Browsing by Subject "image classification"

Now showing 1 - 7 of 7

Access status: Open Access ,
An evaluation of the capabilities of image-based metal component defect recognition with deep learning techniques
(Wydawnictwa AGH, 2024) Wójcik, Michał P.; Pawlikowski, Kacper; Madej, Łukasz
In the era of Industry 4.0, deploying highly specialised machine learning models trained on unique and often scarce datasets is an attractive solution for advancing automated quality control and minimising production costs. Therefore, the main aim of this research is to evaluate the capabilities of three deep learning models (ResNet-18, ResNet-50 and SE-ResNeXt-101 (32 × 4d)) in the identification of surface defects in forged products. Leveraging advanced photography techniques, including studio lighting and a shadowless box, high-quality images of complex product surfaces were acquired for the training data set. Given the relatively small size of the image dataset, aggressive data augmentation techniques were introduced during the training and evaluation process to ensure robust model generalisation ability. The results obtained demonstrate the significant impact of data augmentation on model performance, highlighting its importance in training and evaluating deep learning models with limited data. This research also emphasises the need for innovative data pre-processing strategies in an efficient and robust machine learning model delivery to the industrial environment.
Access status: Open Access ,
Assessment of approaches for the extraction of building footprints from pléiades images
(Wydawnictwa AGH, 2021) Taha, Lamyaa Gamal El-deen; Ibrahim, Rania Elsayed
The Marina area represents an official new gateway of entry to Egypt and the development of infrastructure is proceeding rapidly in this region. The objective of this research is to obtain building data by means of automated extraction from Pléiades satellite images. This is due to the need for efficient mapping and updating of geodatabases for urban planning and touristic development. It compares the performance of random forest algorithm to other classifiers like maximum likelihood, support vector machines, and backpropagation neural networks over the well-organized buildings which appeared in the satellite images. Images were subsequently classified into two classes: buildings and non-buildings. In addition, basic morphological operations such as opening and closing were used to enhance the smoothness and connectedness of the classified imagery. The overall accuracy for random forest, maximum likelihood, support vector machines, and backpropagation were 97%, 95%, 93% and 92% respectively. It was found that random forest was the best option, followed by maximum likelihood, while the least effective was the backpropagation neural network. The completeness and correctness of the detected buildings were evaluated. Experiments confirmed that the four classification methods can effectively and accurately detect 100% of buildings from very high-resolution images. It is encouraged to use machine learning algorithms for object detection and extraction from very high-resolution images.
Access status: Restricted ,
Geological mapping of North Wazirstan, Pakistan using remotely sensed images
(Data obrony: 2017-10-06) Nawaz, Adil
Wydział Geologii, Geofizyki i Ochrony Środowiska
Digitally enhanced OLI Landsat 8 images were applied for mapping of North Waziristan Pakistan. The territory is rough and without rich vegetation; the exposure of the Waziristan ophiolite, related sedimentary lithologies and inaccessibility to the area made the utilization of Landsat information helpful in this investigation. In the remote sensing investigation, Landsat 8 OLI data were used to make band ratios, band combinations, principal component and image classification methods. Multispectral images were prepared and investigated for this study. On the basis of the image classification techniques; unsupervised classification, five principle lithological units are marked which are giving satisfactory results (about 63.07 %.) when compared with referenced geological map using confusion matrix analysis. The outcomes are very satisfied and need to examine about the utility and confinements of remote sensing strategy on the investigation zone. Further to confirm the results of unsupervised classification, extra investigations might be helpful. As a results, issues confronted during the classification must be considered into all general accuracy.
Access status: Restricted ,
Image classification using neural networks
(Data obrony: 2020-12-11) Żelazko, Rafał
Wydział Informatyki, Elektroniki i Telekomunikacji
Access status: Restricted ,
Lithological and structural mapping of the Sorbas area (Baetic Mts., prov. Almería, Spain) based on remotely sensed images
(Data obrony: 2017-07-07) Tarka, Weronika
Wydział Geologii, Geofizyki i Ochrony Środowiska
Digitally enhanced Landsat 8 images were applied for geological mapping of Sorbas Area in Almeria Province, SE Spain. The terrain without abundant vegetation, with semiarid landscape is promising for remote sensing research. For this study multispectral images were processed and analysed. On the basis of the classification, main lithological units were distinguished, with overall agreement with the reference data of 15,127%. The results are subject to discussion about the utility and limitations of remote sensing method on the study area. Further complimentary studies may be useful. Finally, problems encountered during classification must be factored into the overall accuracy.
Access status: Open Access ,
Manual versus Digital Classification of UAV Images in Oak Phenological Studies
(Wydawnictwa AGH, 2025) Będkowski, Krzysztof
This research concerns the phenological phenomenon of the autumn discolorations of sessile oak leaves as the trees prepare for winter dormancy. Sessile oak trees were categorized into five classes according to the general colors of their crowns: from green to brown. Low-altitude UAV-acquired images from the visible B, G, and R bands were used, compared, and evaluated against the results of several classification methods: those that were carried out in the field, visually based on orthomosaic observations, and four variants of digital classification. The analysis showed that those methods that were based on observer assessments were highly subjective. At the same time, there was also the problem of the reference data to which the results of the individual methods could be referred. It was expected that the analyzed phenomenon of tree-crown discoloration would be better visible in aerial photographs than in field observations"," However, visual color classifications using orthomosaics can be too subjective (as has been shown). It is recommended to use supervised digital classification with a careful selection of reference (training) objects. To switch from pixel-classification results to individual tree classifications, a novel approach was adopted in which the class value that was most abundant within the images of each canopy (determined by the supervised classification method selected) could be used. Among the supervised digital-classification methods that were applied, the results that were closest to the classification performed in the field were obtained by using the ML and Fisher algorithms (followed by kNN).
Access status: Open Access ,
Melanoma skin cancer and nevus mole classification using intensity value estimation with convolutional neural network
(Wydawnictwa AGH, 2023) Ashafuddula, N. I. Md.; Islam, Rafiqul
Melanoma skin cancer is one of the most dangerous and life-threatening cancer. Exposure to ultraviolet rays may damage the skin cell's DNA, which can causes melanoma skin cancer. However, detecting and classifying melanoma and nevus moles at their immature stages is difficult. In this work, an automatic deep-learning system has been developed based on intensity value estimation with a convolutional neural network model (CNN) for detecting and classifying melanoma and nevus moles more accurately. Since intensity levels are the most distinctive features for identifying objects or regions of interest, high-intensity pixel values have been selected from extracted lesion images. Incorporating those high-intensity features into CNN improves the overall performance of the proposed model than the state-of-the-art methods for detecting melanoma skin cancer. To evaluate the system, we used five-fold cross-validation. The experimental results showed that superior percentages of accuracy (92.58%), sensitivity (93.76%), specificity (91.56%), and precision (90.68%) were achieved.