphite, ferrite and ausferrite were used, as targets for training mechanical properties of material were used. Training of artificial neural network was performed on quite small database, but with parameters changing we succeeded. Artificial neural network learned to such extent that the error was acceptable. With the oriented neural network we successfully predicted mechanical properties for excluded sample.
Keywords: artificial neural network, factor of phase coherence between the surfaces, fracture toughness, image processing, mechanical properties, metallographic image, ultimate tensile strength, yield strength
Published in DKUM: 12.07.2017; Views: 1554; Downloads: 437
Full text (2,02 MB)
This document has many files! More... |
9. |
10. Computer-based workpiece detection on CNC milling machine tools using optical camera and neural networksSimon Klančnik, Jernej Šenveter, 2010, original scientific article Abstract: In this paper, system for optical determining the workpiece origin on the CNC machine is presented. Similar high sophisticated systems are commercially available but in most cases they are very expensive and so their purchase is economically unjustified. The purpose of our research is to develop an inexpensive system for non-contact determination of the workpiece origin, which is also sufficiently precise for practical use. The system is implemented on a three-axis CNC milling machine Lakos 150 G, which is primarily designed for good machinability materials. Calibration procedure using feed-forward neural networks was developed. With this method the calibration procedure is simplified and the mathematical derivation of camera model is avoided. Learned neural network represents the camera calibration model. After neural network learning is complete, we can begin using the system for determining the workpiece origin. This developed system was through a number of tests proved to be reliable and suitable for use in practice. In the paper, working of system is illustrated with a practical example, which confirms the effectiveness of the implemented system in actual use on machine.
Keywords: neural networks, image processing, milling, workpiece detection
Published in DKUM: 01.06.2012; Views: 2064; Downloads: 44
Link to full text |
